HCI Bibliography Home | HCI Conferences | FAC Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
FAC Tables of Contents: 070911131415

FAC 2014: 8th International Conference on Foundations of Augmented Cognition: Advancing Human Performance and Decision-Making through Adaptive Systems

Fullname:AC 2014: 8th International Conference on Foundations of Augmented Cognition: Advancing Human Performance and Decision-Making through Adaptive Systems
Note:Volume 25 of HCI International 2014
Editors:Dylan D. Schmorrow; Cali M. Fidopiastis
Location:Heraklion, Crete, Greece
Dates:2014-Jun-22 to 2014-Jun-27
Publisher:Springer International Publishing
Series:Lecture Notes in Computer Science 8534
Standard No:DOI: 10.1007/978-3-319-07527-3 hcibib: FAC14; ISBN: 978-3-319-07526-6 (print), 978-3-319-07527-3 (online)
Links:Online Proceedings | Conference Website
  1. Emotional and Cognitive Issues in Augmented Cognition
  2. Machine Learning for Augmented Cognition
  3. Augmented Cognition for Learning and Training
  4. Augmented Cognition for Health and Rehabilitation

Emotional and Cognitive Issues in Augmented Cognition

Physiological Synchronization Is Associated with Narrative Emotionality and Subsequent Behavioral Response BIBAKFull-Text 3-13
  Bethany K. Bracken; Veronika Alexander; Paul J. Zak; Victoria Romero; Jorge A. Barraza
Neurophysiological compliance is a correlation of neurophysiological measures (synchronicity) between individuals. Higher compliance among team members is related to better performance, and higher synchronicity occurs during emotional moments of a stimulus. The aim of the current study is to examine whether synchrony may be observable via peripheral nervous system (PNS) activity. We used inter-subject correlation (ISC) analysis to assess whether synchronicity of PNS measures are related to stimulus emotionality or similarity in behavioral responses. Participants viewed a 100-second emotional video, followed by an appeal to donate experimental earnings to a related charity. We found high ISC for cardiac and electrodermal activity (EDA) between donors versus non-donors. For both groups, we found an association between ISC of cardiac activity and emotional moments in the stimulus. For non-donors we found an association between ISC of EDA and emotional moments. Our findings indicate that PNS measures yield similar results to neurophysiological measures.
Keywords: Cognitive Modeling; Perception; Emotion; and Interaction; Physiological Synchronization; Inter-Subject Correlation Analysis; RR-Interval; Skin Conductance Level; Narrative
A Social-Cognitive Prediction of the Perceived Threat of Terrorism and Behavioral Responses of Terrorist Activities BIBAKFull-Text 14-25
  Lisa A. Cave
This paper applies a social-cognitive model to the situation in Israel following the second intifada. In the model cognitive and social-contextual factors directly influence behavioral responses to terrorism as well as indirectly through affective factors. The findings suggest that the perceived risk of a terrorist attack influenced both preparedness and anxiety and concern. However, in some cases the influence of anxiety and concern on behavioral responses was greater than the cognitive or social-contextual factors i.e. gas mask preparedness. In other cases, the Iranian nuclear threat, the perceived risk did not influence the level of preparedness indirectly through anxiety and concern. The divergence in these findings reflects overconfidence in the state's ability to cope with the nuclear threat and the hypothetical nature of the responses.
Keywords: risk perception; social-cognition; terrorism
Untangling Operator Monitoring Approaches When Designing Intelligent Adaptive Systems for Operational Environments BIBAKFull-Text 26-34
  Ming Hou; Cali M. Fidopiastis
An Intelligent Adaptive System (IAS) is a synergy between an intelligent interface and adaptive automation technologies capable of context sensitive interaction with operators. A well-designed IAS should enable flexible task allocation between the operator and the machine. Research suggests that the integration of real-time operator state assessment (e.g., performance, psychophysiology) can create a true 'human-in-the-loop' system, thereby minimizing deleterious performance effects such as overlooking automation failures and slowly reorienting to tasks. However, these research approaches apply a variety of methodologies to determine sensors, metrics, and overall system design when applied to real world tasks. This paper seeks to untangle these issues such that a more comprehensive framework for systematically evaluating the utility of cognitive state detection methods is attainable.
Keywords: Intelligent tutoring systems; adaptive automation; augmented cognition; psychophysiological measures; cognitive state
Semantic Representation Analysis: A General Framework for Individualized, Domain-Specific and Context-Sensitive Semantic Processing BIBAKFull-Text 35-46
  Xiangen Hu; Benjamin D. Nye; Chuang Gao; Xudong Huang; Jun Xie; Keith Shubeck
Language agnostic methods for semantic extraction, encoding, and applications are an increasingly active research area in computational linguistics. This paper introduces an analytic framework for vector-based semantic representation called semantic representation analysis (SRA). The rationale for this framework is considered, as well as some successes and future challenges that must be addressed. A cloud-based implementation of SRA as a domain-specific semantic processing portal has been developed. Applications of SRA in three different areas are discussed: analysis of online text streams, analysis of the impression formation over time, and a virtual learning environment called V-CAEST that is enhanced by a conversation-based intelligent tutoring system. These use-cases show the flexibility of this approach across domains, applications, and languages.
Keywords: Semantic analysis; language agnostic; domain vocabulary; intelligent tutoring systems
Toward Multi-brain Communication: Collaborative Spelling with a P300 BCI BIBAKFull-Text 47-54
  Christoph Kapeller; Rupert Ortner; Gunther Krausz; Markus Bruckner; Brendan Z. Allison; Christoph Guger; Günter Edlinger
In a brain-computer interface (BCI), users perform specific mental tasks to convey messages or commands through direct measures of brain activity. Typically, users must perform each mental task for two or more seconds before their brain activity is distinct enough for accurate classification. In P300 BCIs, this usually entails silently counting specific flashes three or more times. Although numerous articles have explored the prospect of a P300 BCI that relies on only one flash, results consistently show that the resulting accuracy would be too low for effective communication. The goal of this article was to introduce a new way to reduce the time to identify a message or command. Instead of relying on brain activity from one subject, our system utilized brain activity from eight subjects performing a single trial. Hence, the system could rely on an average based on eight trials, which is more than sufficient for adequate classification, even though each subject contributed only one trial. Results confirmed that all eight subjects could not have attained effective control with a single trial, but could attain 100% accuracy when the other seven subjects' data were also used. This is the first time that people worked together to accomplish a goal with a BCI, and could encourage future research into collaborative brain-based communication and control.
Keywords: brain-computer interface (BCI); brain-machine interface (BMI); multi-brain computing; multi-brain gaming; EEG; ERP; P300; spelling
Deducing User States of Engagement in Real Time by Using a Purpose Built Unobtrusive Physiological Measurement Device: An Empirical Study and HCI Design Challenges BIBAKFull-Text 55-66
  Anthony Psaltis; Charalampos Rizopoulos; Zacharias Lekkas; Constantinos Mourlas
Human emotion is a psycho-physiological state in most cases not obvious to the subject. Different permutations of emotional constituents sometimes cause similar outward expressions; therefore facial expression methods cannot achieve reliable estimates. Sensing physiological manifestations of hormonal and neural stimulations instigated by emotion and affect is widely accepted as a credible method of detecting psycho-physiological states. A major impediment in interactive environments employing physiological sensing affecting the credibility of measurements is the physical and psychological impairment caused by electrodes and wiring used for the acquisition of signals. In the system described in this paper, the above obstacle has been overcome. Physiological signals acquired via an in-house developed computer mouse and coinciding physiological patterns were investigated as reactions to emotion raising events. A classification algorithm analyzed herein produced a real time allocation model of states of engagement. Experiments have revealed strong correlations between events and respective emotional states.
Keywords: HCI; Biofeedback Measurements; Affective Interactions; User Evaluation; Stress Loading
Ubiquitous Augmented Cognition BIBAKFull-Text 67-77
  Anna Skinner; Clementina Russo; Lisa Baraniecki; Molly Maloof
The paradigm shift in pervasive computing drives human-computer interaction (HCI) toward complex domains, where novel approaches to support human cognition in mobile and dynamic environments are necessary. The field of Augmented Cognition (AugCog) provides a scientifically-grounded approach toward intrinsic human information processing and challenges associated with data-intensive systems, leveraging empirically-based HCI solutions that account for human cognitive limitations. Applying this to ubiquitous computing demands unobtrusive technologies capable of time-dependant user assessment in various environments. Technological advances and utilization of personal activity reporting at a consumer level have made ubiquitous AugCog a necessary implementation. Such technologies (i.e., head-mounted displays) produce a deluge of data, generating a need for experimentally-based metrics, algorithms, and adaptive interfaces for closed-loop, synergistic human-technology performance systems. A Ubiquitous AugCog framework is proposed along with an essential use case to guide the design of multi-modal human performance assessment and optimization tools beyond laboratory settings.
Keywords: HCI; Augmented Cognition; Ubiquitous Computing; Pervasive Computing
Our Emotions as Seen through a Webcam BIBAFull-Text 78-89
  Natalie Sommer; Leanne Hirshfield; Senem Velipasalar
Humanity's desire to enable machines to "understand" us drives research that seeks to uncover the mysteries of human beings and of their reactions. That is because a computer's ability to correctly classify our emotions will lead to an enhanced experience for a user. Making use of the eye of the computer, a webcam, we can acquire human reaction data through the acquisition of facial images in response to stimuli. The data of interest in this research are changes in pupil size and gaze patterns in conjunction with classification of facial expression. Although fusion of these measurements has been considered in the past by Xiang and Kankanhalli [14] as well as Valverde et al. [15], their approach was quite different from ours. Both groups used a multimodal set-up: an eye tracker alongside a webcam and the stimulus was visual. A novel approach is to avoid costly eye trackers and rely on images acquired only from a standard webcam to measure changes in pupil size, gaze patterns and facial expression in response to auditory stimuli. The auditory mode is often preferred since luminance does not need to be accounted for, unlike visual stimulation from a monitor. The fusion of the information from these features is then used to distinguish between negative, neutral and positive emotional states. In this paper we discuss an experiment (n = 15) where the stimuli from the auditory version of the international affective picture system (IAPS) are used to elicit these three main emotions in participants. Webcam data is recorded during the experiments and advanced signal processing and feature extraction techniques are used on the resulting image files to achieve a model capable of predicting neutral, positive, and negative emotional states.

Machine Learning for Augmented Cognition

Neural Network Estimation of Atmospheric Thermodynamic State for Weather Forecasting Applications BIBAKFull-Text 93-103
  William J. Blackwell; Adam B. Milstein; Bradley Zavodsky; Clay B. Blankenship
We present recent work using neural network estimation techniques to process satellite observation of the Earth's atmosphere to improve weather forecasting performance. A novel statistical method for the retrieval of atmospheric temperature and moisture (relative humidity) profiles has been developed and evaluated with sounding data from the Atmospheric InfraRed Sounder (AIRS) and the Advanced Microwave Sounding Unit (AMSU) on the NASA Aqua satellite and the Infrared Atmospheric Sounding Interferometer (IASI) and AMSU on the EUMETAT MetOp-A satellite. The present work focuses on the cloud impact on the AIRS and IASI radiances and explores the use of stochastic cloud clearing mechanisms together with neural network estimation. The algorithm outputs are ingested into a numerical model, and forecast information and decision support tools are then presented to a meteorologist. We discuss the underlying physical problem, the algorithmic framework, and the interaction with forecaster.
Keywords: Neural networks; numerical weather prediction; weather forecasting
Augmenting Human Cognition with Adaptive Augmented Reality BIBAKFull-Text 104-113
  Jayfus T. Doswell; Anna Skinner
Wearable Augmented Reality (AR) combines research in AR, mobile/ubiquitous computing, and human ergonomics in which a video or optical see-through head mounted display (HMD) facilitates multi-modal delivery of contextually relevant and computer generated visual and auditory data over a physical, real-world environment. Wearable AR has the capability of delivering on-demand assistance and training across a variety of domains. A primary challenge presented by such advanced HCI technologies is the development of scientifically-grounded methods for identifying appropriate information presentation, user input, and feedback modalities in order to optimize performance and mitigate cognitive overload. A proposed framework and research methodology are described to support instantiation of physiologically-driven, adaptive AR to assess and contextually adapt to an individual's environmental and cognitive state in real time. Additionally a use case within the medical domain is presented, and future research is discussed.
Keywords: augmented cognition; augmented reality; context-awareness; cognitive display; mobile computing; mixed-reality; wearable computing
Two Steps Back for One Step Forward: Revisiting Augmented Cognition Principles from a Perspective of (Social) System Theory BIBAKFull-Text 114-124
  Sven Fuchs; Jessica Schwarz; Frank O. Flemisch
One decade after the Augmented Cognition concept validation experiments, the field may have passed the hype phases of inflated expectations and disillusionment but seems to have lost traction before reaching the maturity necessary for broad acceptance and widespread application. The authors suggest that the engineering-driven approach to the field's challenges may have been necessary in the beginning but should be complemented by looking into implications from the social sciences. The goal of this paper is to raise awareness for the field of (social) system theory by taking two steps back: One to revisit the foundational concepts of AugCog from an alternative perspective, another to illustrate the relevance and importance of social systems principles to the AugCog field. We outline practical implications that (social) system theory holds for the design of adaptation management and conclude our review by suggesting that an approach to human-system cooperation may be able to address the challenges.
Keywords: adaptive systems; adaptation management; augmented cognition; cooperative human-machine systems; human-systems integration; systems engineering; system theory
Mining and Modeling the Phenomenology of Situational Awareness BIBAKFull-Text 125-135
  Monte Hancock; Michael Higley
One expert has said "Most simply put, situational awareness (SA) is knowing what is going on around you." [1] "Knowing" is not just having a checklist of facts. Functionally, SA is about possessing information of sufficient scope and accuracy to support decision making that facilitates effective action. Augmented Cognition research shows that presenting too much data, even of high quality, can be as harmful to effective cognition as presenting little or no data [2]. Research has shows that in 35% of aviation errors in SA, all needed information was present, but not attended to by decision makers. [3] This work presents a formal but simple mathematical SA Model, and describes the application of data mining and modeling to SA errors resulting from inattention to the most salient facts. The model is applied to two data sets to demonstrate a general approach to automating the detection and diagnosis of SA errors.
Keywords: situational awareness; decision support; coincidental correctness; context error
Team Behaviors and Cognitive Cohesion in Complex Situations BIBAKFull-Text 136-147
  Cynthia Lamb; Jerry Lamb; Ronald Stevens; Abaigeal Caras
Our research has indicated that, in addition to technical skills, deliberate and effective team practices are necessary to manage the wide variety of simultaneous and increasingly complex problems that occur during tactical operations. This paper looks at team performance from two aspects, the first is observable team behaviors and the second is from two objective measures of team interactions. The combined results point toward a fuller understanding of team dynamics that can be applied to assessment, improvement, and prediction of team performance in operational situations.
Keywords: Team; Team Performance; Cognitive Cohesion; Team Behaviors; Submarines
Architecture for Machine Learning Techniques to Enable Augmented Cognition in the Context of Decision Support Systems BIBAKFull-Text 148-156
  David Martinez
For a wide range of applications, one of the key challenges is to identify an architecture that is suitable for machine learning techniques to enable important augmented cognition capabilities in the context of complex decision support systems. This overview paper presents an architecture framework. The elements of the architecture are described starting with data formatting, a machine learning algorithm taxonomy, components of courses of action, resource management, and finally the role of augmented cognition within the architecture. The paper includes one cyber security example where the architecture framework is employed. The paper concludes with future work in the development of a recommender system.
Keywords: Machine learning; decision support systems; human-machine interfaces; recommender system
Teams Reorganize Neurodynamically When They Sense Loss of Control BIBAKFull-Text 157-166
  Ronald Stevens; Trysha Galloway
Perturbations to the normal flow of teamwork arise externally through changes in the environment or internally as a result of the team's processes / decisions. We used quantitative neurophysiologic models of the rhythms and organizations of teams to examine the effects of these two classes of perturbations on team neurodynamics. Electroencephalographic (EEG) signals from dyads were transformed into cognitive workload estimates and then into neurodynamic symbols (NS) showing the second-by-second workload of each individual as well as the team. Periods of changing cognitive organizations were identified by a moving average smoothing of the Shannon entropy of the NS data stream and related to team speech, actions and responses to external and internal task changes. Dyads performing an unscripted map navigation (HCRC Map Task) developed fluctuating NS dynamics around the construct of workload which were disrupted by external task perturbations or when the team became confused or uncertain of their progress. Importantly, we detected no significant neurodynamic fluctuations associated with periods when the team made mistakes and did not realize they made the mistake. These results indicated that neurodynamics reorganizations occurred in teams in response to multiple types of perturbations, but primarily when the team perceived difficulties.
Keywords: team neurodynamics; entropy; coordination dynamics; rhythms
Assessing Neural Synchrony in Tutoring Dyads BIBAKFull-Text 167-178
  Bradly Stone; Anna Skinner; Maja Stikic; Robin Johnson
The current study examined synchronous psychophysiological monitoring across a tutor and tutee during a spatial reasoning video game, Tetris®. We hypothesized that increased synchrony across tutor-tutee would correlate with increased performance (i.e. increased learning. A teaming platform enabled simultaneous electroencephalogram (EEG) and electrocardiogram (ECG) acquisition for the tutor-tutee dyad throughout the gaming sessions, using the B-Alert® X10 EEG system (Advanced Brain Monitoring, Inc, Carlsbad, CA). A sample of n = 15 healthy participants as tutees with a single tutor across all dyads completed the protocol with each tutee playing 3 rounds of Tetris®. Initial results indicate small, significant, correlations in psychophysiological metrics that increased with experience. Exploratory stepwise regressions found the correlations explained more variance in performance than individual tutee/tutor psychophysiological metrics. These data imply that synchrony on a psychophysiological level between tutor and tutee impact tutee performance. Further examination of more complex synchrony metrics is required.
Keywords: Neurophysiology; EEG; ECG; Neural Synchrony

Augmented Cognition for Learning and Training

Insights into User Personality and Learning Styles through Cross Subject fNIRS Classification BIBAKFull-Text 181-189
  Danushka Bandara; Leanne Hirshfield; Senem Velipasalar
There is limited literature on classifying user personality/learning style and other cross subject traits using brain activity patterns. In this paper we describe an experiment to classify a computer user's' personality type and learning style using their brain data acquired while they were conducting spatial/verbal tasks in front of a computer. The brain activity in the left and right hemispheres were measured by an fNIRS device and the resulting data was analyzed using the participant's personality/learning style as the label (Obtained through established survey instruments). We obtained promising results for all of the traits we strived to classify providing paths for future research into this area.
Keywords: fNIRS; Personality; Learning styles; Cross subject Classification; Visual/Verbal tasks
Using a Cognitive/Metacognitive Task Model to Analyze Students Learning Behaviors BIBAKFull-Text 190-201
  Gautam Biswas; John S. Kinnebrew; James R. Segedy
Adapting to learners' needs and providing useful, individualized feedback to help them succeed has been a hallmark of most intelligent tutoring systems. More recently, to promote deep learning and critical thinking skills in STEM disciplines, researchers have begun developing open-ended learning environments that present learners with complex problems and a set of tools for learning and problem solving. To be successful in such environments, learners must employ a variety of cognitive skills and metacognitive strategies. This paper discusses a framework that combines a theory-driven, top-down approach with a bottom-up, pattern-discovery approach for analyzing learning activity data in these environments. Combining these approaches allows for more complex qualitative and quantitative interpretation of a student's cognitive and metacognitive abilities. The results of this analysis provide a foundation for developing performance- and behavior-based learner models in conjunction with adaptive scaffolding mechanisms to promote effective, personalized learning experiences.
Keywords: metacognition; theory-driven top-down analysis; pattern-driven bottom-up analysis; effectiveness measures; pattern mining; adaptivity; tutoring
Just Enough Fidelity in Student and Expert Modeling for ITS BIBAKFull-Text 202-211
  Brandt Dargue; Elizabeth Biddle
Intelligent Tutoring Systems (ITSs) are usually comprised of three primary models -- an expert model, a domain or system model, and a student model. Many of these models are quite complex to enable just about any learner to get the optimum tailored experience possible. These systems have shown great results, typically at least one standard deviation (a letter grade) better than traditional training (e.g. [1] [2]). This complexity not only ensured that ITSs were successful, it also prohibited their widespread use (e.g. [3]). Results of studies in which the expert and system models were simplified show similar gains in effectiveness (e.g. [4] [5]), suggesting that lower-cost ITSs can be just as effective as those developed at higher costs. This paper compares the results of effectiveness studies in which the ITSs had various levels of fidelity and presents some recommended guidelines in determining the level of fidelity for student, expert, and system models of the ITS.
Keywords: Cognitive Modeling; Perception; Emotion and Interaction; Machine Learning; Neural Networks Techniques for Data Processing; Adaptive User Interfaces; Human performance improvement; Intelligent Tutoring; Adaptive training
How the Granularity of Evaluation Affects Reliability of Peer-Assessment Modelization in the OpenAnswer System BIBAKFull-Text 212-223
  Maria De Marsico; Andrea Sterbini; Marco Temperini
The OpenAnswer system has the goal of exploiting teacher mediated peer-assessment for the evaluation of answers to open ended questions. The system models both the learning state of each student and their choices during peer-assessment. In OpenAnswer, each student is represented as a Bayesian network made of a triple of finite-domain variables: K for student's Knowledge about a topic, J for the estimated ability to evaluate ("Judge") the answer of another peer, C for Correctness of the answer to a given question. The student's individual sub-networks are connected through further Bayesian variables which model each peer-assessment choice, depending on the type of peer-assessment performed: (G for grading, B for choosing the best, W for choosing the worst). During an assessment session, each student grades a fixed number of peers' answers. The final result for a given session is a full set of grades for all students' answers, although the teacher had actually graded only a part of them. The student's assessments are instantiated in the network as evidence, together with the teacher's (perhaps partially complete) grades, so that OpenAnswer deduces the remaining grades. In the former OpenAnswer implementation, all variables were represented through a probability distribution over three values (Good/Fair/Bad for K and J, correct/fair/wrong for C). We present experiments and simulations showing that, by increasing the domain granularity for all variables from 3 to 6 values (A to F), the information obtained from the Bayesian network achieves higher reliability.
Keywords: assessment; peer-assessment; social collaborative e-learning
What Is Adaptivity? Does It Improve Performance? BIBAKFull-Text 224-235
  Jacqueline A. Haynes; Jody S. Underwood; Robert Pokorny; Amit Spinrad
Asking whether adaptivity improves performance is the wrong question. The right question is what kinds of adaptivity should be used to tailor the interactions between learner, context, objective, and instructional approach to maximize learning and performance. Most research on adaptive learning has focused on learning in intelligent tutoring systems and other digital learning environments. However, there is a lack of research that focuses on retention and deeper learning. This paper will define adaptivity, review different types of adaptivity used for instruction and their effects within the learning environment and longitudinally, and give some examples of how we have used adaptivity for short- and long-term improvement in performance and learning. We conclude that adaptivity in learning environments should be used to focus on deep conceptual learning promoting long term results.
Keywords: adaptivity; intelligent tutoring systems; digital learning environments; learning; pedagogy; individualized instruction
Visualizing Adaptive Learning Effects on Clinical Skill Acquisition and Decay BIBAKFull-Text 236-244
  Phillip M. Mangos; Ari Bodaghee
The purpose of this paper is to present a visualization tool, grounded in modern psychometric theory, for optimizing the parameters of adaptive training systems. The tool can be used in a research capacity to rapidly visualize the course, trajectory, and shape of one's learning curves resulting from different adaptive training conditions and how these are affected by conditions intrinsic to both the task domain and the learner.
Keywords: Adaptive training; skill acquisition; data visualization; medical simulation
How Real Is Good Enough? Assessing Realism of Presence in Simulations and Its Effects on Decision Making BIBAKFull-Text 245-256
  Debbie Patton
Simulations are frequently used for experimentation and training in many domains as a safe and cost-effective stand-in for real world experiences. However, research about which factors (trait and state) affect how real a simulation is to a person and how this "realness" affects cognition is lacking. Presence research lacks the assessment of interactions between psychological and physiological responses in interactive immersive environments. This paper provides empirical results from both trait and state psychological and physiological measures to identify and provide operationally relevant information regarding the realism of presence in a 300° immersive simulation and its effects on a Shoot-Don't-Shoot decision-making task. Participants engaged in a Shoot-Don't-Shoot simulation under three types of feedback conditions: (1) small shock, (2) life bar, and (3) no feedback. Results indicate that (1) trait uncertainty mitigates the stress experience and (2) both immersion and errors were significantly greater in the shock condition. Recommendations for future research are discussed.
Keywords: stress; cognition; performance; decision making; simulation; presence; military
Utilizing the Generalized Intelligent Framework for Tutoring to Encourage Self-Regulated Learning BIBAKFull-Text 257-264
  Anne M. Sinatra
Self-regulated learning is of particular importance to computer-based and online instruction, as students need to manage their own time and their interactions with the system. Elements of self-regulatory learning traditionally include the metacognitive strategies of the students (e.g., their knowledge of their planning, and assessment of their own progress), their management of educational goals (e.g., what information is most important to them, and should receive their primary attention), and the strategies that students use in order to study and retain the provided information [1, 2]. By incorporating feedback and guidance within computer-based learning activities it can encourage students to engage in successful self-regulated learning with a better awareness of their own cognition, and strategies. Intelligent tutoring systems can utilize adaptive scaffolding and guidance in order to support self-regulated student learning [3]. The Generalized Intelligent Framework for Tutoring (GIFT) [4] is an open-source adaptive tutoring system framework. The included tools within GIFT can be used to structure courses which guide individuals through the learning environment and are consistent with self-regulated best practices. The current paper includes a brief review of research into self-regulated learning in the context of computer-based and adaptive instruction. Further, the authoring capabilities of GIFT are discussed, and recommendations are given for future feature additions to GIFT which will benefit instructors who wish to develop courses that facilitate self-regulated learning.
Keywords: Strategy assessment and individual differences; Self-Regulated Learning; Adaptive Tutoring; Intelligent Tutoring Systems
Using Learner Data to Influence Performance during Adaptive Tutoring Experiences BIBAKFull-Text 265-275
  Robert A. Sottilare
During computer-based tutoring sessions, Intelligent Tutoring Systems (ITSs) adapt planning and manage real-time instructional decisions. The link between learner data and enhanced performance is the adaptive tutoring learning effect chain through which learner data informs learner state classification which in turn informs optimal instructional decisions to enhance performance. This paper examines the roles and influence of learner data in both short-term (also called run-time or session) and long-term (also called persistent) learner models used to support adaptive tutoring decisions within the Generalized Intelligent Framework for Tutoring (GIFT). To enhance the usability of tutoring systems and learner performance, recommendations for the design of future learner models are also presented.
Keywords: adaptive tutoring; learner modeling; Intelligent Tutoring Systems

Augmented Cognition for Health and Rehabilitation

An Alternative Design Perspective for Technology Supporting Youngsters with Autism BIBAKFull-Text 279-287
  Priscilla Braz; Viviane Felipe David; Alberto Raposo; Simone Diniz Junqueira Barbosa; Clarisse Sieckenius de Souza
People with autism present several disabilities in communication, social interaction and behavioral fields. There is a wide variation among these individuals and it is essential to develop therapies and materials customized for them. There are many design approaches in Human-Computer Interaction, but most of them present some limitations for designing to this audience. We conducted a study using paper prototyping with children with autism in order to contribute to the design of software for them. In this paper, we report some limitations in using this technique and the need for customizing applications for the individual who will use them. Reflecting on these needs and analyzing approaches to interface design, we present and discuss a proposal for a design methodology that combines Meta-design and Semiotic Engineering.
Keywords: Autism; Prototyping; Semiotic Engineering; Meta-design
The Predictability of Pharm-EEG in Patients with Long Unconscious Status BIBAKFull-Text 288-295
  Sergey Lytaev; Mikhail Aleksandrov; Sergey Vasilyev; Anna Arutunyan
The main syndrome of severe poisoning is coma. An option of coma outcome is a vegetative state. EEG reactivity due to intravenous benzodiazepines estimates the prognosis for such patients. However, a positive benzodiazepines test has the predictability of about 50-60%. The aim of the work is to assess the role of interaction between gamma amino butyric acid (GABA) and cholinergic systems of the brain. The consequent injections of benzodiazepine and atropine lead to a 20% increase in predictability. The results obtained confirm the following hypothesis. Abnormality of GABA-cholinergic interaction is one of the mechanisms of forming a stable pathological system resulting in the pathogenesis of the vegetative state.
Keywords: acute poisoning; neurotoxicity; acute cerebral insufficiency; EEG; bioelectric activity
Somneo: Device with Thermal Stimulation for Modulating Sleep Architecture and Enhancing Neuro-Cognitive Function BIBAKFull-Text 296-304
  Catherine McConnell; Djordje Popovic; Chris Berka; Dan Levendowski; Gene Davis
Sleep deprivation and inefficiency can have a crucial impact on performance. One potential method for ameliorating the impact of bad sleep, or eliminating it all-together, is with sleep stage-dependent sensory stimulation. The effect of superficial facial heating on sleep architecture was studied in 10 subjects. A 20% decrease in sleep onset latency (p < 0.05) was measured when the face was heated by 1oC. These results are support for further development of the patented Somneo, a ubiquitous feedback device for optimizing sleep architecture and duration; through the real-time assessment of sleep stage, and delivery of stage-dependent thermal, visual and/or auditory sensory stimulation.
Keywords: Sleep; Sleep Deprivation; Sensory Stimulation; Performance Optimization; Wearable Devices
Contribution of Biosensors to Enhancing Performance for Users with Special Needs BIBAKFull-Text 305-314
  Thanh Truc T. Nguyen; Martha E. Crosby; Marie Iding; Neil G. Scott
This paper describes two lines of research addressing the use of biosensors for populations with disabilities. The first line of research focused on deriving changing cognitive state information from the patterns of data acquired from users with the goal of improving presentation of multimedia computer information. Detecting individual differences via performance and psychometric tools can be supplemented by using real-time physiological sensors such as eye tracking and pressure applied to a computer mouse. We describe a computer task that demonstrates how to identify cognitive state and discuss types of physiological and cognitive state measures and associated advantages and disadvantages. Adaptive information filtering is discussed as a model for using the physiological information to improve individual performance. In the second line of research we interviewed participants with disabilities in an engineering vocational training program about their needs and suggestions for assistive devices that incorporate biosensors.
Keywords: biosensors; special needs; cognition; physiological sensors; adaptive information filtering
Finding Keys for People with Mild Dementia -- Not Just a Matter of Beeping and Flashing BIBAFull-Text 315-324
  Lars Oestreicher
Searching for everyday objects are a frequent activity for most people. Misplaced keys, mobiles and other devices are a source of annoyance, and even more so, if people are affected by memory problems. Searching for objects is a frustrating activity, especially if this is a frequently recurring phenomenon. There are several existing techniques for retrieving objects, but many of them do not use the available technology to the full extent, providing solutions that are almost "good-enough" but not necessarily useable practice.
   In this paper we present a solution that is intense to be more than good-enough, and simultaneously argue that there is a need for solutions that don't only facilitate a good life for people with impairments, but that also does so with the user's emotional experience (UEX?) in focus.
Patients Initiated Timeline Marking of Events in Parkinson's Disease: Visualization of Time Correlation between Patients Marked Events and Acquired Data from Sensors BIBAKFull-Text 325-334
  J. Artur Serrano; Andrea Thoms; Peter Weber
The reality of a Parkinson's Disease patient involves coping with the condition 24 hours a day for the rest of her or his life. A continuous decay of physical and sometimes cognitive functions makes activities of daily life progressively more difficult to accomplish. Many keep a diary where they take note of feelings, relevant events related to the daily routines, reaction to the medication, etc. Such diaries may prove extremely useful for a better understanding of the disease progression, both by the patient and by the doctor. The SENSE-PARK project went a step forward: it combines the patient diary notes (self-reported) with information gathered from movement sensors (automatic measurement) and a visualization mechanism combining the two. A system has been designed, prototyped and tested. Parkinson's medical specialists, user experience experts, technologists and most important the patients themselves, were involved in this process.
Keywords: Parkinson's Disease (PD); People with Parkinson's (PwP's); patient diaries; marking of events; symptom; timeline; chronic disease management; self-management; second level prevention; activities of daily living (ADL); movement sensor; accelerometer; monitoring; degenerative disease; time correlation; User Centred Design (UCD); participatory design
Biomarker and Biometric Indices of Cognitive Decrements due to Physical Exhaustion BIBAKFull-Text 335-346
  Regina M. Shia; Kyle Traver; Lindsey K. McIntire; Josh A. Hagen; Chuck D. Goodyear; Leanne N. Dykstra; Andrea R. Myers
State of the art sensors and diagnostic tools are continuously being researched, tested, and procured for every piece of high tech equipment in the Air Force while the most critical asset, the Airman, lacks diagnostics to analyze physiological well being and cognitive performance. Eighteen active duty Air Force males completed a physical exhaustion task on a treadmill while performing two cognitive tasks and while having various biometrics and biomarkers collected. We found that while physiological variables exhibited reliable indices of physical exertion, biological changes were found to be more related to cognitive changes.
Keywords: Biomarkers; Physical Exhaustion; Cognitive Performance; Biometrics
Smartphones, Smart Seniors, But Not-So-Smart Apps: A Heuristic Evaluation of Fitness Apps BIBAKFull-Text 347-358
  Paula Alexandra Silva; Kelly Holden; Aska Nii
This paper reports on the results of a heuristic evaluation of Nike+ and RunKeeper, two of the most popular health and fitness mobile apps found in both Google Play and the iTunes stores for Android and iOS platforms respectively. Given the potential benefit of practicing physical exercise in living a healthier and longer life, this study aimed at understanding whether or not these apps are ready to accommodate the needs of older adult users. The study concludes that the inspected apps are not ready to accommodate older adults needs. Small target sizes, insufficient contrast and reduced font sizes, are some of the common violations found in the user interfaces; these are also impeditive of the use of the apps by this target user population. It is thus necessary to highlight these issues in order to eliminate the barrier of access to these apps by this population by also encouraging careful observation of design guidelines.
Keywords: Older adults; gamification; health and fitness; heuristics; heuristic evaluation; active aging
ERmed -- Towards Medical Multimodal Cyber-Physical Environments BIBAFull-Text 359-370
  Daniel Sonntag
With new technologies towards medical cyber-physical systems, such as networked head-mounted displays (HMDs) and eye trackers, new interaction opportunities arise for real-time interaction between cyber-physical systems and users. This leads to cyber-physical environments in which the user has an active role to play inside the cyber-physical system. With our medical application in the context of a cancer screening programme, we are combining active speech based input, passive/active eye tracker user input, and HMD output (all devices are on-body and hands-free) in a convenient way for both the patient and the doctor inside such a medical cyber-physical system. In this paper, we discuss the design and implementation of our resulting Medical Multimodal Cyber-Physical Environment and focus on how situation awareness provided by the environmental sensors effectively leads to an augmented cognition application for the doctor.