HCI Bibliography Home | HCI Conferences | UBICOMP Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
UBICOMP Tables of Contents: 01020304050607080910111213-113-214-114-215

Proceedings of the 2012 International Conference on Ubiquitous Computing

Fullname:Proceedings of the 2012 ACM Conference on Ubiquitous Computing
Editors:Anind K. Dey; Hao-Hua Chu; Gillian Hayes
Location:Pittsburgh, Pennsylvania
Dates:2012-Sep-05 to 2012-Sep-08
Standard No:ISBN: 978-1-4503-1224-0; ACM DL: Table of Contents; hcibib: UBICOMP12
Links:Conference Website
Summary:On behalf of the entire organizing committee, it is our great pleasure to welcome you to the 14th International Conference on Ubiquitous Computing. This marks the fourth time the UbiComp conference has being held in North America, following Orlando, Florida (2009), Orange County, California (2006), Seattle, Washington (2003) and Atlanta, Georgia (2001). UbiComp truly captures the wide variety of research activities in the diverse field of ubiquitous computing, encompassing research from, e.g., Human Computer Interaction, Mobile Computing, Location and Sensing Technology, Machine Learning, Middleware and Systems, and Programming Models and Tools.
    Each UbiComp conference represents a snapshot of our field, capturing the state-of-the-art in technology, the research challenges we are addressing, as well as the people that form the UbiComp community. Each year's proceedings represent an opportunity to learn about new areas and identify upcoming research opportunities, and this year is no exception. UbiComp 2012 builds upon the tradition by expanding to a dual-track technical program, while still allowing participants to experience the program in a variety of sessions, ranging from context awareness to location sharing, from smartphones to fixed infrastructures, from user experiences to novel interactions, and from persuasive computing to physiological sensing.
    This year our international Program Committee, composed of 45 of the leading researchers in the field of ubiquitous computing, evaluated 301 submissions - 223 full papers and 78 notes. Using a multi-phase review process, after quick-rejecting a small number of incomplete or off-topic submissions, each submission was initially reviewed by at least two members of the program committee and two or more external reviewers. Of the 301 submissions, 67 were evaluated by 1-3 additional PC members. After an online discussion, 11 submissions were auto-accepted and 93 submissions were chosen for further review and discussion at a 2-day PC meeting. In total, the Program Committee and 415 external reviewers spent countless hours to provide feedback to the authors through 1245 reviews. After this rigorous process, a record total of 58 submissions - 50 full papers and 8 notes - were accepted for publication in these proceedings, representing an overall acceptance rate of 19.3%. We are pleased to note this acceptance rate equals the highest in the fourteen-year history of the UbiComp conference thus far. We feel our selective review process has resulted in a high-quality set of published papers. A sub-committee discussed and selected 12 of the 58 accepted papers (equivalent to 4% of the submitted papers) to be recognized in these proceedings for their particular level of quality. Of these 12, 3 stood out as the best papers of UbiComp 2012 (equivalent to 1% of the submitted papers).
  1. Building a smarter smartphone
  2. Where are we going and where have we been?
  3. Sensors and surveillance at home
  4. Health@home
  5. On the body and on the move
  6. Sensemaking, scholarship, and science
  7. Sensing and prediction
  8. Kitchens and closets
  9. Energy at home and in the car
  10. Applications
  11. People as sensors
  12. Physiological sensing
  13. Feelings and emotions
  14. Sensing on and with people
  15. Are we there yet?
  16. Pediatric informatics
  17. Indoor location sensing
  18. Sketching and annotations
  19. Crowdsourcing and bootstrapping
  20. UbiComp at home and in the city
  21. Demos
  22. Doctoral colloquium
  23. Posters
  24. Videos
  25. Pervasive Eye Tracking and Mobile Eye-Based Interaction (PETMEI 2012)
  26. Ubiquitous Mobile Instrumentation (UbiMI)
  27. Context-Awareness for Self-Managing Systems (CASEMANS 2012)
  28. Adaptable Service Delivery in Smart Environments
  29. Computer Mediated Social Offline Interactions (SOFTec 2012)
  30. Smart Gadgets Meet Ubiquitous and Social Robots on the Web (UbiRobots)
  31. Workshop on Location-Based Social Networks (LBSN 2012)
  32. Situation, Activity, and Goal Awareness (SAGAware 2012)
  33. Systems and Intrastructure for the Digital Home (HomeSys)
  34. Methodical Approaches to Prove the Effects of Subliminal Perception in Ubiquitous Computing Environments
  35. Digital Object Memories for the Internet of Things (DOMe-IoT)

Building a smarter smartphone

Improving energy efficiency of personal sensing applications with heterogeneous multi-processors BIBAFull-Text 1-10
  Moo-Ryong Ra; Bodhi Priyantha; Aman Kansal; Jie Liu
The availability of multiple sensors on mobile devices offers a significant new capability to enable rich user and context aware applications. Many of these applications run in the background to continuously sense user context. However, running these applications on mobile devices can impose a significant stress on the battery life, and the use of supplementary low-power processors has been proposed on mobile devices for continuous background activities. In this paper, we experimentally and analytically investigate the design considerations that arise in the efficient use of the low power processor and provide a thorough understanding of the problem space. We answer fundamental questions such as which segments of the application are most efficient to be hosted on the low power processor, and how to select an appropriate low power processor. We discuss our measurements, analysis, and results using multiple low power processors and existing phone platforms.
SAPSM: Smart adaptive 802.11 PSM for smartphones BIBAFull-Text 11-20
  Andrew J. Pyles; Xin Qi; Gang Zhou; Matthew Keally; Xue Liu
Effective WiFi power management can strongly impact the energy consumption on Smartphones. Through controlled experiments, we find that WiFi power management on a wide variety of Smartphones is a largely autonomous process that is processed completely at the driver level. Driver level implementations suffer from the limitation that important power management decisions can be made only by observing packets at the MAC layer. This approach has the unfortunate side effect that each application has equal opportunity to impact WiFi power management to consume more energy, since distinguishing between applications is not feasible at the MAC layer. The power cost difference between WiFi power modes is high (a factor of 20 times when idle), therefore determining which applications are permitted to impact WiFi power management is an important and relevant problem. In this paper we propose SAPSM: Smart Adaptive Power Save Mode. SAPSM labels each application with a priority with the assistance of a machine learning classifier. Only high priority applications affect the client's behavior to switch to CAM or Active mode, while low priority traffic is optimized for energy efficiency. Our implementation on an Android Smartphone improves energy savings by up to 56% under typical usage patterns.

Where are we going and where have we been?

Looking ahead: how field trials can work in iterative and exploratory design of ubicomp systems BIBAFull-Text 21-30
  Matthias Korn; Susanne Bødker
We investigate in which forms field trials are a workable model as part of an exploratory design process for sporadic, mobile, non-work settings. A major concern of evaluating ubicomp systems is to study how practices and context of use emerge and develop over time when new technology is introduced. To introduce a sophisticated version of our own prototype in the course of an iterative design process, we conducted a public field trial of the system -- a new platform for mobile democratic discussions in municipal planning -- that we distributed via the Android Market. However, it turned out to be surprisingly difficult to evaluate our design in a setting that stretches over time, place, and without a preselected set of users. Analyzing our difficulties, we develop a general model for methods studying ubicomp systems. On the basis of this model, we characterize an openly interactive approach to field trials in order to look ahead rather than back.
What next, ubicomp?: celebrating an intellectual disappearing act BIBAFull-Text 31-40
  Gregory D. Abowd
Weiser's landmark Scientific American article inspired many researchers to explore an exciting socio-technical vision of a third generation of computing. At the 21st anniversary of that published vision, I want to assess ubicomp's maturity and explore the identity challenge it faces. Today, ubicomp as a niche research topic no longer makes sense; we must celebrate its "disappearance" as a well-scoped research agenda because it has become a profound agenda across most of computing, and beyond. This should not be surprising; the 2nd generation of computing, the personal computer revolution, experienced the same profound disappearance. In celebration of this imminent disappearance, I will highlight the unique contributions of the ubicomp community, express some remaining intellectual challenges, and speculate on how to formulate new visions of computing that might succeed this third generation.

Sensors and surveillance at home

Long-term effects of ubiquitous surveillance in the home BIBAFull-Text 41-50
  Antti Oulasvirta; Aurora Pihlajamaa; Jukka Perkiö; Debarshi Ray; Taneli Vähäkangas; Tero Hasu; Niklas Vainio; Petri Myllymäki
The Helsinki Privacy Experiment is a study of the long-term effects of ubiquitous surveillance in homes. Ten volunteering households were instrumented with video cameras with microphones, and computer, wireless network, smartphone, TV, DVD, and customer card use was logged. We report on stress, anxiety, concerns, and privacy-seeking behavior after six months. The data provide first insight into the privacy-invading character of ubiquitous surveillance in the home and explain how people can gradually become accustomed to surveillance even if they oppose it.
Being SMART about failures: assessing repairs in SMART homes BIBAFull-Text 51-60
  Krasimira Kapitanova; Enamul Hoque; John A. Stankovic; Kamin Whitehouse; Sang H. Son
Inexpensive wireless sensing products are dramatically reducing the cost of in-home sensing. However, these sensors have been found to fail often and prohibitive maintenance costs may negate the cost benefits of inexpensive hardware and do-it-yourself installation. In this paper, we describe a new technique called SMART that uses application-level semantics to detect, assess, and adapt to sensor failures. SMART detects sensor failures at run-time by analyzing the relative behavior of multiple classifier instances trained to recognize the same set of activities based on different subsets of sensors. Once a failure is detected, SMART assesses its importance and adapts the classifier ensemble in attempt to avoid maintenance dispatch. Evaluation on three homes from two public datasets shows that SMART decreases the number of maintenance dispatches by 55% on average, identifies non-fail-stop failures at run-time with more than 85% accuracy, and improves the activity recognition accuracy under sensor failures by 15% on average.
Investigating receptiveness to sensing and inference in the home using sensor proxies BIBAFull-Text 61-70
  Eun Kyoung Choe; Sunny Consolvo; Jaeyeon Jung; Beverly Harrison; Shwetak N. Patel; Julie A. Kientz
In-home sensing and inference systems impose privacy risks and social tensions, which can be substantial barriers for the wide adoption of these systems. To understand what might affect people's perceptions and acceptance of in-home sensing and inference systems, we conducted an empirical study with 22 participants from 11 households. The study included in-lab activities, four weeks using sensor proxies in situ, and exit interviews. We report on participants' perceived benefits and concerns of in-home sensing applications and the observed changes of their perceptions throughout the study. We also report on tensions amongst stakeholders around the adoption and use of such systems. We conclude with a discussion on how the ubicomp design space might be sensitized to people's perceived concerns and tensions regarding sensing and inference in the home.


"Honey=sugar" means unhealthy: investigating how people apply knowledge to rate food's healthiness BIBAFull-Text 71-80
  Feng Gao; Enrico Costanza; M. C. Schraefel
While previous research studied the high level attributes people consider when they assess the healthiness of food they are familiar with, little work has looked at how people assess arbitrary, potentially unfamiliar, food to decide whether it is a healthy choice. Since there is a growing body of work in Ubicomp around health practices, including systems to support healthy eating, it is important to understand how people apply the knowledge they have to food decisions. In our studies we identified 8 attributes participants use for determining if they think a food is "healthy" or not. Based upon our analysis, we reflect on current system designs and propose four future design opportunities: capturing context of healthy eating, preparation and reflection on healthy eating understanding, sharing understanding and in situ information support.
A spark of activity: exploring informative art as visualization for physical activity BIBAFull-Text 81-84
  Chloe Fan; Jodi Forlizzi; Anind K. Dey
In this note, we describe Spark, an informative art display that visualizes physical activity using abstract art. We present results from five deployments, lasting two to three weeks, that suggest that while graph visualizations are useful for information seeking, abstract visualizations are preferred for display purposes. Our results show that informative art is an appropriate way to visualize physical activity, and can be used in addition to graphs to increase enjoyment and engagement with physical activity displays.
Recognizing water-based activities in the home through infrastructure-mediated sensing BIBAFull-Text 85-94
  Edison Thomaz; Vinay Bettadapura; Gabriel Reyes; Megha Sandesh; Grant Schindler; Thomas Plötz; Gregory D. Abowd; Irfan Essa
Activity recognition in the home has been long recognized as the foundation for many desirable applications in fields such as home automation, sustainability, and healthcare. However, building a practical home activity monitoring system remains a challenge. Striking a balance between cost, privacy, ease of installation and scalability continues to be an elusive goal. In this paper, we explore infrastructure-mediated sensing combined with a vector space model learning approach as the basis of an activity recognition system for the home. We examine the performance of our single-sensor water-based system in recognizing eleven high-level activities in the kitchen and bathroom, such as cooking and shaving. Results from two studies show that our system can estimate activities with overall accuracy of 82.69% for one individual and 70.11% for a group of 23 participants. As far as we know, our work is the first to employ infrastructure-mediated sensing for inferring high-level human activities in a home setting.

On the body and on the move

Attacking location privacy: exploring human strategies BIBAFull-Text 95-98
  Thore Fechner; Christian Kray
The proliferation of location-based services in recent years has highlighted the need to consider location privacy. This has led to the development of methods enhancing location privacy, and to the investigation of reasons for sharing location information. While computational attacks on location privacy and their prevention have attracted a lot of research, attacks based on humans strategies and tactics have mostly been considered implicitly. This note addresses this knowledge gap by reporting on a user study, which we conducted in the context of a location-based game. Participants had to identify other players over the course of several weeks. The results show that human strategies for deanonymization and re-identification can be highly successful and thus pose a threat to location privacy comparable to computational attacks. By incorporating real-world knowledge (that is not easily available in automated attacks), human players were able to efficiently identify other people in the game.
An ultra-low-power human body motion sensor using static electric field sensing BIBAFull-Text 99-102
  Gabe Cohn; Sidhant Gupta; Tien-Jui Lee; Dan Morris; Joshua R. Smith; Matthew S. Reynolds; Desney S. Tan; Shwetak N. Patel
Wearable sensor systems have been used in the ubiquitous computing community and elsewhere for applications such as activity and gesture recognition, health and wellness monitoring, and elder care. Although the power consumption of accelerometers has already been highly optimized, this work introduces a novel sensing approach which lowers the power requirement for motion sensing by orders of magnitude. We present an ultra-low-power method for passively sensing body motion using static electric fields by measuring the voltage at any single location on the body. We present the feasibility of using this sensing approach to infer the amount and type of body motion anywhere on the body and demonstrate an ultra-low-power motion detector used to wake up more power-hungry sensors. The sensing hardware consumes only 3.3 μW, and wake-up detection is done using an additional 3.3 μW (6.6 μW total).
Enhancing communication and dramatic impact of online live performance with cooperative audience control BIBAFull-Text 103-112
  Takuro Yonezawa; Hideyuki Tokuda
Recent progress in information technology enables people to easily broadcast events live on the Internet. Although the advantage of the Internet is live communication between a performer and listeners, the current mode of communication is writing comments using Twitter or Facebook, or some similar messaging network. In one type of live broadcast, musical performances, it is difficult for a musician, when playing an instrument, to communicate with listeners by writing comments. We propose a new communication mode between performers who play musical instruments, and their listeners by enabling listeners to control the performer's camera or illumination remotely. The results of four weeks of experiment confirm the emergence of nonverbal communication between a performer and listeners, and among listeners, which increases camaraderie amongst listeners and performers. Additionally, the dramatic impact of a performance is increased by enabling listeners to control various camera actions such as zoom-in or pan in real time. The results also provide implications for design of future interactive live broadcasting services.
Online pose classification and walking speed estimation using handheld devices BIBAFull-Text 113-122
  Jun-geun Park; Ami Patel; Dorothy Curtis; Seth Teller; Jonathan Ledlie
We describe and evaluate two methods for device pose classification and walking speed estimation that generalize well to new users, compared to previous work. These machine learning based methods are designed for the general case of a person holding a mobile device in an unknown location and require only a single low-cost, low-power sensor: a triaxial accelerometer. We evaluate our methods in straight-path indoor walking experiments as well as in natural indoor walking settings. Experiments with 14 human participants to test user generalization show that our pose classifier correctly selects among four device poses with 94% accuracy compared to 82% for previous work, and our walking speed estimates are within 12-15% (straight/indoor walk) of ground truth compared to 17-22% for previous work. Implementation on a mobile phone demonstrates that both methods can run efficiently online.

Sensemaking, scholarship, and science

Takes a transnational network to raise a child: the case of migrant parents and left-behind Jamaican teens BIBAFull-Text 123-132
  Deana Brown; Rebecca E. Grinter
Migration of parents, in pursuit of 'a better life', has deep roots in Caribbean history and culture. However, the separation from children that results means that care gets provided through a transnational network of caregivers and devices. In this paper we describe how mobile phones in particular have entered a complex care network and while they support some communications they have also contributed to many of the difficulties associated with migration. On the basis of our observations, we conclude with a call for future Ubicomp research into family communication to look to support parenting by considering caregiving networks as wider than just the family. Moreover, this study contributes to our thinking about what 'more' means when introducing additional technologies in family and care networks and their ability to reinforce or shift power structures in the networks in which they are embedded.
Ubicomp's colonial impulse BIBAFull-Text 133-142
  Paul Dourish; Scott D. Mainwaring
Ubiquitous computing has a grand vision. Even the name of the area identifies its universalizing scope. In this, it follows in a long tradition of projects that attempt to create new models and paradigms that unite disparate, distributed elements into a large conceptual whole. We link concerns in ubiquitous computing into a colonial intellectual tradition and identify the problems that arise in consequence, explore the locatedness of innovation, and discuss strategies for decolonizing ubicomp's research methodology.
Exploring interspecies sensemaking: dog tracking semiotics and multispecies ethnography BIBAFull-Text 143-152
  Clara Mancini; Janet van der Linden; Jon Bryan; Andrew Stuart
The domestic use of tracking technology with pets is on the rise, yet is under-researched. We investigate how tracking practices reconfigure human-dog relationships changing both humans and dogs. We question the sensemaking mechanisms by which both humans and dogs engage in context-based meaningful exchanges via the technology's mediation. We show how an indexical semiotic perspective could inform the development of interspecies technology. Finally, we discuss the methodological issues raised by doing research with animals and propose an interspecies semiotics which integrates animal companions and animal researchers' accounts into ethnographic observation.

Sensing and prediction

An unsupervised framework for sensing individual and cluster behavior patterns from human mobile data BIBAFull-Text 153-162
  Jiangchuan Zheng; Lionel M. Ni
Human behavior understanding is a fundamental problem in many ubiquitous applications. It aims to automatically uncover and quantify characteristic behavior patterns in users' daily lives as well as disclose behavior clustering structure among multiple users. The key challenge is how to define a naturally interpreted representation for users' daily behavior patterns, which can be easily exploited to not only uncover the behavior similarity among multiple users but also predict users' future activities. In this paper, we define such a representation, and propose a probabilistic framework which can automatically learn it from mass amount of mobile data in unsupervised setting and exploit it to predict user activities. By an appropriate information sharing among multiple users, this framework overcomes single-user data sparsity problem and effectively identifies behavior clustering structures in a set of users. Experiments conducted on a public reality mining data set demonstrate the effectiveness and accuracy of our methods.
Contextual conditional models for smartphone-based human mobility prediction BIBAFull-Text 163-172
  Trinh Minh Tri Do; Daniel Gatica-Perez
Human behavior is often complex and context-dependent. This paper presents a general technique to exploit this "multidimensional" contextual variable for human mobility prediction. We use an ensemble method, in which we extract different mobility patterns with multiple models and then combine these models under a probabilistic framework. The key idea lies in the assumption that human mobility can be explained by several mobility patterns that depend on a sub-set of the contextual variables and these can be learned by a simple model. We showed how this idea can be applied to two specific online prediction tasks: what is the next place a user will visit? and how long will he stay in the current place?. Using smartphone data collected from 153 users during 17 months, we show the potential of our method in predicting human mobility in real life.
Understanding and prediction of mobile application usage for smart phones BIBAFull-Text 173-182
  Choonsung Shin; Jin-Hyuk Hong; Anind K. Dey
It is becoming harder to find an app on one's smart phone due to the increasing number of apps available and installed on smart phones today. We collect sensory data including app use from smart phones, to perform a comprehensive analysis of the context related to mobile app use, and build prediction models that calculate the probability of an app in the current context. Based on these models, we developed a dynamic home screen application that presents icons for the most probable apps on the main screen of the phone and highlights the most probable one. Our models outperformed other strategies, and, in particular, improved prediction accuracy by 8% over Most Frequently Used from 79.8% to 87.8% (for 9 candidate apps). Also, we found that the dynamic home screen improved accessibility to apps on the phone, compared to the conventional static home screen in terms of accuracy, required touch input and app selection time.

Kitchens and closets

Rethinking the smart closet as an opportunity to enhance the social currency of clothing BIBAFull-Text 183-192
  Jennifer A. Rode; Rachel Magee; Melinda Sebastian; Alan Black; Rachel Yudell; Aly Gibran; Nora McDonald; John Zimmerman
Here we present findings of a needs validation study of 18-25 year old women and their wardrobes. Based on their feedback, we developed a prototype system that allows for borrowing and sharing of information about clothing via Facebook. The novelty of our interface lies in its combining RFID tags and social networking. In doing so we bridge the material and virtual realms and demonstrate the importance of material culture for ubiquitous computing.
The French kitchen: task-based learning in an instrumented kitchen BIBAFull-Text 193-202
  Clare J. Hooper; Anne Preston; Madeline Balaam; Paul Seedhouse; Daniel Jackson; Cuong Pham; Cassim Ladha; Karim Ladha; Thomas Plötz; Patrick Olivier
Ubiquitous computing technologies have traditionally striven to augment objects and the environment with sensing capabilities to enable them to respond appropriately to the needs of the individuals in the environment. This paper considers how such technologies might be harnessed to support language learning, and specifically Task-Based Learning (TBL). Task-Based Learning (TBL) involves doing meaningful tasks in a foreign language, emphasising the language's use in practice. TBL is seen as a highly engaging and motivating approach to learning a language, but is difficult to do in the classroom. Here, learners typically engage in activities that only simulate 'real-world' tasks, and as such only rehearse language use, rather than applying the language in practice. In this paper, we explore how an instrumented, context-aware environment whose design is grounded in pedagogical principles can support TBL. We present the French Kitchen, an instrumented kitchen for English speakers who are learning French, and describe a 46-participant evaluation of the kitchen. Based on the evaluation, we provide a set of design recommendations for those building instrumented systems for TBL.
An investigation of contents and use of the home wardrobe BIBA 203-206
  Lucy E. Dunne; Jingwen Zhang; Loren Terveen
The home wardrobe is a complex and variable system, interacted with daily by its user/manager in a time- and resource-constrained decision-making process. Ubiquitous computing technology offers advantages in augmenting the decision-making process, and the potential to simultaneously encourage sustainable behaviors. In this study we present an empirical analysis of the contents of 11 home wardrobes and 3-6 months of daily dressing decisions for 5 users. We find that an average of only 7% of our female participants' wardrobes and 47% of our male participants' wardrobes are in regular use. In addition, we present an analysis of wardrobe contents, outfit composition, and garment utility in the wardrobe.
Fine-grained kitchen activity recognition using RGB-D BIBAFull-Text 208-211
  Jinna Lei; Xiaofeng Ren; Dieter Fox
We present a first study of using RGB-D (Kinect-style) cameras for fine-grained recognition of kitchen activities. Our prototype system combines depth (shape) and color (appearance) to solve a number of perception problems crucial for smart space applications: locating hands, identifying objects and their functionalities, recognizing actions and tracking object state changes through actions. Our proof-of-concept results demonstrate great potentials of RGB-D perception: without need for instrumentation, our system can robustly track and accurately recognize detailed steps through cooking activities, for instance how many spoons of sugar are in a cake mix, or how long it has been mixing. A robust RGB-D based solution to fine-grained activity recognition in real-world conditions will bring the intelligence of pervasive and interactive systems to the next level.

Energy at home and in the car

Providing eco-driving feedback to corporate car drivers: what impact does a smartphone application have on their fuel efficiency? BIBAFull-Text 212-215
  Johannes Tulusan; Thorsten Staake; Elgar Fleisch
The personal transport sector constitutes an important target of energy conservation and emission reduction programs. In this context, eco-feedback technologies that provide information on the driving behavior have shown to be an effective means to stimulate changes in driving in favor of both, reduced costs and environmental impact. This study extends the literature on eco-feedback technologies as it demonstrates that a smartphone application can improve fuel efficiency even under conditions where monetary incentives are not given, i.e. where the drivers do not pay for fuel. The field test, which took place with 50 corporate car drivers, demonstrates an improvement in the overall fuel efficiency by 3.23%. The theoretical contribution underlines the assumption that context-related feedback can favorably influence behavior even without direct financial benefits for the agent. Given the large share of corporate cars, findings are also of high practical importance and motivate future research on eco-driving feedback technologies.
Understanding domestic energy consumption through interactive visualisation: a field study BIBAFull-Text 216-225
  Enrico Costanza; Sarvapali D. Ramchurn; Nicholas R. Jennings
Motivated by the need to better manage energy demand in the home, in this paper we advocate the integration into Ubicomp systems of interactive energy consumption visualisations, that allow users to engage with and understand their consumption data, relating it to concrete activities in their life. To this end, we present the design, implementation, and evaluation of FigureEnergy, a novel interactive visualisation that allows users to annotate and manipulate a graphical representation of their own electricity consumption data, and therefore make sense of their past energy usage and understand when, how, and to what end, some amount of energy was used. To validate our design, we deployed FigureEnergy "in the wild" -- 12 participants installed meters in their homes and used the system for a period of two weeks. The results suggest that the annotation approach is successful overall: by engaging with the data users started to relate energy consumption to activities rather than just to appliances. Moreover, they were able to discover that some appliances consume more than they expected, despite having had prior experience of using other electricity displays.


Lullaby: a capture & access system for understanding the sleep environment BIBAFull-Text 226-234
  Matthew Kay; Eun Kyoung Choe; Jesse Shepherd; Benjamin Greenstein; Nathaniel Watson; Sunny Consolvo; Julie A. Kientz
The bedroom environment can have a significant impact on the quality of a person's sleep. Experts recommend sleeping in a room that is cool, dark, quiet, and free from disruptors to ensure the best quality sleep. However, it is sometimes difficult for a person to assess which factors in the environment may be causing disrupted sleep. In this paper, we present the design, implementation, and initial evaluation of a capture and access system, called Lullaby. Lullaby combines temperature, light, and motion sensors, audio and photos, and an off-the-shelf sleep sensor to provide a comprehensive recording of a person's sleep. Lullaby allows users to review graphs and access recordings of factors relating to their sleep quality and environmental conditions to look for trends and potential causes of sleep disruptions. In this paper, we report results of a feasibility study where participants (N=4) used Lullaby in their homes for two weeks. Based on our experiences, we discuss design insights for sleep technologies, capture and access applications, and personal informatics tools.
RubberBand: augmenting teacher's awareness of spatially isolated children on kindergarten field trips BIBAFull-Text 236-239
  Hyukjae Jang; Sungwon Peter Choe; Inseok Hwang; Chanyou Hwang; Lama Nachman; Junehwa Song
On school field trips, chaperoning teachers' foremost concern is the safety of the children, particularly ensuring that none of them go missing. However, they have limited attention resources and face many challenges in keeping track of their charges. We present RubberBand, an assistive application that helps alleviate the teacher's burden. Our approach adapts to diverse field trip environmental and child behavioral dynamicity, utilizing observations of the relative dispersion of children and their tendency to form sub-groups.

People as sensors

Detecting pedestrian flocks by fusion of multi-modal sensors in mobile phones BIBAFull-Text 240-249
  Mikkel Baun Kjærgaard; Martin Wirz; Daniel Roggen; Gerhard Tröster
Previous work on the recognition of human movement patterns has mainly focused on movements of individuals. This paper addresses the joint identification of the indoor movement of multiple persons forming a cohesive whole -- specifically a flock -- with clustering approaches operating on features derived from multiple sensor modalities of modern smartphones. Automatic detection of flocks has several important applications, including evacuation management and socially aware computing. The novelty of this paper is, firstly, to use data fusion techniques to combine several sensor modalities (WiFi, accelerometer and compass) to improve recognition accuracy over previous unimodal approaches. Secondly, improve the recognition of flocks using hierarchical clustering. We use a dataset comprising 16 subjects forming one to four flocks walking in a building on single and multiple floors. With the best settings, we achieve a F-score accuracy of up to 87 percent an improvement of up to twelve percent points over existing approaches.
Detecting leisure activities with dense motif discovery BIBAFull-Text 250-259
  Eugen Berlin; Kristof Van Laerhoven
This paper proposes an activity inference system that has been designed for deployment in mood disorder research, which aims at accurately and efficiently recognizing selected leisure activities in week-long continuous data. The approach to achieve this relies on an unobtrusive and wrist-worn data logger, in combination with a custom data mining tool that performs early data abstraction and dense motif discovery to collect evidence for activities. After presenting the system design, a feasibility study on weeks of continuous inertial data from 6 participants investigates both accuracy and execution speed of each of the abstraction and detection steps. Results show that our method is able to detect target activities in a large data set with a comparable precision and recall to more conventional approaches, in approximately the time it takes to download and visualize the logs from the sensor.
Orientation-aware scene understanding for mobile cameras BIBAFull-Text 260-269
  Jing Wang; Grant Schindler; Irfan Essa
We present a novel approach that allows anyone to quickly teach their smartphone how to understand the visual world around them. We achieve this visual scene understanding by leveraging a camera-phone's inertial sensors to lead to both a faster and more accurate automatic labeling of the regions of an image into semantic classes (e.g. sky, tree, building). We focus on letting a user train our system from scratch while out in the real world by annotating image regions in situ as training images are captured on a mobile device, making it possible to recognize new environments and new semantic classes on the fly. We show that our approach outperforms existing methods, while at the same time performing data collection, annotation, feature extraction, and image segment classification all on the same mobile device.

Physiological sensing

Understanding physiological responses to stressors during physical activity BIBAFull-Text 270-279
  Jin-Hyuk Hong; Julian Ramos; Anind K. Dey
With advances in physiological sensors, we are able to understand people's physiological status and recognize stress to provide beneficial services. Despite the great potential in physiological stress recognition, there are some critical issues that need to be addressed such as the sensitivity and variability of physiology to many factors other than stress (e.g., physical activity). To resolve these issues, in this paper, we focus on the understanding of physiological responses to both stressor and physical activity and perform stress recognition, particularly in situations having multiple stimuli: physical activity and stressors. We construct stress models that correspond to individual situations, and we validate our stress modeling in the presence of physical activity. Analysis of our experiments provides an understanding on how physiological responses change with different stressors and how physical activity confounds stress recognition with physiological responses. In both objective and subjective settings, the accuracy of stress recognition drops by more than 14% when physical activity is performed. However, by modularizing stress models with respect to physical activity, we can recognize stress with accuracies of 82% (objective stress) and 87% (subjective stress), achieving more than a 5-10% improvement from approaches that do not take physical activity into account.
SpiroSmart: using a microphone to measure lung function on a mobile phone BIBAFull-Text 280-289
  Eric C. Larson; Mayank Goel; Gaetano Boriello; Sonya Heltshe; Margaret Rosenfeld; Shwetak N. Patel
Home spirometry is gaining acceptance in the medical community because of its ability to detect pulmonary exacerbations and improve outcomes of chronic lung ailments. However, cost and usability are significant barriers to its widespread adoption. To this end, we present SpiroSmart, a low-cost mobile phone application that performs spirometry sensing using the built-in microphone. We evaluate SpiroSmart on 52 subjects, showing that the mean error when compared to a clinical spirometer is 5.1% for common measures of lung function. Finally, we show that pulmonologists can use SpiroSmart to diagnose varying degrees of obstructive lung ailments.
A high accuracy, low-latency, scalable microphone-array system for conversation analysis BIBAFull-Text 290-300
  David Sun; John Canny
Understanding and facilitating real-life social interaction is a high-impact goal for Ubicomp research. Microphone arrays offer the unique capability to provide continuous, calm capture of verbal interaction in large physical spaces, such as homes and (especially open-plan) offices. Most microphone array work has focused on arrays of custom sensors in small spaces, and a few recent works have tested small arrays of commodity sensors in single rooms. This paper describes the first working scalable and cost-effective array that offers high-precision localization of conversational speech, and hence enables ongoing studies of verbal interactions in large semi-structured spaces. This work represents significant improvements over prior work in three dimensions -- cost, scale and accuracy. It also achieves high throughput for real-time updates of tens of active sources using off-the-shelf components. We describe the system design, key localization algorithms, and a systematic performance evaluation. We then show how source location data can be usefully aggregated to reveal interesting patterns in group conversations, such as dominance and engagement.

Feelings and emotions

Mood meter: counting smiles in the wild BIBAFull-Text 301-310
  Javier Hernandez; Mohammed (Ehsan) Hoque; Will Drevo; Rosalind W. Picard
In this study, we created and evaluated a computer vision based system that automatically encouraged, recognized and counted smiles on a college campus. During a ten-week installation, passersby were able to interact with the system at four public locations. The aggregated data was displayed in real time in various intuitive and interactive formats on a public website. We found privacy to be one of the main design constraints, and transparency to be the best strategy to gain participants' acceptance. In a survey (with 300 responses), participants reported that the system made them smile more than they expected, and it made them and others around them feel momentarily better. Quantitative analysis of the interactions revealed periodic patterns (e.g., more smiles during the weekends) and strong correlation with campus events (e.g., fewer smiles during exams, most smiles the day after graduation), reflecting the emotional responses of a large community.
Identifying emotions expressed by mobile users through 2D surface and 3D motion gestures BIBAFull-Text 311-320
  Céline Coutrix; Nadine Mandran
Only intrusive and expensive ways of precisely expressing emotions has been proposed, which are not likely to appear soon in everyday Ubicomp environments. In this paper, we study to which extent we can identify the emotion a user is explicitly expressing through 2D and 3D gestures. Indeed users already often manipulate mobile devices with touch screen and accelerometers. We conducted a field study where we asked participants to explicitly express their emotion through gestures and to report their affective states. We contribute by (1) showing a high number of significant correlations in 3D motion descriptors of gestures and in the arousal dimension; (2) defining a space of affective gestures. We identify (3) groups of descriptors that structure the space and are related to arousal. Finally, we provide with (4) a preliminary model of arousal and we identify (5) interesting patterns in particular classes of gestures. Such results are useful for Ubicomp application designers in order to envision the use of gestures as a cheap and non-intrusive affective modality.
Friends don't lie: inferring personality traits from social network structure BIBAFull-Text 321-330
  Jacopo Staiano; Fabio Pianesi; Bruno Lepri; Nicu Sebe; Nadav Aharony; Alex Pentland
In this work, we investigate the relationships between social network structure and personality; we assess the performances of different subsets of structural network features, and in particular those concerned with ego-networks, in predicting the Big-5 personality traits. In addition to traditional survey-based data, this work focuses on social networks derived from real-life data gathered through smartphones. Besides showing that the latter are superior to the former for the task at hand, our results provide a fine-grained analysis of the contribution the various feature sets are able to provide to personality classification, along with an assessment of the relative merits of the various networks exploited.

Sensing on and with people

An integrated framework for human activity classification BIBA 331-340
  Hong Cao; Minh Nhut Nguyen; Clifton Phua; Shonali Krishnaswamy; Xiao-Li Li
This paper presents an integrated framework to enable using standard non-sequential machine learning tools for accurate multi-modal activity recognition. We develop a novel framework that contains simple pre- and post-classification strategies to improve the overall performance. We achieve this through class-imbalance correction on the learning data using structure preserving oversampling (SPO), leveraging the sequential nature of sensory data using smoothing of the predicted label sequence and classifier fusion, respectively. Through evaluation on recent publicly available activity datasets comprising of a large amount of multi-dimensional sensory data, we demonstrate that our proposed strategies are effective in improving classification performance over common techniques such as One Nearest Neighbor (1NN) and Support Vector Machines (SVM). Our framework also shows better performance over sequential probabilistic models, such as Conditional Random Field (CRF) and Hidden Markov Model (HMM) and when these models are used as meta-learners.
BodyScope: a wearable acoustic sensor for activity recognition BIBAFull-Text 341-350
  Koji Yatani; Khai N. Truong
Accurate activity recognition enables the development of a variety of ubiquitous computing applications, such as context-aware systems, lifelogging, and personal health systems. Wearable sensing technologies can be used to gather data for activity recognition without requiring sensors to be installed in the infrastructure. However, the user may need to wear multiple sensors for accurate recognition of a larger number of different activities. We developed a wearable acoustic sensor, called BodyScope, to record the sounds produced in the user's throat area and classify them into user activities, such as eating, drinking, speaking, laughing, and coughing. The F-measure of the Support Vector Machine classification of 12 activities using only our BodyScope sensor was 79.5%. We also conducted a small-scale in-the-wild study, and found that BodyScope was able to identify four activities (eating, drinking, speaking, and laughing) at 71.5% accuracy.
StressSense: detecting stress in unconstrained acoustic environments using smartphones BIBAFull-Text 351-360
  Hong Lu; Denise Frauendorfer; Mashfiqui Rabbi; Marianne Schmid Mast; Gokul T. Chittaranjan; Andrew T. Campbell; Daniel Gatica-Perez; Tanzeem Choudhury
Stress can have long term adverse effects on individuals' physical and mental well-being. Changes in the speech production process is one of many physiological changes that happen during stress. Microphones, embedded in mobile phones and carried ubiquitously by people, provide the opportunity to continuously and non-invasively monitor stress in real-life situations. We propose StressSense for unobtrusively recognizing stress from human voice using smartphones. We investigate methods for adapting a one-size-fits-all stress model to individual speakers and scenarios. We demonstrate that the StressSense classifier can robustly identify stress across multiple individuals in diverse acoustic environments: using model adaptation StressSense achieves 81% and 76% accuracy for indoor and outdoor environments, respectively. We show that StressSense can be implemented on commodity Android phones and run in real-time. To the best of our knowledge, StressSense represents the first system to consider voice based stress detection and model adaptation in diverse real-life conversational situations using smartphones.

Are we there yet?

Cellular data meet vehicular traffic theory: location area updates and cell transitions for travel time estimation BIBAFull-Text 361-370
  Andreas Janecek; Karin A. Hummel; Danilo Valerio; Fabio Ricciato; Helmut Hlavacs
Road traffic can be monitored by means of static sensors and derived from floating car data, i.e., reports from a sub-set of vehicles. These approaches suffer from a number of technical and economical limitations. Alternatively, we propose to leverage the mobile cellular network as a ubiquitous mobility sensor. We show how vehicle travel times and road congestion can be inferred from anonymized signaling data collected from a cellular mobile network. While other previous studies have considered data only from active devices, e.g., engaged in voice calls, our approach exploits also data from idle users resulting in an enormous gain in coverage and estimation accuracy. By validating our approach against four different traffic monitoring datasets collected on a sample highway over one month, we show that our method can detect congestions very accurately and in a timely manner.
Some help on the way: opportunistic routing under uncertainty BIBAFull-Text 371-380
  Eric Horvitz; John Krumm
We investigate opportunistic routing, centering on the recommendation of ideal diversions on trips to a primary destination when an unplanned waypoint, such as a rest stop or a refueling station, is desired. In the general case, an automated routing assistant may not know the driver's final destination and may need to consider probabilities over destinations in identifying the ideal waypoint along with the revised route that includes the waypoint. We consider general principles of opportunistic routing and present the results of several studies with a corpus of real-world trips. Then, we describe how we can compute the expected value of asking a user about the primary destination so as to remove uncertainly about the goal and show how this measure can guide an automated system's engagements with users when making recommendations for navigation and analogous settings in ubiquitous computing.
Predictability of individuals' mobility with high-resolution positioning data BIBAFull-Text 381-390
  Miao Lin; Wen-Jing Hsu; Zhuo Qi Lee
The ability to foresee the next moves of a user is crucial to ubiquitous computing. Disregarding major differences in individuals' routines, recent ground-breaking analysis on mobile phone data suggests high predictability in mobility. By nature, however, mobile phone data offer very low spatial and temporal resolutions. It remains largely unknown how the predictability changes with respect to different spatial/temporal scales. Using high-resolution GPS data, this paper investigates the scaling effects on predictability. Given specified spatial-temporal scales, recorded trajectories are encoded into long strings of distinct locations, and several information-theoretic measures of predictability are derived. Somewhat surprisingly, high predictability is still present at very high spatial/temporal resolutions. Moreover, the predictability is independent of the overall mobility area covered. This suggests highly regular mobility behaviors. Moreover, by varying the scales over a wide range, an invariance is observed which suggests that certain trade-offs between the predicting accuracy and spatial-temporal resolution are unavoidable. As many applications in ubiquitous computing concern mobility, these findings should have direct implications.

Pediatric informatics

Automatic assessment of problem behavior in individuals with developmental disabilities BIBAFull-Text 391-400
  Thomas Plötz; Nils Y. Hammerla; Agata Rozga; Andrea Reavis; Nathan Call; Gregory D. Abowd
Severe behavior problems of children with developmental disabilities often require intervention by specialists. These specialists rely on direct observation of the behavior, usually in a controlled clinical environment. In this paper, we present a technique for using on-body accelerometers to assist in automated classification of problem behavior during such direct observation. Using simulated data of episodes of severe behavior acted out by trained specialists, we demonstrate how machine learning techniques can be used to segment relevant behavioral episodes from a continuous sensor stream and to classify them into distinct categories of severe behavior (aggression, disruption, and self-injury). We further validate our approach by demonstrating it produces no false positives when applied to a publicly accessible dataset of activities of daily living. Finally, we show promising classification results when our sensing and analysis system is applied to data from a real assessment session conducted with a child exhibiting problem behaviors.
Parent-driven use of wearable cameras for autism support: a field study with families BIBAFull-Text 401-410
  Gabriela Marcu; Anind K. Dey; Sara Kiesler
Recorded images of children's activities can be useful to caregivers and clinicians who need behavioral evidence to support children with autism. However, image capture systems for autism are typically complex and provide only a top-down, outsider's view. In this work, we assessed the use of cameras worn by children to record the context of their activities and interactions from their perspective. We used a technology probe to explore how this simple, parent-driven system could be designed for families to adopt in their homes. We present the results of a five-week field study with five families. The system helped parents to (1) see the world from their child's eyes, (2) increase their understanding of their child's needs when their child is uncommunicative, and (3) help them encourage their child's social engagement. We discuss how these systems can be designed and used to their full potential.
Augmenting gesture recognition with erlang-cox models to identify neurological disorders in premature babies BIBAFull-Text 411-420
  Mingming Fan; Dana Gravem; Dan M. Cooper; Donald J. Patterson
In this paper we demonstrate a Markov model based technique for recognizing gestures from accelerometers that explicitly represents duration. We do this by embedding an Erlang-Cox state transition model, which has been shown to accurately represent the first three moments of a general distribution, within a Dynamic Bayesian Network (DBN). The transition probabilities in the DBN can be learned via Expectation-Maximization or by using closed-form solutions. We test this modeling technique on 10 hours of data collected from accelerometers worn by babies pre-categorized as high-risk in the Newborn Intensive Care Unit (NICU) at UCI. We show that by treating instantaneous machine learning classification values as observations and explicitly modeling duration, we improve the recognition of Cramped Synchronized General Movements, a motion highly correlated with an eventual diagnosis of Cerebral Palsy.

Indoor location sensing

A reliable and accurate indoor localization method using phone inertial sensors BIBAFull-Text 421-430
  Fan Li; Chunshui Zhao; Guanzhong Ding; Jian Gong; Chenxing Liu; Feng Zhao
This paper addresses reliable and accurate indoor localization using inertial sensors commonly found on commodity smartphones. We believe indoor positioning is an important primitive that can enable many ubiquitous computing applications. To tackle the challenges of drifting in estimation, sensitivity to phone position, as well as variability in user walking profiles, we have developed algorithms for reliable detection of steps and heading directions, and accurate estimation and personalization of step length. We've built an end-to-end localization system integrating these modules and an indoor floor map, without the need for infrastructure assistance. We demonstrated for the first time a meter-level indoor positioning system that is infrastructure free, phone position independent, user adaptive, and easy to deploy. We have conducted extensive experiments on users with smartphone devices, with over 50 subjects walking over an aggregate distance of over 40 kilometers. Evaluation results showed our system can achieve a mean accuracy of 1.5m for the in-hand case and 2m for the in-pocket case in a 31m×15m testing area.
Robust, low cost indoor positioning using magnetic resonant coupling BIBAFull-Text 431-440
  Gerald Pirkl; Paul Lukowicz
We describe the design, implementation, and evaluation of an indoor positioning system based on resonant magnetic coupling. The system has an accuracy of less than 1 m2 and, because of the underlying physical principle, is robust with respect to disturbances such as people moving around or changes in room configuration. It consists of 16x16x16 cm transmitter coils, each able to cover an area of up to 50 m2, and provides location information to an arbitrary number of mobile receivers with an update rate of up to 30Hz. We evaluate the actual accuracy of the positioning with a robotic arm and show quantitatively that even large metallic objects have little effect on the signal. We then present an elaborate study of the performance of our system for the recognition of abstract locations such as "at the table", "in front of a cabinet". It comprises four different sites with a total of 100 individual locations some as little as 50 cm apart.
ARIEL: automatic wi-fi based room fingerprinting for indoor localization BIBAFull-Text 441-450
  Yifei Jiang; Xin Pan; Kun Li; Qin Lv; Robert P. Dick; Michael Hannigan; Li Shang
People spend the majority of their time indoors, and human indoor activities are strongly correlated with the rooms they are in. Room localization, which identifies the room a person or mobile phone is in, provides a powerful tool for characterizing human indoor activities and helping address challenges in public health, productivity, building management, etc. Existing room localization methods, however, require labor-intensive manual annotation of individual rooms.
   We present ARIEL, a room localization system that automatically learns room fingerprints based on occupants' indoor movements. ARIEL consists of (1) a zone-based clustering algorithm that accurately identifies in-room occupancy "hotspot(s)" using Wi-Fi signatures; (2) a motion-based clustering algorithm to identify inter-zone correlation, thereby distinguishing different rooms; and (3) an energy-efficient motion detection algorithm to minimize the noise of Wi-Fi signatures. ARIEL has been implemented and deployed for real-world testing with 21 users over a 10-month period. Our studies show that it supports room localization with higher than 95% accuracy without requiring labor-intensive manual annotation.

Sketching and annotations

Enhancing the 'second-hand' retail experience with digital object memories BIBAFull-Text 451-460
  Martin de Jode; Ralph Barthel; Jon Rogers; Angelina Karpovich; Andrew Hudson-Smith; Michael Quigley; Chris Speed
For a long time, the second-hand retail market was the preserve of the charity shop. However, the advent of services like eBay has massively increased its prominence. In this paper we describe a novel Internet of Things-based approach to enhancing the second-hand retail experience by augmenting items with their provenance. After a discussion of the underlying technology, we shall describe its deployment in two related case studies conducted in collaboration with Oxfam charity retail outlets in which we tagged donated items with RFID and QR codes, allowing shoppers to hear the story behind the donated items. Finally, we discuss the impact of the deployments and their implications for the second-hand retail sector.
Walk&Sketch: create floor plans with an RGB-D camera BIBAFull-Text 461-470
  Ying Zhang; Chuanjiang Luo; Juan Liu
Creating floor plans for large areas via manual surveying is labor-intensive and error-prone. In this paper, we present a system, Walk&Sketch, that creates floor plans of an indoor environment by a person walking through the environment at a normal strolling pace and taking videos using a consumer RGB-D camera. The method computes floor maps represented by polylines from a 3D point cloud based on precise frame-to-frame alignment. It aligns a reference frame with the floor and computes the frame-to-frame offsets from the continuous RGB-D input. Line segments at a certain height are extracted from the 3D point cloud, and are merged to form a polyline map, which can be further modified and annotated by users. The explored area is visualized as a sequence of polygons, providing users with the information on coverage. Experiments have done in various areas of an office building and have shown encouraging results.
Façade map: continuous interaction with media façades using cartographic map projections BIBAFull-Text 471-480
  Sven Gehring; Antonio Krüger
The increasing number of media façades is a prominent example of the digital augmentation of urban spaces. Many media façades cover most of the outer shell of a building and come with a 3D form factor. They offer great potential for remote interaction in which the interactive area goes beyond the parts of the façade that are visible from the user's current perspective. Common interaction techniques often focus on a fixed part of the media façade. This restricts exploiting the full capabilities and the potential of such gigantic screens. In this paper we describe how to apply cartographic map projections to create 2D map representations of media façades to address this problem. We describe how a continuous interaction with the media façade is possible, independent of the form factor. We analyze existing media façades and provide a set of guidelines for how to create façade maps for different form factors.

Crowdsourcing and bootstrapping

Automatically characterizing places with opportunistic crowdsensing using smartphones BIBAFull-Text 481-490
  Yohan Chon; Nicholas D. Lane; Fan Li; Hojung Cha; Feng Zhao
Automated and scalable approaches for understanding the semantics of places are critical to improving both existing and emerging mobile services. In this paper, we present CrowdSense@Place (CSP), a framework that exploits a previously untapped resource -- opportunistically captured images and audio clips from smartphones -- to link place visits with place categories (e.g., store, restaurant). CSP combines signals based on location and user trajectories (using WiFi/GPS) along with various visual and audio place "hints" mined from opportunistic sensor data. Place hints include words spoken by people, text written on signs or objects recognized in the environment. We evaluate CSP with a seven-week, 36-user experiment involving 1,241 places in five locations around the world. Our results show that CSP can classify places into a variety of categories with an overall accuracy of 69%, outperforming currently available alternative solutions.
Helping mobile apps bootstrap with fewer users BIBAFull-Text 491-500
  Xuan Bao; Paramvir Bahl; Aman Kansal; David Chu; Romit Roy Choudhury; Alec Wolman
A growing number of mobile apps are exploiting smartphone sensors to infer user behavior, activity, or context. Inference requires training using labeled ground truth data. Obtaining labeled data for new apps is a "chicken-egg" problem. Without a reasonable amount of labeled data, apps cannot provide any service. But until an app provides useful service it is not worth installing and has no opportunity to collect user data. This paper aims to address this problem. Our intuition is that even though users are different, they exhibit similar patterns on certain sensing dimensions. For instance, different users may walk and drive at different speeds, but certain speeds will indicate driving for all users. These common patterns could be used as "seeds" to model new users through semi-supervised learning. We prototype a technique to automatically extract the commonalities to seed personalized inference models for new users. We evaluate the proposed technique through example apps and real world data.
Expectation and purpose: understanding users' mental models of mobile app privacy through crowdsourcing BIBAFull-Text 501-510
  Jialiu Lin; Norman Sadeh; Shahriyar Amini; Janne Lindqvist; Jason I. Hong; Joy Zhang
Smartphone security research has produced many useful tools to analyze the privacy-related behaviors of mobile apps. However, these automated tools cannot assess people's perceptions of whether a given action is legitimate, or how that action makes them feel with respect to privacy. For example, automated tools might detect that a blackjack game and a map app both use one's location information, but people would likely view the map's use of that data as more legitimate than the game. Our work introduces a new model for privacy, namely privacy as expectations. We report on the results of using crowdsourcing to capture users' expectations of what sensitive resources mobile apps use. We also report on a new privacy summary interface that prioritizes and highlights places where mobile apps break people's expectations. We conclude with a discussion of implications for employing crowdsourcing as a privacy evaluation technique.

UbiComp at home and in the city

Making technology homey: finding sources of satisfaction and meaning in home automation BIBAFull-Text 511-520
  Leila Takayama; Caroline Pantofaru; David Robson; Bianca Soto; Michael Barry
Home and automation are not natural partners -- one homey and the other cold. Most current automation in the home is packaged in the form of appliances. To better understand the current reality and possible future of living with other types of domestic technology, we went out into the field to conduct need finding interviews among people who have already introduced automation into their homes and kept it there -- home automators. We present the lessons learned from these home automators as frameworks and implications for the values that domestic technology should support. In particular, we focus on the satisfaction and meaning that the home automators derived from their projects, especially in connecting to their homes (rather than simply controlling their homes). These results point the way toward other technologies designed for our everyday lives at home.
Democratizing ubiquitous computing: a right for locality BIBAFull-Text 521-530
  Sebastian Weise; John Hardy; Pragya Agarwal; Paul Coulton; Adrian Friday; Mike Chiasson
Trends such as the increasing adoption of smartphones, the development of the service-oriented internet, and diffusion of sensing technologies into cities have the potential to combine in order to form a ubiquitous computing infrastructure. At the same time, as the computer diffuses into the physical world, it loses its location-neutrality, exposing the urgent need for a debate of design choices in ubiquitous computing. In this paper, we discuss the process of urban development as a source of inspiration for such design choices. Looking from the ground up, of particular interest is the opportunity to localize and democratize an emerging ubiquitous computing infrastructure. The design choices we negotiate today will determine the society in which we will live in the future.
iPods, Ataris, and Polaroids: a personal inventories study of out-of-use electronics in Swiss households BIBAFull-Text 531-535
  Silke Gegenbauer; Elaine M. Huang
The retention of old electronic devices is a practice of importance to sustainability and ubicomp. In this research, we aim to understand people's reasons for keeping out-of-use electronic devices. Using the Personal Inventories qualitative method we conducted 17 in-home visits to learn what technologies people keep and explore their relationships with out-of-use technologies. We identify various reasons for keeping devices that build upon existing work on electronics and sustainability.


Touché: touch and gesture sensing for the real world BIBA 536
  Ivan Poupyrev; Chris Harrison; Munehiko Sato
Touché proposes a novel Swept Frequency Capacitive Sensing technique that can not only detect a touch event, but also recognize complex configurations of the human hands and body. Such contextual information significantly enhances touch interaction in a broad range of applications, from conventional touchscreens to unique contexts and materials. For example, in our explorations we add touch and gesture sensitivity to the human body and liquids. We demonstrate the rich capabilities of Touché with five example setups from different application domains and conduct experimental studies that show gesture classification accuracies of 99% are achievable with our technology.
Indoor-outdoor activity recognition by a smartphone BIBA 537
  Kazushige Ouchi; Miwako Doi
It is increasingly important to recognize daily activity pattern in order to detect early sign of dementia in the aging society. This paper shows indoor-outdoor activity recognition using only a smartphone. We developed an indoor living activity recognition engine and an outdoor migration activity recognition engine, and combined them into an Android™ application. The former recognizes not only "resting" or "walking" but also user's various living activities such as "vacuuming" and "brushing teeth" by using a built-in accelerometer and a built-in microphone. The latter engine recognizes the user's means of migration, namely, "resting," "walking," "running," and "boarding" by using a built-in accelerometer. It enables users to continuously recognize indoor-outdoor activities by switching between the two engines depending on an acquisition condition of GPS.
Discovering the web by location with Webnear.me BIBA 538
  Basil Hess; Fabio Magagna; Juliana Sutanto
While mobile apps for smartphones are consistently popular, the most common way for users to explore the Internet is still through the WWW. Websites are however not explicitly equipped with information regarding their location -- an issue for use on mobile devices. With this work we aim at bridging this gap by adding a location layer to websites and letting users browse by nearby websites. We present a mobile demonstrator called Webnear.me. Once installed on the smartphone, users are able to list websites in proximity their location: Near.me. Websites in proximity to another one can be browsed too: Near.this. With our application we strive to give answers to the question of how web content should be tagged with locations. We approach this question with several content- and user-centric location-tagging methods.
LiDSN: a method to deploy wireless sensor networks securely based on light communication BIBA 539-540
  Giang Doan; Minh Nguyen; Takuya Takimoto; Takuro Yonezawa; Jin Nakazawa; Kazunori Takashio; Hideyuki Tokuda
Deploying Wireless Sensor Networks (WSN) securely still requires users to have certain skills and exert effort. In the near "sensor everywhere" future, a much simpler method for deploying WSN will be necessary for end-users. We propose LiDSN (Light Communication for Deploying Secure Wireless Sensor Networks) which enables users to achieve deployment tasks via simple interaction. LiDSN leverages light-based communication between an LED and a light sensor in order to add a new sensor node securely into existing WSN. Through touching interaction, a new sensor node ID and secret key can be transmitted to the WSN, and then the WSN is able to identify which node should be added while maintaining the security of the WSN.
Lightweight image processing algorithms on the camera sensor node in WMSNs BIBA 541-542
  Sun Rongli; Xiao Kejiang; Wang Rui; Cui Li
To enable the prospect of Wireless Multimedia Sensor Networks (WMSNs), in this paper the lightweight image processing algorithms embeddable on the camera sensor node are proposed. (1) the target segmentation algorithm effectively solves the influence of changing light and low gray contrast, and reserves complete target shape. (2) the target shape feature extraction algorithm well removes the influence of segmentation holes and scatter noise, and accurately extracts key shape features. In the evaluation, the renderings processed by the algorithms illustrate fully the effectiveness of target segmentation and the accuracy of target shape feature extraction.
CookTab: smart cutting board for creating recipe with real-time feedback BIBA 543-544
  Ayaka Sato; Koji Tsukada
Although many cooking recipes have been shared in the world, there are still many homemade meals that are never written down as recipes. The difficulty to create recipes of such homemade meals lies on (1) experienced cookers might not have accurate information of ingredients (e.g., weight and timing) since they often decide the amount of ingredients just by intuition, (2) they often have trouble to record such accurate information while cooking. To solve these problems, we propose a smart cutting board, CookTab, which allows a user to easily record his/her cooking activities (e.g., the names and quantities of ingredients) while provides real-time feedback to motivate him/her.
SenSprout: inkjet-printed soil moisture and leaf wetness sensor BIBA 545
  Yoshihiro Kawahara; Hoseon Lee; Manos M. Tentzeris
In this paper we show a low cost and environmentally friendly fabrication for an agricultural sensing application. An antenna, a soil moisture sensor, and a leaf wetness sensor are inkjet-printed on paper substrate. A microprocessor attached to the paper substrate is capable of detecting the capacitance change on the surface of the sensor, and report the data over the wireless communication interface. This sensing system is useful to optimize irrigation systems.
AnyType: creating typography from anything, anywhere BIBA 546
  Laura Devendorf; Kimiko Ryokai
AnyType is a creative application that lets people transform elements and objects in the physical world into novel digital typefaces. The portability, computational power and network capabilities of AnyType allow the user to take design into the wild so that they can create and share in the same moment in which they are inspired. With AnyType, we invite people to reinterpret their everyday environment and transform it into a set of possible creative inputs.
CarSafe demo: supporting driver safety using dual-cameras on smartphones BIBA 547
  Chuang-Wen You; Martha Montes-de-Oca; Thomas J. Bao; Nicholas D. Lane; Hong Lu; Giuseppe Cardone; Lorenzo Torresani; Andrew T. Campbell
We demonstrate CarSafe, a driver safety application for Android phones that fuses information from both front and back cameras and others embedded sensors on the phone to detect and alert drivers to dangerous driving conditions in and outside of the car. In this demonstration, we set up an emulated driving environment to show how CarSafe works.

Doctoral colloquium

A framework to promote user engagement in participatory sensing applications BIBA 548-551
  Osarieme Omokaro
Incentives have been introduced in participatory sensing applications to encourage the general public to engage in providing quality data that is meaningful to a data collection campaign. However, it is likely that there is no single incentive mechanism that is guaranteed to increase and sustain user engagement. We believe that to sustain user engagement in participatory sensing campaigns, incentives should be tailored to reflect the interests of individuals, as well as the nature of the application. We propose a framework that provides participatory sensing application developers with the flexibility to offer various incentives within a single participatory sensing campaign.
Integrating participatory sensing and informal science education BIBA 552-555
  Scott Heggen
In light of the declining number of new students pursuing education in science, technology, engineering, and mathematics, informal science educators have adopted public participation in scientific research as a tool to produce gains in engagement. Following their lead, we propose to use a form of public participation in scientific research known as participatory sensing to increase engagement in these academic areas. Participatory sensing involves volunteers using mobile phones and the embedded sensing capabilities to collect data, and is well suited for the task as it provides the students with a familiar tool for conducting complex scientific research. To accomplish this goal, we have developed two components: a toolkit for defining, creating, and managing a participatory sensing campaign, including automated generation of mobile applications; and a curriculum designed around the toolkit, where students conduct scientific research with mobile phones as their primary data collection tools. Thus far, the results of this work have shown the potential for participatory sensing as an informal education tool to increase engagement and interest in pursuing careers in science and technology.
A flexible tool for participating, authoring, and managing citizen science campaigns on-the-go BIBA 556-559
  Sunyoung Kim
Grassroots participation is a great resource for monitoring environmental phenomena, and collecting and analyzing data in a variety of fields, called Citizen Science. The proliferation of mobile devices has helped to boost citizen science activities. However, the creation of such tools is under the control of developers and accompanying infrastructure that most local organizations, which are often the bodies of citizen science activities, lack. This often hinders citizen science activities from prospering. This work aims to create a visual environment where people without programming skills can build mobile data-collection tools and manage data collectively. The expected contributions include a creation of a tool to prosper citizen science by lowering technical barriers; an understanding of the dynamics of data collection and management through grassroots participation; and implications for designing citizen science tools.
Using embodied allegories to design gesture suites for human-data interaction BIBA 560-563
  Francesco Cafaro
Human-Data Interaction (HDI) systems can be defined as technologies that use embodied interaction to facilitate the users' exploration of rich datasets. As the design of gestures for Whole-Body Interaction is often based on an uninformed trial and error approach, I propose the use of Johnson's embodied schemata, extended with allegories, to inform the design of suites of gestures for HDI systems. This approach involves: (1) the identification of embodied allegories to encourage data exploration, (2) a study of the allegorical relation between input and output, and (3) an analysis of the implication of the (social) space.
Consent reconsidered; reframing consent for ubiquitous computing systems BIBA 564-567
  Ewa Luger
The developing complexity and decreasing visibility of pervasive computing systems, coupled with increasing value and sensitivity of personal data, mean that it is no longer sufficient to design systems that assume users capable of making informed decisions at a single moment. In particular, the unprecedented sensitivity of contextual data, and the potential harms associated with inferences made on the basis of that data, highlights the need to revisit our design principles in respect of consent. This thesis will use a mixed-methods approach to reframe 'consent' for ubiquitous computing systems, resulting in a series of design guidelines to inform future developments.
Personalized lighting control based on a space model BIBA 568-571
  Filip Petrushevski
This research focuses on personalization of lighting conditions in office buildings. A lighting control agent is proposed that uses spatial context retrieved from a space model, as well as other context data, to address the challenges of personalized lighting control. Benefits include improved user satisfaction, productivity and minimized energy use. A user scenario is presented to illustrate the envisioned concept of personalized lighting control. Requirements are derived from this and related scenarios. A system design is proposed that meets these requirements. A first version of a system prototype has been implemented and validated against the user scenario.
Design and implementation of a space model server for indoor location-based services BIBA 572-575
  Miloš Šipetic
This research investigates a space model server for indoor location-based services which require fine-grained spatial data. Functional and non-functional requirements for a space model server that supports such services are identified. A system architecture is proposed that scales well in terms of model size, query loads and types of services. The space model reuses a schema for network-based space layouts which supports high spatial resolution and efficient local queries. Properties of a query language used to extract partial models from the space model server are investigated. System implementation and validation are discussed.
Activity recognition using a spectral entropy signature BIBA 576-579
  Jessica Beltrán Márquez
Context identification is one of the key challenges in Ubicomp. An application example is providing contextual information to caregivers of person with dementia to identify assistance needs. Environmental audio provides significant and representative information of the context and the challenge is to automatically identify audio cues coming from overlapping sound sources without sophisticated microphone arrangements. My thesis proposes a succinct representation of the audio, based on the spectral entropy of the signal, and we show experimentally its robustness to source overlap and noise. This would permit ubiquitous applications that perform sound-based activity identification directly in mobile phones.
A privacy-by-design approach to location sharing BIBA 580-583
  Marcello Paolo Scipioni
Despite the proliferation of location-based services on mobile platforms, privacy concerns still refrain many people from using them regularly. Moreover, current location sharing tools often present over-simplistic privacy settings by which users are forced to the binary alternative of sharing everything or nothing. The goal of this research is to build novel privacy-aware tools through which users can share their location more easily and in the way they consider more appropriate. Starting from the study of the sharing functionalities and how people use them, I aim at building a platform for efficiently sharing location, supported by a usable interface through which users can easily understand how sharing works and feel in control of their data. Furthermore, the security mechanisms employed are conceived such that privacy is considered as an integral part of the sharing mechanisms, in a privacy-by-design approach.


RoCoMo: a generic ontology for context modeling, representation and reasoning in a context-aware middleware BIBA 584-585
  Preeti Bhargava; Shivsubramani Krishnamoorthy; Ashok Agrawala
We describe an abstract, generic and extensible ontology, the Rover Context Model Ontology (RoCoMO), which is currently being designed and developed to model and represent context in an intelligent context-aware middleware system, called Rover II. The Rover Context Model (RoCoM) is the underlying context model for Rover II and is centered on four primitives that can be used to represent a situation: entity, event, activity and relationship. The ontology is expressed using the Web Ontology Language (OWL) and includes two components -- RoCoM Core Ontology and the RoCoM Application Ontology. We also illustrate its usage with the aid of a public safety application called M-Urgency that is currently deployed at the UMD campus.
Interactive Pong: exploring ways of user inputs through prototyping with sensors BIBA 586-587
  Wei Liu; Aadjan van der Helm; Pieter Jan Stappers; Walter Aprile; Gert Pasman; Ianus Keller
This study aimed to explore ways of user inputs through designing interactive game controllers with different type of sensor. From building four experiential prototypes on Pong, we learned to drive design by focusing on interaction qualities, which determine the use of sensors. We found that the interaction qualities together as a set offer a way to design aesthetics of behavior in interaction.
Development of a distributed chemical event system BIBA 588-589
  Young Yoon; Seokmin Yoon; Minjoong Yoon
We introduce the ideas of developing a distributed event-based system for screening and monitoring the activities that can lead to the production of hazardous chemicals such as explosive materials and narcotic drugs. This system is built on top of the state-of-the-art content-based publish/subscribe messaging substrate that processes complex chemical events in a robust and scalable way. This system also leverages the chemical information encoded in semantic chemistry networks to identify any undesirable chemical reactions.
Listen-to-nose: a low-cost system to record nasal symptoms in daily life BIBA 590-591
  Nan-Chen Chen; Kuo-Cheng Wang; Hao-Hua Chu
This paper proposes Listen-to-Nose, a phone-based system that detects and records when and where a person's nose-related symptoms, such as sneezing and runny nose, occur in everyday settings. It is hoped that this system can be used to collect reference data for doctors to diagnose the cause of these symptoms.
Mobile posture monitoring system to prevent physical health risk of smartphone users BIBA 592-593
  Hosub Lee; Young Sang Choi; Sunjae Lee
With the widespread use of a smartphone, users tend to use their smartphone for a long period of time in unhealthy postures; bending forward the neck and watching the relatively small screen closely with concentration. If users keep such unhealthy postures for a long time, they are susceptible to musculoskeletal disorders and eye problems such as cervical disc and myopia, respectively. To prevent users from having these diseases, we propose a new methodology to monitor the posture of smartphone users with built-in sensors. The proposed mechanism estimates various values representing user postures like the tilt angle of the neck, viewing distance, and gaze condition of the user, by analyzing sensor data from a front-faced camera, 3-axis accelerometer, orientation sensor, or any combination thereof, and warns the user if estimated values are maintained within the abnormal range over the allowed time. Via the proposed mechanism, users are able to be aware of their unhealthy postures, and then try to correct their postures.
Top of worlds: method for improving motivation to participate in sensing services BIBA 594-595
  Hitoshi Kawasaki; Atsushi Yamamoto; Hisashi Kurasawa; Hiroshi Sato; Motonori Nakamura; Hajime Matsumura
We propose a method for improving motivation to participate in sensing services by presenting rankings in multidimensional hierarchical sets. We call this method Top of Worlds. Because previously proposed methods only rank a user among all other users, many have little chance of being ranked in the top group, resulting in little motivation to continue. Top of Worlds creates many sets with varying granularity to increase the chance of many users being ranked in the top group and presents these rankings in those sets. Through an experiment, we partially confirmed the validity of Top of Worlds.
From rotary telephones to universal number entry systems: can the past re-shape the future? BIBA 596-597
  Julie Webster; Parisa Eslambolchilar; Harold Thimbleby
Although number entry appears to be a trivial task, user errors are still common and could be a result of poorly engineered interaction with the devices. We are challenging the design of universal number entry systems by looking at cases where user errors are frequently made. The telephone is used as a platform to compare input devices for number entry where we can look for speed and accuracy trade-offs between direct and indirect inputs. We will focus on the knob, button, and touchscreen and hope to find guidelines for when each is appropriate to use in a number entry system.
Towards causal models for building behavioral user profile in ubiquitous computing applications BIBA 598-599
  Belkacem Chikhaoui; Shengrui Wang; Hélène Pigot
This paper presents a practical and novel model for behavioral user profile construction using causal relationships. Causal relationships are extracted from behavior sequences for building user profiles. Our model discovers significant patterns from behavior sequences, then it discovers patterns associations using normalized mutual information. Causal relationships between significant patterns are then identified using the transfer entropy approach. We empirically demonstrate that these causality-based profiles accurately describe users profiles and allow developing practical Ubicomp applications.
Indoor-outdoor activity recognition by a smartphone BIBA 600-601
  Kazushige Ouchi; Miwako Doi
It is increasingly important to recognize daily activity pattern in order to detect early sign of dementia in the aging society. This paper shows indoor-outdoor activity recognition using only a smartphone. We developed an indoor living activity recognition engine and an outdoor migration activity recognition engine, and combined them into an Android™ application. The former recognizes not only "resting" or "walking" but also user's various living activities such as "vacuuming" and "brushing teeth" by using a built-in accelerometer and a built-in microphone. The latter engine recognizes the user's means of migration, namely, "resting," "walking," "running," and "boarding" by using a built-in accelerometer. It enables users to continuously recognize indoor-outdoor activities by switching between the two engines depending on an acquisition condition of GPS satellites.
Using social network graphs for search space reduction in internet of things BIBA 602-603
  Chirabrata Bhaumik; Amit Kumar Agrawal; Priyanka Sinha
In this paper, we explore reduction of search space in sensor data analytics using social network graph theory. Human centric social network allow graphical connect of individuals either based on familiarity or common intent. This facilitates people centric applications as they now operate on a much smaller data set. Extending this analogy to sensor networks, if sensors can be associated with meaningful social groups, it will reduce sensor data analytics and processing overhead for an application by a huge order. In this paper we explore how in Internet-of-Things sensors can be assigned to human beings who in turn are connected in social networks. Effectively in this way, sensors become part of a social network that results in a reduced data set for sensor data analytics.
CalMate: communication support system for couples using a calm avatar BIBA 604-605
  Maki Nakagawa; Koji Tsukada; Itiro Siio
Many people find that communication between men and women is difficult regardless of their efforts to understand their partners. Especially, negative feelings cause troubles on communication of couple members. In this paper, we proposed a novel communication support system for couples that helps couple members share their negative feelings and heal over them smoothly using a physical avatar.
Preserving location privacy by distinguishing between public and private spaces BIBA 606-607
  Jeremy Wood
'Location Anonymization' seeks to preserve privacy in location data by blurring people's locations primarily when they are in places that are not public; the coordinates of someone in public are blurred less or not at all. The method also calls for tracking each person for only a limited time (e.g. 24 hours). The hope is that this method will allow individual traces to be distributed and used as data without aggregation. The method was evaluated with 21 GPS-derived tracks. Results are promising. The anonymization appears to be adequate, and the anonymized data are information-rich.
Mobile augmented reality learning tool to simulate experts' perspectives in the field BIBA 609-610
  Kimiko Ryokai; Deepak Subramanian; Leslie Tom
Mobile Augmented Reality (MAR) -- techniques to dynamically overlay digital information in the user's view through mobile devices -- has the potential to uniquely contribute to people learning about objects or environments in situ. Using interactive expert videos and side-by-side MAR views on a location sensitive tablet, our prototype system, GreenHat MAR, simulates how experts go about making observations in the field, and encourages students to actively observe their environment to learn about biodiversity and sustainability issues in their natural environment. We present our design process, the GreenHat MAR prototype, and results from our preliminary evaluation study.
Multi-touch passwords for mobile device access BIBA 611-612
  Ian Oakley; Andrea Bianchi
Draw-a-Secret password schemes, like the Google Android Pattern Lock, entail stroking out a shape on a touch screen. This paper explores techniques for expanding the richness of this input modality (multitouch input, off-target interaction) in order to increase password entropy and resistance to observation. A formative user study highlights user perceptions and usability issues relating to this design space and suggests directions for future development of this concept.
Evaluating semi-automatic annotation of domestic energy consumption as a memory aid BIBA 613-614
  Darren P. Richardson; Enrico Costanza; Sarvapali D. Ramchurn
Frequent feedback about energy consumption can help conservation, one of the current global challenges. Such feedback is most helpful if users can relate it to their own day-to-day activities. In earlier work we showed that manual annotation of domestic energy consumption logs aids users to make such connection and discover patterns they were not aware of. In this poster we report how we augmented manual annotation with machine learning classification techniques. We propose the design of a lab study to evaluate the system, extending methods used to evaluate context aware memory aids, and we present the results of a pilot with 5 participants.
User profile generation reflecting user's temporal preference through web life-log BIBA 615-616
  Akinori Nakamura; Nobuhiko Nishio
We have analyzed logs that which web pages are viewed by users. Information recommendation is one of hot research areas for users activities support. Although many of recommendation systems are eager to match a user's preference, if the user does not want that at that moment, it would be just a noise no matter how much match the preference matches user's preference over all. It is important to understand what the user really wants each of moment timely. Therefore, in this paper, we make use of the following two characteristics for inference user's temporal wish. First is to adapt the degree of user's each interest with time range evolution. Second, web browsing logs related to an activity has been temporarily reinforced. The preliminary result of an algorithm is introduced.
The occurrence of vigilance during intermittent use BIBA 617-618
  M. Giles Phillips
In social media, user engagement is mediated by an online profile, through which our interactions with online social worlds are framed. By adapting and mediating the embodied acts of Identify Performance and Impression Management, the online profile informs socialization and self-identity. This research posits that the particular use case for maintaining an online profile creates an unprecedented, technology-driven form of human vigilance during intermittent use. A set of design principles is proposed in order to guide the design of more effective and sustainable interactions that support vigilance during cases of intermittent use. These principles can be generalized from social networking into numerous domains of HCI.
Personalization of an energy awareness pervasive game BIBA 619-620
  Rui Neves Madeira; André Vieira; Nuno Correia
One of the recurrent major environmental problems is the high energy consumption. It has been challenging to find methods of persuading people to have better habits on energy usage. We are proposing the use of personalization to enhance a mobile and pervasive-based gaming approach to better foster domestic energy awareness close to people. The game is based on real-time domestic energy consumption data and presents persuasive feedback information, beyond the competitive feeling of the game. The personalization mechanisms are provided by an external web service that is designed to serve different applications, even if from different systems or domains.
An integrated framework for human activity recognition BIBAFull-Text 621-622
  Hong Cao; Minh Nhut Nguyen; Clifton Phua; Shonali Krishnaswamy; Xiao-Li Li
This poster presents an integrated framework to enable using standard non-sequential machine learning tools for accurate multi-modal activity recognition. Our framework contains simple pre- and post-classification strategies such as class-imbalance correction on the learning data using structure preserving oversampling, leveraging the sequential nature of sensory data using smoothing of the predicted label sequence and classifier fusion, respectively, for improved performance. Through evaluation on recent publicly-available OPPORTUNITY activity datasets comprising of a large amount of multi-dimensional, continuous-valued sensory data, we show that our proposed strategies are effective in improving the performance over common techniques such as One Nearest Neighbor (1NN) and Support Vector Machines (SVM). Our framework also shows better performance over sequential probabilistic models, such as Conditional Random Field (CRF) and Hidden Markov Models (HMM) and when these models are used as meta-learners.
DHT-based sensor data management for geographical range query BIBA 623-624
  Junki Terayama; Jin Nakazawa; Hideyuki Tokuda
Nowadays, since each sensor network is managed within a single organization, sensor data cannot be obtained externally. When these sensor networks are virtualized that means everyone is able to obtain data anywhere without minding which sensor network the data belongs, two features will be required. One of these is geographical range query. This research realizes it using Z-order in the same way with related works [1][2][3][4]. The other requirement is distributed sensor data management. Current systems adapt the way that stores the data in a (or some) centralized server(s), or that stores the data in many servers, having one centralized server to store indexes of the address of the data. This research proposes a method not relating real space geographical information and relative position of peer in ID space. By using this method, in the place where density of people and smart phones with many sensors increase suddenly such as Super Bowl and new year countdown in NY, by using DHT, sensor data don't concentrate on a specified peer on managing the data. This research simulates and evaluates this method.
Understanding how trace segmentation impacts transportation mode detection BIBA 625-626
  Yung-Ju Chang; Mark W. Newman
Transportation mode (TM) detection is one of the activity recognition tasks in ubiquitous computing. A number of previous studies have compared the performance of various classifiers for TM detection. However, the current study is the first work aiming to understand how TM detection performance is impacted by how the recorded location traces are segmented into data segments for training a classifier. In our preliminary experiments we examine three trace segmentation (TS) methods -- Uniform Duration (UniDur), Uniform Number of Location Points (UniNP), and Uniform Distance (UniDis) -- and compare their performance on detecting different transportation modes. The results indicate that while driving can be more accurately detected by using UniDis method, walking and bus can be more accurately detected by using UniDur method. This suggests that choosing a right TS method for training a TM classifier is an important step to accurately detect particular transportation modes.
SmartShadow-K: an practical knowledge network for joint context inference in everyday life BIBA 627-628
  Li Zhang; Gang Pan; Zhaohui Wu; Shijian Li; Cho-Li Wang
Smart environments require to percept conditions of people. Current context-aware systems mainly model limited user situations, which constrains their coverage and effect in real world usage. This paper proposes an encyclopedic knowledge network to enable practical context inference in our daily life by: 1) expressing essential semantics of contextual concepts and relations into a well-informed relational network, and 2) exploiting relational semantics to infer various contexts simultaneously. The performance of the approach is validated in real challenging problems and compared with inference of human being.
Surrounding context and episode awareness using dynamic Bluetooth data BIBA 629-630
  Yiqiang Chen; Zhenyu Chen; Junfa Liu; Derek Hao Hu; Qiang Yang
Bluetooth information can efficiently capture characteristics of user-centric surrounding contexts, such as formal meeting or chatting with friends, shopping with friends or alone, etc. In this paper, we extract novel features from Bluetooth traces and use these features for recognizing contextual behavior as well as inferring continuous episode transition. Evaluation results show that extracted novel features are very effective, which enable the model to achieve an average of 87% accuracy for specific context classification and the ability of episode inference from real-life Bluetooth traces.
WiFiTreasureHunt: a mobile social application for staying active physically BIBA 631-632
  M. Chuah; G. Jakes; Z. Qin
Smartphones these days are equipped with many embedded sensors which enable new applications across different domains, namely healthcare, environmental monitoring, social networks, and transportation. In our previous work, we developed a location-based Android-based application called Fitness Tour for combating obesity. In this poster, we present an enhanced location-based application called WiFiTreasureHunt that encourages young adults and school children who own smartphones to stay active physically. Our application includes several new features: (a) randomly generated exercise tours with hidden treasures at some selected locations, (b) group-based games where updates of group members' visits can be shown on each player's screen, and (c) social network interface that allows participating users to invite friends to participate in self-organized group competitions. The group feature allows users to exert social pressure on one another to adopt healthier lifestyle via outdoor physical activities. Our main goal is to use this application to encourage children and college students to adopt more active lifestyles and hence combat the obesity problem.
Semantic anomaly detection in daily activities BIBA 633-634
  Enamul Hoque; John Stankovic
We monitor activities of daily living of smart home residents to detect anomalies in their behavior. Unlike traditional anomaly detection systems, we aim to reduce false positives in anomaly detection with the help of semantic rules. Some of these rules are predefined based on expert knowledge and the rest are learned by the system with the help of resident/expert feedback. We also correlate trend of change in different activities to improve anomaly detection. In addition to monitor statistical deviation from regular behavior, we also detect deviation from healthy and social norms (defined by experts) as anomalies.
Design of a context aware signal glove for bicycle and motorcycle riders BIBA 635-636
  Anthony Carton
For bicycle and motorcycle riders, visibility is a constant concern for safe riding. For the designer, minimizing additional demands on the rider's attention is just as crucial when the device will be used while operating a vehicle, especially a bicycle or motorcycle. This riding glove uses common sensors to recognize a small set of hand gestures used by riders and then actuates appropriate LED patterns for enhanced gesture visibility. The configuration of LEDs translates the gesture to an illuminated directional chevron, extending functionality into the night hours. By equipping the device to recognize existing hand gestures, activation of directional LED signals is simplified allowing the rider to focus on riding while the glove responds to and extends the visibility of the rider's hand gestures. This context awareness allows the device to cooperate with the rider, rather than asking the rider to interact with the device.
TeC apps for smart spaces: simple, decentralized, resilient, and self-healing BIBA 637-638
  João Pedro Sousa; Xiang Shen; Vasilios Tzeremes; Frank Hodum
TeC is a framework for end-user design, deployment, and evolution of applications for smart spaces. Design is declarative and focuses on simple tailoring of behavior and on interconnection of devices such as motion sensors, cameras, thermostats, and smart electric meters. TeC apps act as teams of elements with no central control: elements play their roles autonomously, and app behavior is emergent. Under the hood, the operational semantics promotes resiliency: the failure of any element may cause degraded operation of the features that depend on it, but all others remain operational. Automated (re)deployment of TeC designs allows users to keep evolving their apps as they buy new gadgets or change their minds about features.
Semantic context relevance assessment in urban ubiquitous environments BIBA 639-640
  Beibei Hu; Abdelghani Chibani; Yacine Amirat
We present a rule-based architecture (CIDA) for the provision of relevant information tailored to the user's current context, which consists of an ontology-based context model (ConAD) and a rule engine (RARE). ConAD is extensible to characterize the contextual situations in urban environments, and RARE supports the reconfiguration of the behavior of systems in different situations. Our preliminary evaluation results based on emergency scenarios show that CIDA is feasible for providing context-aware urban information services.
Towards macroscopic human behavior based authentication for mobile transactions BIBA 641-642
  Sotirios Kentros; Yusuf Albayram; Athanasios Bamis
Integration of Near Field Communication (NFC) sensors into mobile devices has enabled their use for authentication. The ubiquitous nature of authentication using mobile devices comes though with increased security considerations. In addition to the risk of being stolen, mobile devices are increasingly susceptible to different types of software attacks. User-provided passwords such as Personal Identification Numbers (PINs) are often employed to ameliorate these limitations. The use of passwords though, has its own vulnerabilities that are mainly caused by the passwords' static nature and low entropy. To eliminate the security threats caused by untrusted devices and static passwords, we propose the development of new types of biometric authentication, based on macroscopic human behavior.
TempoString: a tangible tool for children's music creation BIBA 643-644
  Liang He; Guang Li; Yang Zhang; Danli Wang; Hongan Wang
In this paper, we introduce the design and implementation of TempoString, an easy-to-use tool which assists children with music creation. It provides such a fun and novel platform by allowing children to "draw" music on a canvas and then edit it using a rope. The main contribution of our work is the novel access which allows children to "paint" music on a canvas and then edit using a rope.
Preliminary evaluation of feature level compensation for missing data in multi-sensor activity recognition BIBA 645-646
  Ryoma Uchida; Ren Ohmura
Activity recognition using multiple body-worn sensors can directly monitor the movement of each body part and can recognize various activities accurately. However, using multiple sensors increases the chance of sensor failure or communication failure, and most current activity recognition algorithms do not work when failure occurs due to the difference (reduction) of the dimension of the feature vector from that of complete sensor data expected in system design time. Therefore, we compared three possible techniques to solves this problem on the feature value level: a classifier trained with reduced feature values, feature value compensation with multiple regression, and feature value compensation with kernel regression, in a no failure situation. All of these techniques do not depend on classification algorithms. While creating a regression model, which is in the training phase, requires relatively high computational power, compensation itself can work with low computational power. As overall results, kernel regression had the best performance that was the closest to the no failure situation. Also, the results imply that each sensor position has its own effective method and more accurate coping can be viable with the appropriate choice of the method.
Using mid-range RFID for location based activity recognition BIBA 647-648
  Juhi Ranjan; Yu Yao; Erin Griffiths; Kamin Whitehouse
Development of smarthome home application depends on the ability to identify resident activity and track occupancy of rooms as people move within a residence. Existing solutions to home activity recognition are evaluated using controlled experiments and having participants maintain logs of daily activities as ground truth. In our study, we evaluate the effectiveness of using mid-range RFID as a research tool to perform in-situ evaluation of smarthome systems. We propose that using bracelets and anklets embedded with passive RFID tags can provide an accurate ground truth system, which can help evaluate the performance of research solutions for smarthomes with higher accuracy -- in presence of natural variability of people in activities and movement in homes.
Multi-layer e-textile circuits BIBA 649-650
  Lucy E. Dunne; Kaila Bibeau; Lucie Mulligan; Ashton Frith; Cory Simon
Stitched e-textile circuits facilitate wearable, flexible, comfortable wearable technology. However, while stitched methods of e-textile circuits are common, multi-layer circuit creation remains a challenge. Here, we present methods of stitched multi-layer circuit creation using accessible tools and techniques.
MobileQueue: an image-based queue card management system through augmented reality phones BIBA 651-652
  Chuang-Wen You; Wen-Huang Cheng; Arvin Wen Tsui; Tsung-Hung Tsai; Andrew Campbell
We propose MobileQueue, a mobile queue-card management system that offers more freedom to customers by enabling image-based queue-card retrieving and service-information querying actions using mobile phones. MobileQueue interacts with cloud services allowing customers to query summary description and availability (e.g., available seats) of services provided by stores. MobileQueue also offers suggestions to waiting customers such as potentially interesting substitute activities and stores.
Plastic is fantastic!: experimenting with the building affordances of fuse beads in physical computing BIBA 653-654
  Lalya Gaye; Peter C. Wright
We present the use of plastic fuse beads as a prototyping approach in physical computing and as a material in electronic circuitry. We introduce the properties of this craft and material, and describe a collaborative experiment with a group of teenagers, in which this approach was tested as a participatory project. This open-format workshop demonstrated the feasibility, affordances and youth-friendliness of using this craft and material for simple DIY physical computing projects and for the tangible learning of basic principles of interaction design.
Unsupervised discovery of spatial relationships between objects for activity recognition inside smart home BIBA 655-656
  Kevin Bouchard; Bruno Bouchard; Abdenour Bouzouane
Data mining techniques have been vastly exploited recently to overcome complex problems that humans struggle to solve. Particularly, the recognition of the activity of daily living of a smart home's resident is a challenging issue that requires advanced algorithms using extensive plans' library. In this paper, we propose a novel unsupervised learning technique for the discovery of sequential pattern related to spatial relationships of objects inside a smart home. We concretely use this approach to automatically construct a library of plans. Finally, we demonstrate the efficiency with a practical activity recognition algorithm by comparing learned knowledge over expert's defined library in a real smart home.
uSmell: a gas sensor system to classify odors in natural, uncontrolled environments BIBA 657-658
  Sen H. Hirano; Khai N. Truong; Gillian R. Hayes
Smell can be used to infer quite a bit of context about environments. Previous research primarily has shown that gas sensors can be used to discriminate accurately between odors when used in testing chambers. However, potential real-world applications require these sensors to perform an analysis in uncontrolled environments, which can be challenging. In this poster, we present our gas sensor system, called uSmell, to address these challenges. This system has the potential to improve context-aware applications, such as lifelogging and assisted living.
Opportunities for ubiquitous computing in the homes of low SES older adults BIBA 659-660
  Ginger E. White; Katherine H. Connelly; Kelly E. Caine
Eight hour contextual observations have been conducted in the homes of 5 low socioeconomic status (SES) urban-dwelling older adults. The purpose of the observations was to understand the daily needs and challenges of older adults in order to design appropriate technology that can allow older adults to age-in-place (age at home). The long term goal of the study is to develop a suite of age-in-place technologies tailored to the lifestyle needs of low SES urban and rural-dwelling older adults. This paper presents initial findings and discusses how this ongoing research will be used to inform the design of future age-in-place technologies.
Phone-based gait analysis to detect alcohol usage BIBA 661-662
  Hsin-Liu (Cindy) Kao; Bo-Jhang Ho; Allan C. Lin; Hao-Hua Chu
This study proposes a phone-based system to detect the gait anomalies of a person waking under the influence of alcohol. This phone-based system can sense a person's alcohol usage and record the location/time context. This data can help identify problem drinking behaviors, such as drinking before work or before driving.
weShop: using social data as context in the retail experience BIBA 663-664
  Brian M. Landry; Kelly Dempski
Uncertainty about a product can act as a barrier to purchase. The more confident a customer is about a product, the more likely she is to purchase it. Online shopping websites provide an array of tools and information to support decision-making (e.g., product comparison, ratings, reviews, etc.). In contrast, few tools are available in physical stores to help customers navigate the decision process. We have developed a mobile application prototype to support the purchase decision process in the store. At the core of the experience is the use of social profile data as a form of context to provide a tailored experience aimed at reducing customer uncertainty.


Gluballoon: an unobtrusive and educational way to better understand one's diabetes BIBA 665-666
  Angelika Dohr; Jeff Engler; Frank Bentley; Richard Whalley
Diabetes patients adjust their insulin injections according to their food consumption, physical activity and glucose levels. These adjustments are often trial-and-error, and newly diagnosed patients often use logbooks to catalog their daily activities and aid their physicians in developing an appropriate regimen.
   Gluballoon is an electronic diabetes logbook that makes food/insulin/glucose/activity logging fun, easy and precise. Designed for newly diagnosed diabetes patients, working in conjunction with physicians, Gluballoon helps patients understand how their daily activities affect their blood glucose levels. The mobile service we built uses newly developed technologies to automatically log physical activity, insulin dosing and glucose levels. The collected data is compiled into a central service available from tablets, phones, and the web that displays their vital statistics (and the relationship between the statistics) in an easy and fun visual format.
Squama: a programmable window and wall for future physical architectures BIBA 667-668
  Jun Rekimoto
In this video we present Squama, a programmable physical window or wall that can independently control the visibility of its elemental small square tiles. This is an example of programmable physical architecture, our vision for future architectures where the physical features of architectural elements and facades can be dynamically changed and reprogrammed according to people's needs. When Squama is used as a wall, it dynamically controls the transparency through its surface, and simultaneously satisfies the needs for openness and privacy. It can also control the amount of sunlight and create shadows, called programmable shadows, in order to afford indoor comfort without completely blocking the outer view. In this video, we show how in future, architectural space can become dynamically changeable and introduce the Squama system as an initial instance for exemplifying this concept.
FlyingBuddy2: a brain-controlled assistant for the handicapped BIBA 669-670
  Yipeng Yu; Dan He; Weidong Hua; Shijian Li; Yu Qi; Yueming Wang; Gang Pan
The motor impaired people have much limit in moving. The devices augmenting their mobility will be much helpful for improving their living experiences. This poster develops a brain-controlled assistive system, called FlyingBuddy2, to aid the handicapped in mobility. It uses the brain EEG signals to directly control a quadrotor. Signals from an EEG headset are transmitted wirelessly to a computer, then the decoded brain signals are converted to trigger the quadrotor to move in 3D space. Three applications are developed: thinking to play games, thinking to see, and thinking to take pictures.
CarSafe: a driver safety app that detects dangerous driving behavior using dual-cameras on smartphones BIBA 671-672
  Chuang-Wen You; Martha Montes-de-Oca; Thomas J. Bao; Nicholas D. Lane; Hong Lu; Giuseppe Cardone; Lorenzo Torresani; Andrew T. Campbell
Driving while being tired or distracted is dangerous. We are developing the CafeSafe app for Android phones, which fuses information from both front and back cameras and others embedded sensors on the phone to detect and alert drivers to dangerous driving conditions in and outside of the car. CarSafe uses computer vision and machine learning algorithms on the phone to monitor and detect whether the driver is tired or distracted using the front camera while at the same time tracking road conditions using the back camera. CarSafe is the first dual-camera application for smart-phones.

Pervasive Eye Tracking and Mobile Eye-Based Interaction (PETMEI 2012)

2nd International Workshop on Pervasive Eye Tracking and Mobile Eye-Based Interaction (PETMEI 2012): proposal for a workshop (mini-track) at UbiComp 2012 BIBA 673-676
  Andreas Bulling; Shiwei Cheng; Geert Brône; Päivi Majaranta
Early work on applied eye tracking investigated gaze as an input modality to interact with a desktop computer and discussed some of the human factors and technical aspects involved in performing common computer tasks with the eyes such as pointing and menu selection. Since then, eye tracking technology has considerably matured. Research on eye-based interaction is starting to gain interest in various specialized areas that are no longer restricted to desktop environment, such as virtual reality, human-human and human-robot interaction. There is also a growing interest to take eye tracking out into the wild, to mobile and pervasive settings.
Automatic analysis of eye-tracking data using object detection algorithms BIBA 677-680
  Stijn De Beugher; Younes Ichiche; Geert Brône; Toon Goedemé
In this paper we investigate the integration of object detection algorithms with eye-tracking data. The emerging technology of lightweight mobile eye-trackers enables realistic in-the-wild user experience experiments. Unfortunately, mobile eye-trackers generate a large amount of video data, which up to now requires manual analysis. This time-consuming and repetitive task renders processing large datasets economically infeasible. Our main contribution is the use of object detection algorithms to perform this analysis task automatically. We compare several object detection algorithms with regard to both speed and accuracy. To prove their functionality, we have recorded an eye-tracker shopping experiment and processed the data using object detection techniques.
Dataset for the evaluation of eye detector for gaze estimation BIBA 681-684
  Victoria Ponz; Arantxa Villanueva; Rafael Cabeza
Being able to perform eye tracking with low cost technology is the key to broaden its applications and one of the major goals for the eye tracking community nowadays. Furthermore, new datasets to evaluate the different methods are needed to reproduce the real conditions in which these algorithms work. In this paper, we present a dataset containing images of subjects with different gaze orientations as a new evaluation tool. First step in eye tracking algorithms is to detect the region of the eyes, and using the Gi4e dataset, we evaluate the best performing public Haar based classifiers under different gaze orientations to detect the eye area, proving this dataset to be a fair evaluation method.
Hybrid eye detection algorithm for outdoor environments BIBA 685-688
  Jose Javier Bengoechea; Arantxa Villanueva; Rafael Cabeza
When performing eye detection in a driving scenario, new challenges arise that do not occur in a standard indoor eye tracking session. Rapid subject movement, non-controlled fast light variation and partial or total occlusions are the main problems that must be overcome. Furthermore, sunlight's infrared component makes it difficult the use of active artificial infrared light sources. In this paper, we describe a novel algorithm that combines Viola Jones face detector and TLD (Tracking Learning Detection) algorithm. In a standard driving scenario, it achieves a 84% rate of detection. Furthermore, we have designed a filtering stage that allows a low false positive rate. The algorithms hardware requirement is a standard web cam, and it can potentially work in real time.
Parallax error in the monocular head-mounted eye trackers BIBA 689-694
  Diako Mardanbegi; Dan Witzner Hansen
This paper investigates the parallax error, which is a common problem of many video-based monocular mobile gaze trackers. The parallax error is defined and described using the epipolar geometry in a stereo camera setup. The main parameters that change the error are introduced and it is shown how each parameter affects the error. The optimum distribution of the error (magnitude and direction) in the field of view varies for different applications. However, the results can be used for finding the optimum parameters that are needed for designing a head-mounted gaze tracker. It has been shown that the difference between the visual and optical axes does not have a significant effect on the parallax error, and the epipolar geometry can be used for describing the parallax error in the HMGT.
Location by parts: model generation and feature fusion for mobile eye pupil tracking under challenging lighting BIBA 695-700
  Thomas B. Kinsman; Jeff B. Pelz
Using infrared based mobile eye trackers outdoors is difficult, and considered intractable by some [1, 2]. The challenge of bright uncontrolled daylight illumination complicates the process of locating the subject's pupil. To make mobile eye tracking more ubiquitous, we are developing more sophisticated algorithms to find the subject's pupil. We use a semi-supervised process to initiate the pupil tracking, automatically generate an ensemble of models of the pupil for each video, and use multi-frame techniques to help locate the pupil across frames. A mixture of experts (consensus) is used to indicate a good estimate of pupil location. The algorithm presented here details developing work in automatically finding the pupil in situations where there is a significant amount of light reflecting off the eye, when the subject is squinting, and when the pupil is partially occluded. The output of this algorithm will be cascaded into a subsequent stage for exact pupil fitting.
Detecting eye contact using wearable eye-tracking glasses BIBA 699-704
  Zhefan Ye; Yin Li; Alireza Fathi; Yi Han; Agata Rozga; Gregory D. Abowd; James M. Rehg
We describe a system for detecting moments of eye contact between an adult and a child, based on a single pair of gaze-tracking glasses which are worn by the adult. Our method utilizes commercial gaze tracking technology to determine the adult's point of gaze, and combines this with computer vision analysis of video of the child's face to determine their gaze direction. Eye contact is then detected as the event of simultaneous, mutual looking at faces by the dyad. We report encouraging findings from an initial implementation and evaluation of this approach.
Enhanced gaze interaction using simple head gestures BIBA 705-710
  Oleg Špakov; Päivi Majaranta
We propose a combination of gaze pointing and head gestures for enhanced hands-free interaction. Instead of the traditional dwell-time selection method, we experimented with five simple head gestures: nodding, turning left/right, and tilting left/right. The gestures were detected from the eye-tracking data by a range-based algorithm, which was found accurate enough in recognizing nodding and left-directed gestures. The gaze estimation accuracy did not noticeably suffer from the quick head motions. Participants pointed to nodding as the best gesture for occasional selections tasks and rated the other gestures as promising methods for navigation (turning) and functional mode switching (tilting). In general, dwell time works well for repeated tasks such as eye typing. However, considering multimodal games or transient interactions in pervasive and mobile environments, we believe a combination of gaze and head interaction could potentially provide a natural and more accurate interaction method.
Eye gesture recognition on portable devices BIBA 711-714
  Vytautas Vaitukaitis; Andreas Bulling
Hand-held portable devices have received only little attention as a platform in the eye tracking community so far. This is mainly due to their -- until recently -- limited sensing capabilities and processing power. In this work-in-progress paper we present the first prototype eye gesture recognition system for portable devices that does not require any additional equipment. The system combines techniques from image processing, computer vision and pattern recognition to detect eye gestures in the video recorded using the built-in front-facing camera. In a five-participant user study we show that our prototype can recognise four different continuous eye gestures in near real-time with an average accuracy of 60% on an Android-based smartphone (17.6% false positives) and 67.3% on a laptop (5.9% false positives). This initial result is promising and underlines the potential of eye tracking and eye-based interaction on portable devices.

Ubiquitous Mobile Instrumentation (UbiMI)

UbiMI: ubiquitous mobile instrumentation BIBA 715-716
  Denzil Ferreira; Emiliano Miluzzo; Jonna Hakkila; Tom Lovett; Vassilis Kostakos
Thanks to the rapid development of mobile technologies, smartphones allow people to be reachable anywhere and anytime. In addition to the benefits for end users, researchers and developers can also benefit from the powerful devices that participants potentially carry on a daily basis. This minitrack workshop brings together researchers with an interest on using mobile devices as instruments to collect data and conduct mobile user studies, with a focus on understanding human-behavior, routines and gathering context.
Context-aware mobile crowdsourcing BIBA 717-720
  Andrei Tamilin; Iacopo Carreras; Emmanuel Ssebaggala; Alfonse Opira; Nicola Conci
Ubiquity of internet-connected media-and sensor-equipped portable devices has emerged a range of opportunities for direct involvement of citizens into public decision making, leading to a new participatory format of public administration functioning. Intersecting the power of the crowdsourcing problem-solving paradigm by directly relying on human intelligence, with instantaneity and situation-awareness of mobile technologies, one gets a context-aware crowdsourcing approach for problem-solving in the right circumstances with the right people. In this paper, we present a prototype implementation of a context-aware mobile crowdsourcing system that enables the deployment and execution of crowdsourcing campaigns with users carrying mobile devices. The system is designed to maximize conditions for user participation, while minimizing the usage of energy. The paper describes the system architecture, defines an optimized sampling algorithm, and outlines a preliminary experimentation study carried out.
A comparison of alternative client/server architectures for ubiquitous mobile sensor-based applications BIBA 721-724
  Gary M. Weiss; Jeffrey W. Lockhart
Mobile devices such as smart phones, tablet computers, and music players are ubiquitous. These devices typically contain many sensors, such as vision sensors (cameras), audio sensors (microphones), acceleration sensors (accelerometers) and location sensors (e.g., GPS), and also have some capability to send and receive data wirelessly. Sensor arrays on these mobile devices make innovative applications possible, especially when data mining is applied to the sensor data. But a key design decision is how best to distribute the responsibilities between the client (e.g., smartphone) and any servers. In this paper we investigate alternative architectures, ranging from a "dumb" client, where virtually all processing takes place on the server, to a "smart" client, where no server is needed. We describe the advantages and disadvantages of these alternative architectures and describe under what circumstances each is most appropriate. We use our own WISDM (WIreless Sensor Data Mining) architecture to provide concrete examples of the various alternatives.
Ubiquitous inference of mobility state of human custodian in people-centric context sensing BIBA 725-728
  Mattia Gustarini; Katarzyna Wac
People-centric sensing using people's smartphones offers new research opportunities for large case studies. It presents many challenges, e.g., efficient capture of person's mobility, understanding of context changes and preservation of user privacy. We propose an accurate and energy-efficient method able to capture user's mobility, thus the context changes, while preserving his/her privacy. Our solution can be applied to systems that aim to efficiently sense context on smartphones to study large scale phenomena or perform location management.
Engaging participants for collaborative sensing of human mobility BIBA 729-732
  Helena Rodrigues; Maria João Nicolau; Rui João José; Adriano Moreira
Human mobility has been widely studied for a variety of purposes, from urban planning to the study of spread of diseases. These studies depend heavily on large datasets, and recent advances in collaborative sensing and WiFi infrastructures have created new opportunities for generating that data. However, these methods and procedures require the participation of a significant community of users through extended periods of time. In this paper, we address the problem of how to engage people to participate in the data collection process. We have conducted a user study on the utilisation of a mobile collaborative sensing application. We have found that users react positively to campaigns, but it is difficult to keep them participating for long periods of time. We also hypothesise that one must close the loop, rewarding the participants with services based on the collected data, eventually showing that there is added value obtainable from crowd sourcing.
On the challenges of building a web-based ubiquitous application platform BIBA 733-736
  Heiko Desruelle; John Lyle; Simon Isenberg; Frank Gielen
People use an increasing number of consumer electronic devices to access their mobile apps. To enhance the applications' immersive user experience, these devices often expose APIs for accessing a wide array of sensors and domain-specific capabilities. Existing mobile application environments, however, only provide limited support for cross-device access of such APIs. To address this limitation, the Webinos platform was designed. Webinos is a virtualized Web-based application platform, aiming to support the collaboration of multiple devices within a single mobile application. In this paper we elaborate on the Webinos platform design. We discuss the encountered design challenges regarding portability, scalability, and privacy, and how these were mitigated.
Multimodal annotation tool for challenging behaviors in people with Autism spectrum disorders BIBA 737-740
  Akane Sano; Javier Hernandez; Jean Deprey; Micah Eckhardt; Matthew S. Goodwin; Rosalind W. Picard
Individuals diagnosed with Autism Spectrum Disorders (ASD) often have challenging behaviors (CB's), such as self-injury or emotional outbursts, which can negatively impact the quality of life of themselves and those around them. Recent advances in mobile and ubiquitous technologies provide an opportunity to efficiently and accurately capture important information preceding and associated with these CB's. The ability to obtain this type of data will help with both intervention and behavioral phenotyping efforts. Through collaboration with behavioral scientists and therapists, we identified relevant design requirements and created an easy-to-use mobile application for collecting, labeling, and sharing in-situ behavior data in individuals diagnosed with ASD. Furthermore, we have released the application to the community as an open-source project so it can be validated and extended by other researchers.
Using ontologies to reduce user intervention to deploy sensing campaigns with the InCense toolkit BIBA 741-744
  Marcela D. Rodríguez; Roberto Martínez; Moisés Pérez; Luis A. Castro; Jesus Favela
This paper presents the InCense research toolkit to facilitate researchers with little or no technical background to implement a sensing application for mobile phones. To reach this end, InCense provides a GUI and an interactive ontology to enable users to define the configuration of the sensing application, i.e. what sensing components to add, and the flow of the sensing session. We illustrate the ease of use of the InCense platform through a scenario in which both opportunistic and participatory sensing paradigms are used.
A preliminary study of sensing appliance usage for human activity recognition using mobile magnetometer BIBA 745-748
  Mi Zhang; Alexander A. Sawchuk
Human activity recognition and human behavior understanding play a central role in the field of ubiquitous computing. In this paper, we propose a novel method using magnetometer embedded in the mobile phone to recognize activities by detecting household appliance usage. The key idea of our approach is that when the mobile phone user performs a certain activity at home, the embedded magnetometer is capable of capturing the changes of the magnetic field strength around the mobile phone caused by the household appliance in operation. Our mobile application uses these changes as magnetic signatures for each of these appliance such that the daily household activities associated with these appliance such as cooking can be recognized.

Context-Awareness for Self-Managing Systems (CASEMANS 2012)

Existing challenges and new opportunities in context-aware systems BIBA 749-751
  Waltenegus Dargie; Juha Plosila; Vincenzo De Florio
Merging the features of Cloud computing, autonomic computing, pervasive computing, and mobile computing are now at its initial stage but the effort is visibly showing the benefits of these paradigms. A large number of applications can take advantage of this, including healthcare, traffic control, and social network applications. However, these applications are complex by nature and introduce several challenges of their own, for example, reliable sensing, accurate context recognition, scalability, security, and the challenge of dealing with previously unforeseen side-effects of adaptations. These challenges can be surmounted when researchers of diverse background come together and provide different views of the same problems and help each other understand the complex relationships between contending ideas. The Casemans 2012 workshop opens the necessary platform for researchers of ubiquitous computing, autonomic computing, and similar fields to address these issues.
Privacy context model for dynamic privacy adaptation in ubiquitous computing BIBA 752-757
  Florian Schaub; Bastian Könings; Stefan Dietzel; Michael Weber; Frank Kargl
Ubiquitous computing is characterized by the merger of physical and virtual worlds as physical artifacts gain digital sensing, processing, and communication capabilities. Maintaining an appropriate level of privacy in the face of such complex and often highly dynamic systems is challenging. We argue that context awareness not only enables novel UbiComp applications but can also support dynamic regulation and configuration of privacy mechanisms. We propose a higher level context model that abstracts from low level details and contains only privacy relevant context features. Context changes in our model can trigger reconfiguration of privacy mechanisms or facilitate context-specific privacy recommendations to the user. Based on our model, we analyze potential privacy implications of context changes and discuss how these results could inform actual reconfiguration of privacy mechanisms.
Context-aware content adaptation in access point BIBA 758-761
  Shahram Mohrehkesh; Tamer Nadeem; Michele C. Weigle
Instead of traditional content adaptation at servers or clients, we propose context-aware content adaptation at the Access Point (AP). We show that because of the special characteristics of the AP such as: being the last node at the edge of the network, no power constraint, and powerful computing capabilities, it can be the best candidate for context-aware content adaptation in high dynamic wireless mobile networks. In fact, it can adapt content more accurately and faster in a high diverse and dynamic context. Content adaptation at the application and MAC layers of the AP is introduced in this paper.
Vertical and horizontal integration towards collective adaptive system: a visionary approach BIBA 762-765
  Liang Guang; Ethiopia Nigussie; Juha Plosila; Hannu Tenhunen
Hybrid multi-domain computing systems are emerging. While the context-aware self-adaptive system models are under intensive research in individual computing domains, their integration into a collective adaptive system still remains a major challenge. This position paper visions a meet-in-the-middle approach, where horizontal integration is applied to sub-system models extracted from vertical integration. The integration relies on orthogonal behavior and execution models respectively capturing the functional and non-functional features of sub-systems. The construction towards guaranteed services can be achieved with composition of static (worst-case) execution models, while best-effort services can be constructed with statistical models. Given that each computing domain has, to some extent, formulated its own design flow of context-aware systems, the envisaged meet-in-the-middle integration approach maximizes the reuse of existing models and platforms, thus is promising for the highly-complex system design process.

Adaptable Service Delivery in Smart Environments

Service delivery and provision in smart environment BIBA 766-768
  Charles Gouin-Vallerand; Bessam Abdulrazak
This document presents our proposal for a workshop on service delivery/provision in smart environment. The proposed type of workshop is a mini-track, with expected 10 to 12 authors/participants, divided in three presentation sessions.
Precise passive RFID localization for service delivery in smart home BIBA 769-772
  Kevin Bouchard; Jeremy Lapalu; Bruno Bouchard; Abdenour Bouzouane
Smart home research foresees a future where persons afflicted by a type of cognitive impairment, such as Alzheimer's disease, could pursue a longer autonomous life at home by being punctually assisted in their everyday activities. Few research teams have begun noticing that not only we need to offer appropriate services at the right time, but also that we need to adapt them to the resident profile. To do so, we must increase the accuracy and the granularity of our knowledge about the current state of environment. In this paper, we propose a new system based on the cheap and non intrusive passive RFID technology for fine grained localization of objects inside a smart home. We do so in regard for better service delivery by providing richer information about the environment.
Software provision in smart environment based on fuzzy logic intelligibility BIBA 774-777
  Charles Gouin-Vallerand; Brian Y. Lim; Anind K. Dey
Ubiquitous applications and smart environment technologies are complex to deploy, manage and use. Intelligibility, in ubiquitous computing applications, explains to users what a system did (outputs) and why it did it (inputs or contextual information). Making software more intelligible can reduce the complexity of a system for users. This paper presents our work on an intelligibility strategy for fuzzy logic systems, applied to a context-aware software organization and service provision (SOSP) middleware for smart environments. This fuzzy logic intelligibility strategy has been evaluated and tested with two groups of real users (technical and less technical users), and two versions of our prototype (with and without intelligibility).
System services partitioning in ambient assisted living environment BIBA 778-781
  Cédric Seguin; Florent De Lamotte; Jeans-Luc Philippe
The aging population of European countries is becoming a social and economical stake. With age can come difficulties or disabilities to carry out daily life tasks, alone. Studies show that the number of the elderly people in France will be multiplied by two, within the next thirty years. To postpone as long as possible the hospitalization of dependent persons and allow them to live with dignity, researchers have been working on home automation, smart-homes and ambient assisted living. Nowadays, houses are still evolving and have, within them, equipments always more smarter. It is not uncommon to see electronic devices such as computer, connected tv and smart sensors: as many powerful resources not completely used. However, those untapped capacities could be used for person monitoring, video processing and other greedy algorithms, without adding any new specialized component. Thus it could ensure the quality of services required by the user and the dependability of its home automation system.
   This paper presents a method of service deployment in an environment for handicap persons, based on ontologies and supervision.
Weights of evidence for intelligible smart environments BIBA 782-785
  Brian Y. Lim; Anind K. Dey
Smart environments are improving their performance and services by increasingly using ubiquitous sensing and complex inference mechanisms. However, this comes at a cost of reduced intelligibility, user trust and control. The Intelligibility Toolkit was developed to support the automatic generation and provision of explanations to help users understand context-aware inference. We have extended the toolkit to generate explanations for a wider range of inference models and to provide two styles of explanations -- rule traces and weights of evidence. We describe explanations generated from several inference models for a smart home dataset for activity recognition. This demonstrates the versatility of using the Intelligibility Toolkit to retain explanatory capabilities across different inference models.
Generic architecture for ambient intelligence based on an organizational centered multi-agent approach BIBA 786-789
  Patrice C. Roy; Nicolas Lachiche; Pierre Gançarski; Alban Meffre; Christophe Collet
In order to maintain and improve the quality of life of elderly and people with cognitive impairments in their home, we must elaborate assistive technologies that will alleviate the effects of cognitive decline. The use of ambient intelligence, such as smart homes, is a way to provide assistance services. However, managing these services is not a trivial task. In this paper, we propose an organizational centered multi-agent system (OCMAS) architecture in order to manage these services in a smart home. This approach allows to ease the management of services and the deployment of new services in the smart home system dynamically.

Computer Mediated Social Offline Interactions (SOFTec 2012)

Workshop on Computer Mediated Social Offline Interactions (SOFTec 2012) BIBA 790-791
  Nemanja Memarovic; Marc Langheinrich; Vassilis Kostakos; Geraldine Fitzpatrick; Elaine M. Huang
The proliferation of social networking sites and mobile technology allows us to check on our friends and family, follow what experts in our field think, or simply 'check-in' online. While in many ways advantageous, the ability to be constantly connected is significantly affecting our offline interaction behavior. People sharing a table today might ignore each other for stretches at a time in order to interact with far-away friends through mobile technology instead. The goal of this workshop is to examine how we can build technologies that promote offline interactions. We plan to discuss how offline interactions can be spurred within different social groups and different settings through currently available devices and technologies. We also plan to explore how such technologies can be built and used for different types of offline engagement (e.g., playful vs. serious). The workshop aims to establish a community interested in computer mediated offline interaction.
Enriching family personal encounters with ambient social media BIBA 792-793
  Raymundo Cornejo; Mónica Tentori; Jesús Favela
As SNS become ubiquitous, users are exploiting SNS content to enrich in-person gatherings. In this paper we present the results of a 26-weeks deployment study of an interactive display involving a lightweight Facebook client, and a movement-based social exergame, to explore how this technology impact in-person interactions with one extended family. Our results indicate that the use of the display is semi-public, and catalyzed opportunistic gatherings. We close discussing how the social implications of our results contribute to the use of public social displays, and its social implications for encouraging people to be socially engaged.
Using media façades to engage social interaction BIBA 794-795
  Sven Gehring; Antonio Krüger
Media façades in urban spaces offer great potential for new forms of collaborative multi-user interaction. Beyond interaction, they also allow for connecting people and for triggering social interaction between the different users. We report on our experiences of how simultaneous interaction with a media façade at-a-distance can engage social offline interaction between users. We built an application that allows for simultaneous painting on a façade, and gathered informal feedback during the ARS Electronica Festival in Linz, Austria.
Reactions: Twitter based mobile application for awareness of friends' emotions BIBA 796-797
  Kiraz Candan Herdem
Social media services, such as Twitter, facilitate social interaction between friends providing a method to share of the information of their actions and states of mind. At times when emotions are running high, some people may benefit from the help of their friends. If people are aware of emotional states of their friends, they can start a conversation to understand why they feel like that and how to support them. I study on a new interaction method for the awareness of emotions and to manage the emotional states. This paper presents one part of my study that aims to help mobile users to interact offline with their friends when they need emotional support. Emotions of mobile users will be detected with the new emotion detection method in development.
Leveraging media repertoires to create new social ties BIBA 798-799
  Kenneth Joseph; Rui José; Kathleen M. Carley
We propose a system which allows users to select how and with whom they are available for contact by managing a set of personal "identities" and budding relationships. The most important of these media are public displays, which allow a low-cost barrier for finding potential friends through interaction via the display and through the attendance of displayed social events. In helping two people to both become aware of each other's existence and to pick media which suit their preferences, we believe such a system can increase the odds of two strangers forming a strong social bond.
Putting 'local' back into public Wifi hotspots BIBA 800-801
  Matthias Korn; Clemens Nylandsted Klokmose
Public Wifi hotspots in cafes and public places are based on wireless local area network technology (WLAN). In contrast to the common understanding of connecting directly to the internet when connecting to a Wifi hotspot, we are proposing to bring the original notion of connecting to a local network back to the fore. By hooking into the act of a user connecting to a local network, we see a design space emerge that allows us to spur various (off-and on-line) activities in a hyperlocal context. We propose to (re-)explore this notion of the locality of networks in the age of the ubiquitous Wifi hotspot in cafes, bars, community centers, and other (semi-)public places in order to facilitate co-located activities for such varied purposes as fostering local community, civic participation, sociality in general, and entertainment. We propose a network locality that builds on local infrastructure (WLAN) and combines personal devices (mobile phones) with stationary interactive surface technology (wall displays and tables) to facilitate social on-and off-line interactions in local settings. In this position paper, we outline technological opportunities associated with this idea as well as envisioned usage scenarios in different settings.
What can 'people-nearby' applications teach us about meeting new people? BIBA 802-803
  Eran Toch; Inbal Levi
'People-nearby' applications for meeting new people online are some of the most popular examples of systems that lead people from an online interaction to an offline interaction. This paper provides a critical review of available applications, and identifies three key properties that are essential for the applications: physical location, identity management, and trust. The paper suggests open research questions that can explain the success of these applications and guide the design of new technologies that encourage offline interactions.
Fostering off-line interactions through local ubicomp systems: the case of urban development BIBA 804-805
  Sebastian Weise; John Hardy; Pragya Agarwal; Paul Coulton; Adrian Friday; Mike Chiasson
Many global internet services today can be thought of as being managed 'top-down' without much appreciation or requirement for local control. New services such as location-based data stores implemented in cities around the world suggest opportunities for novel forms of management of data with relevance to a local context. We argue that such localization of ubiquitous system management provides an opportunity in supporting local off-line interaction and 'community building' and that urban development, which requires interaction between members of different communities, presents an interesting case where such systems could be realised.

Smart Gadgets Meet Ubiquitous and Social Robots on the Web (UbiRobots)

Smart gadgets meet ubiquitous and social robots on the web BIBA 806-809
  Abdelghani Chibani; Craig Schlenoff; Edson Prestes; Yacine Amirat
Ubiquitous robotics, ambient Intelligence and cloud robotics are new research topics that start to gain popularity among the robotics community. The overlap that exists now between ubirobots and AmI makes their integration together within cloud computing valuable to create a hybrid physical-digital space rich with myriad of proactive intelligent services that enhance the quality and the way of our living and working. Indeed, there is no visible cooperation or synergies between ubiquitous computing and robots communities. This paper presents a workshop that is intended to facilitate discussions and build a bridge between these communities. Moreover we hope that satellite topics such as affective computing, semantic reasoning, and human-computer interaction will enhance such discussions and foster the research in this area. We believe that both communities can learn and benefit from their mutual experiences.
Ontology-based state representation for intention recognition in cooperative human-robot environments BIBA 810-817
  Craig Schlenoff; Anthony Pietromartire; Zeid Kootbally; Stephen Balakirsky; Sebti Foufou
In this paper, we describe a novel approach for representing state information for the purpose of intention recognition in cooperative human-robot environments. States are represented by a combination of spatial relationships in a Cartesian frame along with cardinal direction information. This approach is applied to a manufacturing kitting operation, where humans and robots are working together to develop kits. Based upon a set of predefined high-level states relationships that must be true for future actions to occur, a robot can use the detailed state information presented in this paper to infer the probability of subsequent actions occurring. This would enable the robot to better help the human with the operation or, at a minimum, better stay out of his or her way.
Combining robotic frameworks with a smart environment framework: MCA2/SimVis3D and TinySEP BIBA 818-825
  Michael Arndt; Karsten Berns; Sebastian Wille; Norbert Wehn; Luiza de Souza
This work describes the combination of three software frameworks from two different domains: robotics and smart environments. The two robotic frameworks MCA2 and SimVis-3D that have been in use for several years on a multitude of different robotic systems and TinySEP, a modular framework for smart environments were combined to create a win-win-situation for both roboticists and ubiquitous computing researchers. The possibilities and advantages this combination can offer are discussed, especially in situations where mobile robots and smart environments coexist next to each other. This work is concluded by an experiment that shows the feasibility and the strengths of the proposed approach.
Nesting the context for pervasive robotics BIBA 826-833
  Tamás Haidegger; Marcos E. Barreto; Paulo J. S. Gonçalves; Maki Habib; Veera Ragavan; Craig Schlenoff; Alberto Vaccarella; Edson Prestes
Service robotics is becoming a leading application area of human-centered technologies, and the rise of household and personal assistance robots forecasts an utopist world of human -- robot collaborative society. Along the road, one of the robotics community's major tasks is to work on the harmonization of trends, standardization of terms, interfaces and technologies. It is important to keep the scientific and social progress under control through sufficient public outreach and technology dissemination. Along those lines, the IEEE Robotics & Automation Society is sponsoring a working group entitled Ontologies for Robotics and Automation that will bridge cutting edge technology to users of the services -- the general public. In this paper, the background of the project is presented, the definitions and examples of descriptive systems of relations are described, showing how ontologies can help to address the above challenges.
An evidential fusion approach for activity recognition under uncertainty in ambient intelligence environments BIBA 834-840
  Faouzi Sebbak; Abdelghani Chibani; Yacine Amirat; Farid Benhammadi; Aicha Mokhtari
In ambient intelligence environments, the information provided by robot's embedded sensors and physical or logical entities may be inaccurate and uncertain. The Dempster-Shafer evidence Theory (DST) gives a mathematical convenient framework for the evidential fusion representation and inference of uncertain information. However, DST yields counterintuitive results in high conflicting ambient intelligence situations. This paper aims to provide a new strategy to manage conflict in activity recognition process in the ambient intelligence applications. It addresses the challenge of uncertainty and proposes an evidential fusion model based on the management of conflicting situation to optimize decision making in activity recognition. The proposed approach gives intuitive interpretation for combining multiple sources in conflicting situations and avoids the problems of using The Dempster-Shafer rule of combination.
Modeling ontology for multimodal interaction in ubiquitous computing systems BIBA 842-849
  Ahmad Wehbi; Amar Ramdane Cherif; Chakib Tadj
People communicate with each other using different ways, such as words, gestures, etc. to give information about their status, emotions and intentions. But how may this information be described in a way that autonomous systems (e.g. Robots) can react with a human being in a given environment?
   A multimodal interface allows a more flexible and natural interaction between a user and a computing system. This paper presents a methodological approach for designing an architecture that facilitates the work of a fusion engine. The selection of modalities and the fusion of events invoked by the fusion engine are based upon the definition of an ontology that describes the environment where a multimodal interaction system exists.
Multimodal architecture to strengthen the interaction of the robot in ambient intelligence environments BIBA 850-851
  Nadia Touileb Djaid; Nadia Saadia; Amar Ramdane-Cherif
With the development of applications called "intelligent", one of the challenges of research on multimodality in ambient intelligence environments is the elaboration of architectural solutions that respond and adapt to different types of constraints in the human robotic interaction.
   These architectures must continually adapt to changes due to external disturbances or user actions. They are therefore subject to restrictions in use (in real time) when the robot interacts with the user and the environment.
   The main objective of this paper is to propose a model of adaptive software architecture, which allows the robot to use several modalities and make the fusion of the data to increase its interaction with the environment while considering the context. We also introduce fuzzy logic in the processing of data from input modalities. This multimodal software architecture that considers the context is modeled by colored, timed and stochastic Petri nets (CTSPN) simulated in CPNTools.
Web-based automated black-box testing framework for component based robot software BIBA 852-859
  Jeong Seok Kang; Hong Seong Park
Reliability of component based robot software depends on the quality of each component because any defective components will have a ripple effect on systems built with them. Thus, testing of unit component, composite component and component based robot software is critical for checking the correctness of the software functionality. This paper proposes Web-based automated black-box testing framework for component based robot software. The proposed framework provides automated testing service, testing for different robot platform and distributed test environment, and sharing test resources. We have implemented the proposed framework and evaluated it on the component based front guidance application to output a guidance statement by sensing front obstacles, and control robot wheels by sensing a back user.
Autonomic framework based on semantic models for self-management of ubiquitous systems BIBA 860-862
  Mahdi Ben Alaya; Thierry Monteil; Khalil Drira
The Internet of things consists of a high amount of heterogeneous objects that are widely distributed and evolve frequently according to their context changes. Management of such a complex environment is costly in terms of time and money. Designing a context aware autonomic framework with capability of self-management is a challenge. This paper proposes FRAMESELF, a generic and extensible autonomic framework to self-manage ubiquitous environments based on ontologies, graph models, and reasoning rules. A smart metering use case is experimented to illustrate the proposed solution.
Web-based service brokerage for robotic devices BIBA 863-865
  Simon Mayer
In this position paper we describe how technologies from the Web of Things domain could help to simplify and automate the interaction between robotic devices and their surroundings. Specifically, we discuss how Web patterns like Resource-oriented Architectures or Representational State Transfer together with semantic metadata could help to create environments where robots seamlessly interact with other devices in their vicinity: Using services provided by other devices and offering services themselves. One of the main goals in the Web of Things community is to furnish smart environments with sensors and actuators that offer self-described interfaces and are openly accessible from other devices -- Robots should be enabled to make use of this wealth of instrumentation of their surroundings!
Using indistinguishability in ubiquitous robot organizations BIBA 866-872
  John Lewis; Eric T. Matson; Sherry Wei
As robots become more pervasive and ubiquitous in the lives of humans, they become increasingly involved in everyday tasks formerly executed by humans. Humans should expect robots to take on tasks to simplify our lives, by working with humans just as other humans do, in normal organizations and societies. This labor specialization allows humans more comfort, time or focus on higher level desires or tasks. To further this unification of relationships, the defined line between humans and other non-humans must become more indistinguishable. This ever increasing degree of indistinguishability provides we care less about who or what executes a task or solves a goal, as long as that entity is capable and available. In this paper, we propose a model and a simple example implementation which minimizes the strict line between humans, software agents, robots, machines and sensors (HARMS) and reduces the distinguishability between these actors.
Towards an upper ontology and methodology for robotics and automation BIBA 873-882
  Edson Prestes; Abdelghani Chibani; Alessandro Saffiotti; Craig Schlenoff; Sébastien Gérard; Ricardo Sanz; Marcos E. Barreto; Raj Madhavan; Yacine Amirat
In this article, we present the ongoing efforts within the newly formed IEEE-RAS Working Group named Ontologies for Robotics and Automation. We focus in particular on one of the four subgroups that compose this working group, called the Upper Ontology/Methodology (UpOM) subgroup. As the name indicates, the aim of this subgroup is to develop an upper ontology and a methodology for ontology building and evaluation. This methodology will be used to coordinate the distributed development of domain specific ontologies by the other three subgroups, and to generate a global ontology that we hope will contribute to the standardization process of robotics and automation. This paper presents the composition, the envisioned methodology, and the future work of the UpOM subgroup. It also discusses some general aspects related to ontologies for the robotics and automation field, and to the efforts in standardizing them.
Future research challenges and applications of ubiquitous robotics BIBA 883-891
  Abdelghani Chibani; Yacine Amirat; Samer Mohammed; Norihiro Hagita; Eric T. Matson
Ambient intelligence, ubiquitous and networked robots, cloud robotics, are new research hot topics that start to gain popularity among the robotics community. They enable robots to acquire richer functionalities and open the way for the composition of a variety of robotic services with three functions: semantic perception, reasoning and actuation. This paper introduces the recent challenges and future trends of these topics.
Open platform for ubiquitous robotic services BIBA 892-893
  Mi-sook Kim; Hong Seong Park
Open Platform for Robotic Services (OPRoS) is an open source robot software platform funded by the Korean government. Its research results are released on its homepage. OPRoS supplies several IDEs working with its framework for easy and fast development. The Component Editor, Component Composer, and Simulator are core development tools for ubiquitous robot. Robot-in-the-loop-Simulation (RILS) is an additional simulation based development tool. This paper explains these core tools used with a reference robot.

Workshop on Location-Based Social Networks (LBSN 2012)

The preface of the 4th International Workshop on Location-Based Social Networks BIBA 894-896
  Yu Zheng; Jason Hong
We briefly introduce the 4th international workshop on location-based social networks (LBSN 2012), describing its objective, importance, and results.
We know where you live: privacy characterization of foursquare behavior BIBA 898-905
  Tatiana Pontes; Marisa Vasconcelos; Jussara Almeida; Ponnurangam Kumaraguru; Virgilio Almeida
In the last few years, the increasing interest in location-based services (LBS) has favored the introduction of geo-referenced information in various Web 2.0 applications, as well as the rise of location-based social networks (LBSN). Foursquare, one of the most popular LBSNs, gives incentives to users who visit (check in) specific places (venues) by means of, for instance, mayorships to frequent visitors. Moreover, users may leave tips at specific venues as well as mark previous tips as done in sign of agreement. Unlike check ins, which are shared only with friends, the lists of mayorships, tips and dones of a user are publicly available to everyone, thus raising concerns about disclosure of the user's movement patterns and interests. We analyze how users explore these publicly available features, and their potential as sources of information leakage. Specifically, we characterize the use of mayorships, tips and dones in Foursquare based on a dataset with around 13 million users. We also analyze whether it is possible to easily infer the home city (state and country) of a user from these publicly available information. Our results indicate that one can easily infer the home city of around 78% of the analyzed users within 50 kilometers.
Improving location prediction services for new users with probabilistic latent semantic analysis BIBA 906-910
  James McInerney; Alex Rogers; Nicholas R. Jennings
Location prediction systems that attempt to determine the mobility patterns of individuals in their daily lives have become increasingly common in recent years. Approaches to this prediction task include eigenvalue decomposition [5], non-linear time series analysis of arrival times [10], and variable order Markov models [1]. However, these approaches all assume sufficient sets of training data. For new users, by definition, this data is typically not available, leading to poor predictive performance. Given that mobility is a highly personal behaviour, this represents a significant barrier to entry. Against this background, we present a novel framework to enhance prediction using information about the mobility habits of existing users. At the core of the framework is a hierarchical Bayesian model, a type of probabilistic semantic analysis [7], representing the intuition that the temporal features of the new user's location habits are likely to be similar to those of an existing user in the system. We evaluate this framework on the real life location habits of 38 users in the Nokia Lausanne dataset, showing that accuracy is improved by 16%, relative to the state of the art, when predicting the next location of new users.
Predicting future locations with hidden Markov models BIBA 911-918
  Wesley Mathew; Ruben Raposo; Bruno Martins
The analysis of human location histories is currently getting an increasing attention, due to the widespread usage of geopositioning technologies such as the GPS, and also of online location-based services that allow users to share this information. Tasks such as the prediction of human movement can be addressed through the usage of these data, in turn offering support for more advanced applications, such as adaptive mobile services with proactive context-based functions. This paper presents an hybrid method for predicting human mobility on the basis of Hidden Markov Models (HMMs). The proposed approach clusters location histories according to their characteristics, and latter trains an HMM for each cluster. The usage of HMMs allows us to account with location characteristics as unobservable parameters, and also to account with the effects of each individual's previous actions. We report on a series of experiments with a real-world location history dataset from the GeoLife project, showing that a prediction accuracy of 13.85% can be achieved when considering regions of roughly 1280 squared meters.
Beyond "local", "categories" and "friends": clustering foursquare users with latent "topics" BIBA 919-926
  Kenneth Joseph; Chun How Tan; Kathleen M. Carley
In this work, we use foursquare check-ins to cluster users via topic modeling, a technique commonly used to classify text documents according to latent "themes". Here, however, the latent variables which group users can be thought of not as themes but rather as factors which drive check in behaviors, allowing for a qualitative understanding of influences on user check ins. Our model is agnostic of geo-spatial location, time, users' friends on social networking sites and the venue categories-we treat the existence of and intricate interactions between these factors as being latent, allowing them to emerge entirely from the data. We instantiate our model on data from New York and the San Francisco Bay Area and find evidence that the model is able to identify groups of people which are of different types (e.g. tourists), communities (e.g. users tightly clustered in space) and interests (e.g. people who enjoy athletics).
Exploring trajectory-driven local geographic topics in foursquare BIBA 927-934
  Xuelian Long; Lei Jin; James Joshi
The location based social networking services (LBSNSs) are becoming very popular today. In LBSNSs, such as Foursquare, users can explore their places of interests around their current locations, check in at these places to share their locations with their friends, etc. These check-ins contain rich information and imply human mobility patterns; thus, they can greatly facilitate mining and analysis of local geographic topics driven by users' trajectories. The local geographic topics indicate the potential and intrinsic relations among the locations in accordance with users' trajectories. These relations are useful for users in both location and friend recommendations. In this paper, we focus on exploring the local geographic topics through check-ins in Pittsburgh area in Foursquare. We use the Latent Dirichlet Allocation (LDA) model to discover the local geographic topics from the checkins. We also compare the local geographic topics on weekdays with those at weekends. Our results show that LDA works well in finding the related places of interests.
Crowd-sourced cartography: measuring socio-cognitive distance for urban areas based on crowd's movement BIBA 935-942
  Shoko Wakamiya; Ryong Lee; Kazutoshi Sumiya
On behalf of the rapid urbanization, urban areas are gradually becoming a sophisticated space where we often need to know ever evolving features to take the most of the space. Therefore, keeping up with the dynamic change of urban space would be necessary, while it usually requires lots of efforts to understand newly visiting and daily changing living spaces. In order to explore and exploit the urban complexity from crowd-sourced lifelogs, we focus on location-based social network sites. In fact, due to the proliferation of location-based social networks, we can easily acquire massive crowd-sourced lifelogs interestingly indicating their experiences in the real space. In particular, we can conduct various novel urban analytics by monitoring crowd's experiences in an unprecedented way. In this paper, we particularly attempt to exploit crowd-sourced location-based lifelogs for generating a socio-cognitive map, whose purpose is to deliver much simplified and intuitive perspective of urban space. For the purpose, we measure socio-cognitive distance among urban clusters based on human mobility to represent accessibility of urban areas based on crowd's movement. Finally, we generate a socio-cognitive map reflecting the proposed socio-cognitive distances which have computed with massive geo-tagged tweets from Twitter.
Mining the semantics of origin-destination flows using taxi traces BIBA 943-949
  Wangsheng Zhang; Shijian Li; Gang Pan
Origin-destination (OD) flows reflect both human activity and urban dynamic in a city. However, our understanding about their patterns remains limited. In this paper, we study the GPS traces of taxis in a city with several millions people, China and find that there are significant patterns under the OD flows constructed from taxis' random motion. Our spatiotemporal analysis shows that those patterns have close relationship with the semantics of OD flows, hence we can mine the semantics of OD flows from raw GPS trace data. The approach we proposed offers a novel way to explore the human mobility and location characteristic.
Towards reliable spatial information in LBSNs BIBA 950-955
  Ke Zhang; Wei Jeng; Francis Fofie; Konstantinos Pelechrinis; Prashant Krishnamurthy
The proliferation of Location-based Social Networks (LBSNs) has been rapid during the last year due to the number of novel services they can support. The main interaction between users in an LBSN is location sharing, which builds the spatial component of the system. The majority of the LBSNs make use of the notion of check-in, to enable users to volunteeringly share their whereabouts with their peers and the system. The flow of this spatial information is unidirectional and originates from the users' side. Given that currently there is no infrastructure in place for detecting fake checkins, the quality of the spatial information plane of an LBSN is solely based on the honesty of the users. In this paper, we seek to raise the awareness of the community for this problem, by identifying and discussing the effects of the presence of fake location information. We further present a preliminary design of a fake check-in detection scheme, based on location-proofs. Our initial simulation results show that if we do not consider the infrastructural constraints, location-proofs can form a viable technical solution.
Detection, classification and visualization of place-triggered geotagged tweets BIBA 956-963
  Shinya Hiruta; Takuro Yonezawa; Marko Jurmu; Hideyuki Tokuda
This paper proposes and evaluates a method to detect and classify tweets that are triggered by places where users locate. Recently, many related works address to detect real world events from social media such as Twitter. However, geotagged tweets often contain noise, which means tweets which are not content-wise related to users' location. This noise is problem for detecting real world events. To address and solve the problem, we define the Place-Triggered Geotagged Tweet, meaning tweets which have both geotag and content-based relation to users' location. We designed and implemented a keyword-based matching technique to detect and classify place-triggered geotagged tweets. We evaluated the performance of our method against a ground truth provided by 18 human classifiers, and achieved 82% accuracy. Additionally, we also present two example applications for visualizing place-triggered geotagged tweets.
Users sleeping time analysis based on micro-blogging data BIBA 964-968
  Haoran Yu; Guangzhong Sun; Min Lv
The emergence of new social network services, often labeled as Web 2.0, has permitted an amazingly increase of user generated content. In particular, Sina Weibo, a popular Chinese micro-blogging service is designed as platforms allowing users to generate contents that open to the public. From analyzing activates of submitting posts to Sina Weibo, some features of users can be estimated. This paper aims to contribute to this growing body of literature by studying how users' frequent activities reflect their sleeping time and living time zones. By mining a large set of users' activates data from Sina Weibo, we demonstrate its possible role to detect the sleeping time of users and find a new method for judging users' time zone.
Spatial dissemination metrics for location-based social networks BIBA 972-979
  Antonio Lima; Mirco Musolesi
The importance of spatial information in Online Social Networks is increasing at a fast pace. The number of users regularly accessing services from their phones is rising and, therefore, local information is becoming more and more important, for example in targeted marketing and personalized services. In particular, news, from gossips to security alerts, are daily spread across cities through social networks. Content produced by users is consumed by their friends or followers, whose locations can be known or inferred. The spatial location of users' social connections strongly affects the areas where such information will be disseminated. As a consequence, some users can deliver content to a certain geographic area more easily and efficiently than others, for example because they have a larger number of friends in that area.
   In this paper we present a set of metrics that quantitatively capture the effects of social links on the spreading of information in a given area. We discuss possible application scenarios and we present an initial critical evaluation by means of two datasets from Twitter and Foursquare by discussing a series of case studies.
LBSNRank: personalized pagerank on location-based social networks BIBA 980-987
  Zhaoyan Jin; Dianxi Shi; Quanyuan Wu; Huining Yan; Hua Fan
Different from traditional social networks, the location-based social networks allow people to share their locations according to location-tagged user-generated contents, such as checkins, trajectories, text, photos, etc. In location-based social networks, which are based on users' checkins, people could share his or her location according to checkin while visiting around. However, people's locations change frequently and the rankings of people change dynamically too, which makes ranking on graphs a challenging work. To address this challenge, we propose the LBSNRank algorithm on graphs with nodes whose contents change dynamically. To validate our algorithm on real datasets, we have crawled and analyzed a dataset from the Dianping website. Experiments on this real dataset show that our LBSNRank algorithm performs better than traditional personalized PageRank in efficiency.
Followee recommendation in asymmetrical location-based social networks BIBA 988-995
  Josh Jia-Ching Ying; Eric Hsueh-Chan Lu; Vincent S. Tseng
Researches on recommending followees in social networks have attracted a lot of attentions in recent years. Existing studies on this topic mostly treat this kind of recommendation as just a type of friend recommendation. However, apart from making friends, the reason of a user to follow someone in social networks is inherently to satisfy his/her information needs in asymmetrical manner. In this paper, we propose a novel mining-based recommendation approach named Geographic-Textual-Social Based Followee Recommendation (GTS-FR), which takes into account the user movements, online texting and social properties to discover the relationship between users' information needs and provided information for followee recommendation. The core idea of our proposal is to discover users' similarity in terms of all the three properties of information which are provided by the users in a Location-Based Social Network (LBSN). To achieve this goal, we define three kinds of features to capture the key properties of users' interestingness from their provided information. In GTS-FR approach, we propose a series of novel similarity measurements to calculate similarity of each pair of users based on various properties. Based on the similarity, we make on-line recommendation for the followee a user might be interested in following. To our best knowledge, this is the first work on followee recommendation in LBSNs by exploring the geographic, textual and social properties simultaneously. Through a comprehensive evaluation using a real LBSN dataset, we show that the proposed GTS-FR approach delivers excellent performance and outperforms existing stat-of-the-art friend recommendation methods significantly.
Geo-activity recommendations by using improved feature combination BIBA 996-1003
  Masoud Sattari; Murat Manguoglu; Ismail H. Toroslu; Panagiotis Symeonidis; Pinar Senkul; Yannis Manolopoulos
In this paper, we propose a new model to integrate additional data, which is obtained from geospatial resources other than original data set in order to improve Location/Activity recommendations. The data set that is used in this work is a GPS trajectory of some users, which is gathered over 2 years. In order to have more accurate predictions and recommendations, we present a model that injects additional information to the main data set and we aim to apply a mathematical method on the merged data. On the merged data set, singular value decomposition technique is applied to extract latent relations. Several tests have been conducted, and the results of our proposed method are compared with a similar work for the same data set.
TraMSNET: a mobile social network application for tourism BIBA 1004-1011
  Jorge Gaete-Villegas; Meeyoung Cha; Dongman Lee; In-Young Ko
By leveraging location data in online social networks, Location-based Social Networks (LBSNs) can support diverse human activities such as tourism. Different applications aim to aid tourists and provide better experience in their travels by matching co-located users based on what they have in common. However, users with little in common but with potential to help each other given the context and place could not be matched. In this paper we introduce traMSNet, a LBSN that implements a matching algorithm considering homophily, as well as users complementary skills in a touristic location. Our idea is validated with a survey that asked potential travelers about their needs when looking for a travel partner. Moreover, we present a matching algorithm that is evaluated it with real tourists. The evaluation shows that considering complementarity when matching individuals is preferred by users. Therefore, by only considering similarities, important issues are left aside.

Situation, Activity, and Goal Awareness (SAGAware 2012)

International Workshop on Situation, Activity and Goal Awareness (SAGAware 2012) BIBA 1012-1015
  Parisa Rashidi; Liming Chen; William K. Cheung
Ubiquitous computing aims to enable and support anywhere, anytime, context-aware applications. Sensing, interpretation and integration of events, behaviors and environmental states have been keys to the success of such ubiquitous systems. Over the past two decades, there has been a constant shift of sensor observation modeling, representation, interpretation and usage, namely from low-level raw observation data and their direct/hardwired usage, data aggregation and fusion, to high-level formal context modeling and context-based computing. It is envisioned that this trend will continue towards a further higher level of abstraction, allowing situation, activity and goal modeling, representation and inference, thus realizing the vision of ubiquitous computing. The proposed "mini-track" workshop intends to bring together researchers and practitioners from relevant fields to present and disseminate the latest accomplished and/or ongoing research on Situation, Activity and Situation Awareness (SAGAware) and their novel application in ubiquitous computing. It aims to facilitate knowledge transfer and synergy, bridge gaps between different research communities/groups, lay down foundation for common purposes, and help identify opportunities and challenges for interested researchers and technology and system developers.
An ontological context model for representing a situation and the design of an intelligent context-aware middleware BIBA 1016-1025
  Preeti Bhargava; Shivsubramani Krishnamoorthy; Ashok Agrawala
A major challenge of context models is to balance simplicity, generality, usability and extensibility. It is also important that the model be practical and implementable. In pursuit of this goal, this paper proposes a context model, Rover Context Model (RoCoM), structured around four primitives that can be used to represent and model any situation and activity: entities, events, relationships, and activities. It introduces the notion of templates of context for each primitive and describes, albeit briefly, the RoCoM Ontology (RoCoMO). It also describes the design and architecture of an abstract, generic and intelligent context-aware middleware called Rover II. We propose this framework as a solution to address the context problem as a whole, and be usable in many domains. We also illustrate its application with the aid of a context-aware public safety application that is deployed in the UMD campus.
A benchmark dataset to evaluate sensor displacement in activity recognition BIBA 1026-1035
  Oresti Baños; Miguel Damas; Héctor Pomares; Ignacio Rojas; Máté Attila Tóth; Oliver Amft
This work introduces an open benchmark dataset to investigate inertial sensor displacement effects in activity recognition. While sensor position displacements such as rotations and translations have been recognised as a key limitation for the deployment of wearable systems, a realistic dataset is lacking. We introduce a concept of gradual sensor displacement conditions, including ideal, self-placement of a user, and mutual displacement deployments. These conditions were analysed in the dataset considering 33 fitness activities, recorded using 9 inertial sensor units from 17 participants. Our statistical analysis of acceleration features quantified relative effects of the displacement conditions. We expect that the dataset can be used to benchmark and compare recognition algorithms in the future.
USC-HAD: a daily activity dataset for ubiquitous activity recognition using wearable sensors BIBA 1036-1043
  Mi Zhang; Alexander A. Sawchuk
Many ubiquitous computing applications involve human activity recognition based on wearable sensors. Although this problem has been studied for a decade, there are a limited number of publicly available datasets to use as standard benchmarks to compare the performance of activity models and recognition algorithms. In this paper, we describe the freely available USC human activity dataset (USC-HAD), consisting of well-defined low-level daily activities intended as a benchmark for algorithm comparison particularly for healthcare scenarios. We briefly review some existing publicly available datasets and compare them with USC-HAD. We describe the wearable sensors used and details of dataset construction. We use high-precision well-calibrated sensing hardware such that the collected data is accurate, reliable, and easy to interpret. The goal is to make the dataset and research based on it repeatable and extendible by others.
Health score prediction using low-invasive sensors BIBA 1044-1048
  Masamichi Shimosaka; Shinya Masuda; Kazunari Takeichi; Rui Fukui; Tomomasa Sato
Scores of health state for elderly people are regarded as important in nursing or medical fields. On the other hand, gaining the scores needs nurses to execute questionnaires. Owing to this, the execution rate for the health assessment is still low in ordinary homes. To solve this problem, we propose a method to predict the health score by using low-invasive sensors. We adopt regression as the prediction method and construct features to absorb the individual difference. As a part of feasibility study of social participation for elderly people, we execute the survey of health state using questionnaires by a nurse and install low-invasive sensors in real life simultaneously. Experimental result in the feasibility study shows a promise of the score prediction from sensor data. In addition, the result suggests that the extraction of features related to living behaviors improves the accuracy compared to using raw sensor data.
Passive detection of situations from ambient FM-radio signals BIBA 1049-1053
  Shuyu Shi; Stephan Sigg; Yusheng Ji
We introduce a passive system to recognise environmental situations. Differing from other RF-based approaches, our system has the advantage of neither installing a transmitter generating the signal nor equipping the monitored entities with any active component. When activities are performed, it consecutively samples ambient RF-signals, derived from a non-cooperating FM-radio source. Since changes in an environment impact the propagation of radio waves, this data implicitly contains information to distinguish environmental situations. We experimentally demonstrate the distinction of the situations 'empty room', 'opened door' and 'walking person' with an average accuracy of over 90%.
Applications of mobile activity recognition BIBA 1054-1058
  Jeffrey W. Lockhart; Tony Pulickal; Gary M. Weiss
Activity Recognition (AR), which identifies the activity that a user performs, is attracting a tremendous amount of attention, especially with the recent explosion of smart mobile devices. These ubiquitous mobile devices, most notably but not exclusively smartphones, provide the sensors, processing, and communication capabilities that enable the development of diverse and innovative activity recognition-based applications. However, although there has been a great deal of research into activity recognition, surprisingly little practical work has been done in the area of applications in mobile devices. In this paper we describe and categorize a variety of activity recognition-based applications. Our hope is that this work will encourage the development of such applications and also influence the direction of activity recognition research.
Predicting mobile application usage using contextual information BIBA 1059-1065
  Ke Huang; Chunhui Zhang; Xiaoxiao Ma; Guanling Chen
As the mobile applications become increasing popular, people are installing more and more Apps on their smart phones. In this paper, we answer the question whether it is feasible to predict which App the user will open. The ability for such prediction can help pre-loading the right Apps to the memory for faster execution or help floating the desired Apps to the home screen for quicker launch. We explored a variety of contextual information, such as last used App, time, location, and the user profile, to predict the user's App usage using the MDC dataset. We present three findings from our studies. First, the contextual information can be used to learn the pattern of user's App usage and to predict App usage effectively. Second, for the MDC dataset, the correlation between sequentially used Apps has a strong contribution to the prediction accuracy. Lastly, the linear model is more effective than the Bayesian model to combine all contextual information and for such predictions.
Evaluating the robustness of activity recognition using computational causal behavior models BIBA 1066-1074
  Frank Krüger; Alexander Steiniger; Sebastian Bader; Thomas Kirste
Activity recognition is a challenging research problem in ubiquitous computing domain and has to tackle omnipresent uncertainties, e.g., resulting from ambiguous or intermittent sensor readings. In this paper, we introduce an activity recognition approach based on causal modeling and probabilistic plan recognition. To evaluate the performance of our approach systematically, we generated sensor data with different error rates using a simulation. This data served as input for the activity recognition in a series of experiments. In these experiments we stepwise introduced and combined additional sources of uncertainty, i.e., different duration models and ignoring certain sensors, to demonstrate the robustness of our approach. Our evaluation shows that Computational Causal Behavior Models provide a basis for a robust activity recognition system.
Towards the detection of unusual temporal events during activities using HMMs BIBA 1075-1084
  Shehroz S. Khan; Michelle E. Karg; Jesse Hoey; Dana Kulic
Most of the systems for recognition of activities aim to identify a set of normal human activities. Data is either recorded by computer vision or sensor based networks. These systems may not work properly if an unusual event or abnormal activity occurs, especially ones that have not been encountered in the past. By definition, unusual events are mostly rare and unexpected, and therefore very little or no data may be available for training. In this paper, we focus on the challenging problem of detecting unusual temporal events in a sensor network and present three Hidden Markov Models (HMM) based approaches to tackle this problem. The first approach models each normal activity separately as an HMM and the second approach models all the normal activities together as one common HMM. If the likelihood is lower than a threshold, an unusual event is identified. The third approach models all normal activities together in one HMM and approximates an HMM for the the unusual events. All the methods train HMM models on data of the usual events and do not require training data from the unusual events. We perform our experiments on a Locomotion Analysis dataset that contains gyroscope, force sensor, and accelerometer readings. To test the performance of our approaches, we generate five types of unusual events that represent random activity, extremely unusual events, unusual events similar to specific normal activities, no or little motion and normal activity followed by no or little motion. Our experiments suggest that for a moderately sized time frame window, these approaches can identify all the five types of unusual events with high confidence.

Systems and Intrastructure for the Digital Home (HomeSys)

HomeSys: systems and infrastructure for the digital home BIBA 1085-1089
  Tom Rodden; Anmol Sheth
We present a workshop proposal focusing on future digital home infrastructures and systems needed to support ubiquitous computing applications and services. The workshop aims to be the premiere venue that brings together researchers and practitioners across the disciplines of Systems and Networking, Ubiquitous Computing and HCI to elaborate ways in which the current infrastructure in the digital home can be reshaped to meet the needs of users.
Engaging end users in real smart space programming BIBA 1090-1095
  Evgenia Litvinova; Petri Vuorimaa
Smart spaces, either public or private, has been a hot topic for more than a decade. They are claimed to bring various advantages for their users. However, only few people are actually using smart spaces. One of the reasons for that is the lack of attention paid to user interfaces used to control the space. Both industrial and academic research is often focused on hardware and device interoperability issues. There is not enough studies about end-user mental models, how and why people want to control and program smart spaces. In this position paper, we propose a strategy of how to bring end-user programming in smart spaces into real life. Our idea is three-fold: 1) concentrate on users' mental models, 2) create intuitive ubiquitous user interface, which combines the direct interaction pattern and the magnetic poetry interface metaphor, and 3) install a control system in a public smart space, where a lot of people can use it on daily basis. We aim to conduct a long term user study, from which we are planning to get unique data about evolution of people's expectations and mental models in the context of smart space control.
MagnoTricorder: what you need to do before leaving home BIBA 1096-1101
  Mostafa Uddin; Tamer Nadeem
In this paper we present the design and the evaluation of a framework MagnoTricorder, a system that utilizes the magnetic sensor in smartphones to detect the running devices at home thru a singlepoint sensing. MagnoTricorder leverages the effect of Electro Magnetic Interference (EMI) generated by the AC current in the main power-line at home. This EMI induces a magnetic field that highly fluctuates the reading of the magnetic sensor in smartphones. In this paper, we utilize this characteristic for detecting and identifying the running devices at home thru the Circuit Breaker Panel. Experimental evaluation demonstrates the feasibility of the developed framework. Results show that MangoTricorder can detect and identify individual devices with 93%-98% accuracy.
Living with an intelligent thermostat: advanced control for heating and cooling systems BIBA 1102-1107
  Rayoung Yang; Mark W. Newman
In order to better understand the opportunities and challenges of an intelligent system in the home, we studied the lived experience of a thermostat, the Nest. The Nest utilizes machine learning, sensing, and networking technology, as well as eco-feedback features. To date, we have conducted six interviews and one diary study. Our findings show that improved interfaces through web and mobile applications changed the interactions between users and their home system. Intelligibility and accuracy of the machine learning and sensing technology influenced the way participants perceive and adapt to the system. The convenient control over the system combined with limitations of the technology may have prevented the desired energy savings. These findings assert that thoughtful, continuous involvement from users is critical to the desired system performance and the success of interventions to promote sustainable choices. We suggest that an intelligent system in the home requires improved intelligibility and a better way in which users can provide deliberate input to the system.
HomeLab: shared infrastructure for home technology field studies BIBA 1108-1113
  A. J. Bernheim Brush; Jaeyeon Jung; Ratul Mahajan; James Scott
Researchers who develop new home technologies using connected devices (e.g. sensors) often want to conduct large-scale field studies in homes to evaluate their technology, but conducting such studies today is quite challenging, if not impossible. Considerable custom engineering is required to ensure hardware and software prototypes work robustly, and recruiting and managing more than a handful of households can be difficult and cost-prohibitive. To lower the barrier to developing and evaluating new technologies for the home environment, we call for the development of a shared infrastructure, called HomeLab. HomeLab consists of a large number of geographically distributed households, each running a common, flexible framework (e.g., HomeOS [4]) in which experiments are implemented. The use of a common framework enables engineering effort, along with experience and expertise, to be shared among many research groups. Recruitment of households to HomeLab can be organic: as a research group recruits (a few) households to participate in its field study, these households can be invited to join HomeLab and participate in future studies conducted by other groups. As the pool of households participating in HomeLab grows, we hope that researchers will find it easier to recruit a large number of households to participate in field studies.
Putting home users in charge of their network BIBA 1114-1119
  Yiannis Yiakoumis; Sachin Katti; Te-Yuan Huang; Nick McKeown; Kok-Kiong Yap; Ramesh Johari
Policy-makers, ISPs and content providers are locked in a debate about who can control the Internet traffic that flows into our homes. In this paper we argue that the user, not the ISP or the content provider, should decide how traffic is prioritized to and from the home. Home users know most about their preferences, and if they can express them well to the ISP, then both the ISP and user are better off. To test the idea we built a prototype that lets users express highlevel preferences that are translated to low-level semantics and used to control the network.

Methodical Approaches to Prove the Effects of Subliminal Perception in Ubiquitous Computing Environments

Methodical approaches to prove the effects of subliminal perception in ubiquitous computing environments BIBA 1120-1121
  Andreas Riener; Miriam Reiner; Myounghoon Jeon; Pierre Chalfoun
To cope with the rising volume of information in human-computer interfaces, explicit and attentive interaction is more and more frequently replaced by implicit means of information exchange, supported by context-and activity-aware systems and applications. The trend of excessive information is, however, still ongoing, calling for further solutions to reduce a persons cognitive load or level of attention. Subliminal interaction techniques are considered a promising approach to deliver information to a person without causing much supplementary workload. This workshop aims at discussing the potential of subliminal perception to improve the information flow for human-computer interaction in the light of the fact that, up to now, the results have been mixed. One group of researchers has provided evidence that subliminal stimulation works, but the other has found that it does not, or even cannot, work. To clarify this issue, experts from various domains attending the workshop will discuss how subliminal effects can be scientifically supported or how a certain claim could be empirically refuted.
The role of subliminal perception in vehicular interfaces BIBA 1122-1126
  Andreas Riener; Myounghoon Jeon
Following laws and provisions passed on the national and international level, the most relevant goal of future traffic and vehicular interfaces is to increase road safety. To alleviate the cognitive load associated with the interaction with the variety of emerging information and assistance systems in the car, subliminal stimulation is assumed to be a promising technique. To assess the potential of subliminal cues that could be used as their interaction means in future vehicles, we have organized a workshop within the frame of the automotive user interfaces conference (AutoUI 2011) to discuss this topic in a group of experts. This paper summarizes the findings from that workshop and should give researchers a starting point for their own activities in the field by indicating sort of grand research challenges and most critical issues. In particular, the goal of this summary article is to make this challenging research field more 'tangible' for researchers working in a range of disciplines, such as engineering, neuroscience, computer science, and psychophysiology. While currently discussed in the automotive domain only, the principles, research questions, and findings could immediately (and easily) be transferred to and adopted in other research fields. Interaction based on subliminal techniques can have an impact on society at large, making significant contributions toward a more natural, convenient, and even relaxing future style of interaction with any complex systems.
A systematic approach to using music for mitigating affective effects on driving performance and safety BIBA 1127-1132
  Myounghoon Jeon
Research has shown that affective effects on driving performance and safety are as dangerous as (or even more dangerous than) effects of the secondary tasks [11]. There has been some research on the use of speech-based systems for the intervention, but little research on the use of music has attempted to mitigate a driver's affective states while driving. The current paper identifies various taxonomies of the effects of music and explores plausible research variables, considerations, and practical application directions.
More cooperative, or more uncooperative: decision-making after subliminal priming with emotional faces BIBA 1133-1137
  Juan Liu; Xianghong Sun; Yan Ge; Kan Zhang
Is subliminal priming able to affect people's choices and decision-making? The prisoners' dilemma is a canonical example of a game analyzed that shows why two individuals might not cooperate each other, even if it appears that it is in their best interest to do so. In the regular version of the prisoner's dilemma game, collaboration is dominated by betrayal, and as a result, the only possible outcome of the game is for both prisoners to betray the other. Regardless of what the other prisoner chooses one will always gain a greater payoff by betraying the other. Because betrayal is always more beneficial than cooperation, all objective prisoners would seemingly betray the other. This study examined whether subliminal emotional faces influence human's decision-making in the repeated prisoners' dilemma. In this study, subliminal emotional face was the independent variable. According to different emotional valence (happy, neutral or angry) and different present way of emotional faces (a transparent figure, or a backward masking face), the independent variable has 7 levels. So, 84 undergraduates were randomly divided into seven groups, participants in each group were subliminally primed with one kind of unseen face, after which they completed pre-designed negotiations task. The results showed that whatever the way to show subliminal emotional faces: by a transparent figure, or backward masking, both affected human's decision-making. Under the influence of different ways to present subliminal faces, participants choose their own behavior more cooperative or more uncooperative. These findings contribute to subliminal perception research on decision-making and the implications for this study are discussed.
Affective priming with subliminal auditory stimulus exposure BIBA 1138
  Xianghong Sun; Yan Ge; Kan Zhang; Juan Liu
The primacy hypothesis about affection (Zajonc, 1980) holds that positive and negative affective reactions can be elicited with minimal stimulus input and virtually no cognitive processing. This hypothesis challenges the cognitive appraisal viewpoint (Lazarus, 1982), which maintains that affection cannot emerge without prior cognitive mediation. There have been many studies shown that human emotion could be affected by subliminal visual stimulus, so how about subliminal auditory stimulus (SAS)? In this study two pieces of traditional Chinese music were used as SAS, and the unheard music was played in a continuous loop, which was different from the commonly used priming paradigm. 56 undergraduates were randomly divided into two groups, participants in one group were exposed to the subliminal happy music, and in the other group were exposed to the subliminal sad music. A before-and-after self-paired design was used to assess the emotion of all the subjects. During the experiment their galvanic skin response (GSR) and subjective ratings were recorded. The results showed that SAS caused the obviously change on human's GSR, but there was no change found in their subjective ratings of emotional valence (happy-unhappy). A lot of evidence showed that GSR was more sensitive than subjective ratings for the evaluation to current emotion status. The overall results of our study confirmed this perspective. So, we believed that SAS affected people's emotion, and this kind of affective priming wasn't perceived consciously by people themselves.
Incorporating subliminal perception in synthetic environments BIBA 1139-1144
  David Pizzi; Ilkka Kosunen; Cristina Viganó; Anna Maria Polli; Imtiaj Ahmed; Daniele Zanella; Marc Cavazza; Sid Kouider; Jonathan Freeman; Luciano Gamberini; Giulio Jacucci
Advanced interactive visualization such as in virtual environments and ubiquitous interaction paradigms pose new challenges and opportunities in considering real-time responses to subliminal cues. In this paper, we propose a synthetic reality platform that, combined with psychophysiological recordings, enables us to study in realtime the effects of various subliminal cues. We endeavor to integrate various aspects known to be relevant to implicit perception. The context is of consumer experience and choice of an artifact where the generation of subliminal perception through an intelligent 3D interface controls the spatio-temporal aspects of the information displayed and of the emergent narrative. One novel contribution of this work is the programmable nature of the interface that exploits known perceptive phenomena (e.g. masking, crowding and change blindness) to generate subliminal perception.
Are you cool enough for Texas Hold'Em Poker? BIBA 1145-1149
  Marc Kurz; Gerold Hölzl; Andreas Riener; Bernhard Anzengruber; Thomas Schmittner; Alois Ferscha
Experienced poker players have the ability to suppress and hide emotions and reactions to avoid providing information about the quality of the dealt private cards and the own probability of winning to the adversaries. Besides unswayable luck and bravery, bluffing is the only skill that could massively improve the own chance of winning. This paper investigates whether a subliminal reaction in terms of changing facial surface skin temperature can be linked to the quality of the dealt private cards (i.e., the probability of winning the actual hand). Therefore, a dataset containing thermal imaging has been recorded during a No Limit Texas Hold'Em Poker tournament-session with six players in total and two players being observed with a high-resolution thermal imaging camera and manual provision of their dealt private cards as ground-truth. Preliminary results show that the facial skin temperature varies massively (±1.2°C), which constitutes the research hypothesis that a significant change in the surface face skin temperature can be linked to the quality of the dealt cards in terms of winning chance for an actually played hand.
Perifoveal display: combining foveal and peripheral vision in one visualization BIBA 1150-1155
  Valentin Heun; Anette von Kapri; Pattie Maes
The Perifoveal Display (see Figure 1) is a visualization display for complex, real-time, dynamic data such as stock market data, traffic or control room as well as virtual 3D environments. The system takes advantage of the unique properties of the human perceptive system, which is capable of perceiving a high degree of detail in the foveal area, but has a unique more subliminal type of perception of movement and brightness in the peripheral area. The Perifoveal Display varies how data is visualized based on the user's viewing direction. Data in the center of the user's focus is displayed in a lot of detail. Movement and change in brightness as well as amount of detail and size highlight important data changes that fall into the periphery. The results of our user study show that the system is able to support the user while observing complex data.

Digital Object Memories for the Internet of Things (DOMe-IoT)

Digital Object Memories for the Internet of Things (DOMe-Iot) BIBA 1156-1159
  Fahim Kawsar; Chris Speed; Alexander Kröner; Jens Haupert; Thomas Ploetz; Daniel Schreiber
The Internet of Things connects digital information sources with physical objects -- which transforms an artifact from being a passive object into a 'thing' that may link to data, store data and even offer data to users. Digital Object Memories (DOMe) comprise hardware and software components, which together provide an open and universal platform for capturing, associating, and interacting with the digital information of connected objects -- including storage, documentation and provision of information concerning actions an object is or might be involved in. The goal of this continuation of an established workshop series (predecessor events include DIPSO 2007-09 in conjunction with Ubicomp 2007-09, DOMe in conjunction with Intelligent Environment 2009, DOMe-IoT 2010 in conjunction with Ubicomp 2010, and NOMe-IoT in conjunction with Ubicomp 2011) is to twofold: 1.) initiate a conversation concerning the potential for objects to develop agency; and 2.) explore how data that is associated with an object may leverage real-world actions. Here, DOMe 2012 provides a hybrid interdisciplinary workshop format that will combine traditional presentations and discussion with practice-based experimentation.
How to instill activity into digital object memories BIBA 1160-1163
  Jens Haupert; Christian Hauck; Alexander Kröner
In todays product management life-cycle data play a growing role. Fixed product data, sensor readings and external events form continuously growing data collections, the digital object memory. To create a surplus value, this data is exploited in applications, e.g. by asking queries to such memories (e.g. "get unexpected observations"). The necessary logic to answer such questions may vary with time as different entities come in contact with different types of objects. This raises the challenge how to decouple questions from the corresponding logic, how to modify the logic, how to deploy such logic to the memory and how to execute the logic on the memory itself. This article describes work in progress concerning extending an existing memory framework to support analysis, processing and communication behavior of so called Active Digital Object Memories.
Customizing instructions from smart objects BIBA 1164-1166
  Luc Weiler; Alexander Kröner; Boris Brandherm
The Internet of Things enables authors to use physical objects for communicating digital content that may influence human decision making. Human experts may employ this novel information channel to deliver instructions concerning an object right where it is needed -- at the object. Eventually, the user of such an object may perceive the object as an expert information source. However, since real-world actions are usually performed in contexts difficult to predict by the author of such instructions, a follower will have to adapt these before application. This article proposes to link knowledge concerning such adaptation with the object as well, and thus to create a two-way communication between expert author and instruction follower.
Take me I'm yours: mimicking object agency BIBA 1167-1170
  Chris Speed; Duncan Shingleton
This paper speculates, through a design demonstration, upon a future context in which objects will begin to talk to us and even give us instructions. The purpose of the research is to anticipate a time when correlations between the data sets that are associated with different objects are found and the objects themselves are used to impart this 'new' knowledge back to us. Such an occasion may be considered to represent a form of agency.
   Located within the technical and cultural context of the Internet of Things, this paper introduces a lineage for our relationship with objects from 1. Read Only, 2. Read and Write and 3. Read, Write and Act. The paper proceeds to establish the conditions for a third generation of Internet of Things by articulating the nature of networks, their structure and their capacity to support the principles of Actor-Network Theory which may lead to a condition in which objects may take on a form of agency.
   The paper further introduces an iPhone App entitled Take Me I'm Yours that operates as a working but speculative design project mimicking the conditions in which objects may talk to us. The designers speculate a design fiction in which object databases may begin to identify associations and propose 'actions' to a user. The application and demonstration at UbiComp 2012 will offer delegates an opportunity to experience a sense of what it may feel like in the future when objects may begin telling us what to do.
Adaptive workflows in smart environments: combining imperative and declarative models BIBA 1171-1174
  Marcus Staender; Aristotelis Hadjakos; Daniel Schreiber
Specifying interaction between users and smart environments is an important topic in pervasive computing. Both imperative and declarative languages have been investigated in this context. Declarative approaches require more abstract thinking and higher modeling effort but enable greater flexibility. A survey of related work suggests, however, that the high modeling effort of declarative approaches is prohibitive to their practical application. In contrast, imperative approaches lead to static control-flow and over-specification. Still, they are used, mainly due to their simplicity. Our approach supports a systematic transformation process from imperative models to declarative ones. Our method comprises an imperative, workflow-based language that we extended with novel declarative constructs and an algorithm for converting imperative models into declarative ones. Our approach requires only a modest level of declarative specification literacy for reaching a degree of flexibility that formerly only expert designers could achieve with hand-crafted declarative models.
Prosthetic memory: object memories and security for children BIBA 1175-1178
  Juan Antonio; Álvarez García; Luis Miguel Soria Morillo; Juan Antonio Ortega Ramírez; Ismael Cuadrado Cordero
Children younger than 3 years old are very special humans, their psychomotor and social development is very fast and parents and relatives would like to know every new detail (when, who, where, what, how and why) in real time. These news are difficult to remember and some kind of diary is needed. Here we propose a "prosthetic memory" based on Digital Object Memories applied to Web of Things using hidden NFC tags in children's clothes, mobile applications for smartphones and a central server to store the ontologized information.
Approaches to interacting with digital object memories in the real world BIBA 1179-1182
  Ralph Barthel; Martin de Jode; Andrew Hudson-Smith
As IoT (Internet of Things) technologies and infrastructures become more mature, opportunities for engagement with representations of digital object memories (DOM) in the real world increase. Digital object memories can provide added value and pave the way for new consumer-oriented IoT products and services. However, our research experience of employing digital object memories in different systems for reminiscing, mediation of second-hand retail environments and augmenting digital heritage experiences (e.g. in museums) also point to some significant challenges as to how people can interact with DOMs in situ. Based on this work we will put forth some of the key user experience challenges that we encountered when employing representations of DOMs in the real world in the course of the last two and a half years and discuss some alternative routes we wish to explore through future research.
Experiments with the internet of things in museum space: QRator BIBA 1183-1184
  Andrew Hudson-Smith; Steven Gray; Claire Ross; Ralph Barthel; Martin de Jode; Claire Warwick; Melissa Terras
Emergent Internet of Things (IoT) based technologies offer the potential for new ways in engaging with places, spaces and objects. The use of mobile and tablet computing linked specifically to objects and memory, comment and narrative creation opens up a potentially game-changing methodology in user interaction above and beyond the traditional 'kiosk' type approach. In this position statement we detail the QRator project in the Grant Museum at University College London. The QRator project explores how handheld mobile devices and Internet enabled interactive digital labels can create new models for public engagement, personal meaning-making and the construction of narrative opportunities inside museum spaces. The project won the United Kingdom National Museum and Heritage Award for Innovation for exploring the cultural shift that is anticipated as society moves to a ubiquitous form of computing in which every device is 'on', and every device is connected in some way to the Internet.
Balancing human agency and object agency: an end-user interview study of the internet of things BIBA 1185-1188
  Haiyan Jia; Mu Wu; Eunhwa Jung; Alice Shapiro; S. Shyam Sundar
Advances in the field of the Internet of Things (IoT) have made it possible for everyday objects to attain agency. However, it is unclear how laypersons perceive the increasingly active artifacts. These perceptions are likely to foreground their future responses to IoT objects as they become relevant actors in the physical world and begin to influence everyday user experience. We conducted an in-depth interview study to investigate individuals' knowledge, attitudes, expectations and concerns relating to IoT technologies. Findings show that affordances such as interactivity and modality can be reconceptualized in order to enhance user perceptions of relatedness with the objects. Different from technology-centric and user-centric approaches, the paper suggests a balance between human agency and object agency by adopting a need-oriented design paradigm when building an integral, self-adjusting, user-relevant archetype of IoT.
Digital object memories for the internet of things (DOMe-IoT) BIBA 1189-1192
  Alexander Kröner; Jens Haupert; Chris Speed; Fahim Kawsar; Thomas Ploetz; Daniel Schreiber
Digital Object Memories (DOMes) comprise hardware and software components, which together provide an open and universal platform for capturing and interacting with the digital information of connected objects -- including storage, documentation and provision of information concerning actions an object is or might be involved in. We envisage that connected objects equipped with DOMes will be enabled to make suggestions and propositions to human users -- which implies that an object may have a level of agency. The latter concept is a striking possibility that may change the way that we perceive, interact, and relate to objects. The goal of this established workshop series is to twofold: 1.) initiate a conversation concerning the potential for objects to develop agency; and 2.) explore how data that is associated with an object may leverage real-world actions. DOMe-IoT 2012 provides a hybrid interdisciplinary workshop format that will combine traditional presentations and discussion with practice-based experimentation.