[1]
SpiroVest: an e-textile-based wearable spirometer with posture change
adaptability
Poster, demo, & video presentations
/
Enokibori, Yu
/
Ito, Yoshu
/
Suzuki, Akihisa
/
Mizuno, Hirotaka
/
Shimakami, Yuuki
/
Kawabe, Tsutomu
/
Mase, Kenji
Adjunct Proceedings of the 2013 International Joint Conference on Pervasive
and Ubiquitous Computing
2013-09-08
v.2
p.203-206
© Copyright 2013 ACM
Summary: Daily continuous spirometry is expected to detect lung disease initial
symptoms that occur in daily contexts. Current medical spirometers are
insufficient for such usage because they force uncomfortable conditions for
users, such as pinching their noses with a clip and holding a mouthpiece in
their mouths. To solve this issue, we propose an e-textile-based wearable
spirometer called SpiroVest that estimates lung behavior from torso-girth
movements. It does not require any uncomfortable conditions that interfere with
daily activity. In addition, our wearable spirometer is able to estimate
accurate respiratory volume against variety of postures by a simple and
posture-independent error reduction mechanism.
[2]
E-textile pressure sensor based on conductive fiber and its structure
Poster, demo, & video presentations
/
Enokibori, Yu
/
Suzuki, Akihisa
/
Mizuno, Hirotaka
/
Shimakami, Yuuki
/
Mase, Kenji
Adjunct Proceedings of the 2013 International Joint Conference on Pervasive
and Ubiquitous Computing
2013-09-08
v.2
p.207-210
© Copyright 2013 ACM
Summary: This paper proposes a novel e-textile-based pressure sensor. Textile is a
common material in our life, used in such items as sheets, seats, and clothing.
If these items are equipped with sensor functions, they can invisibly assist
humans without significant lifestyle changes. Our sensor is suitable for mass
production and durable in daily hard use cases. The sensor is woven with common
weaving machines with a special manner and its material is a common low-cost
conductive fiber that does not use special and costly materials, such as
optical fiber. The sensor mechanism is supported by the textile structure; thus
our sensor has durability for frictional force and scratch occurring sometime
in daily context. In this paper, we also introduce two example usages of our
textile sensor: a bed-size body pressure sensor for anti-pressure-ulcer
treatment and a wearable foot-pressure sensor for walk and skill analyses.
[3]
Unit selection using k-nearest neighbor search for concatenative speech
synthesis
Poster session
/
Mizuno, Hideyuki
/
Takahashi, Satoshi
Proceedings of the 3rd International Universal Communication Symposium
2009-12-03
p.379-382
Keywords: concatenative speech synthesis, nearest neighbor search, synthesis unit
selection, text to speech
© Copyright 2009 ACM
Summary: We propose a new approach to rapidly identifying adequate synthesis units in
extremely large speech corpora. Our aim is to develop a concatenative speech
synthesis system with high performance (both speech quality and throughput) for
various practical applications. Utilizing very large speech corpora allows more
natural sounding synthesized speech to be created; the downside is an increase
in the time taken to locate the synthesis units needed. The key to overcoming
this problem is introducing state-of-the art database retrieval technologies.
The first selection step, based on simple hash search, tabulates all synthesis
unit candidates. The second step selects N best candidates using nearest
neighbor search, a typical database retrieval technique. Finally, the best
sequence of synthesis units is determined by Viterbi search. A runtime
measurement test and subjective experiment are carried out. Their results
confirm that the proposed approach reduces the runtime by about 40% compared to
using only hash search with no degradation in the quality of synthesized speech
for a 15 hour corpus.
[4]
Tele-Consultation System Supporting Asymmetrical Communications Between
Customers and Expert Staff in Distributed Environment
Organizational and Social Issues
/
Tanaka, T.
/
Mizuno, H.
/
Tsuji, H.
/
Kojima, H.
Proceedings of the Seventh International Conference on Human-Computer
Interaction
1997-08-24
v.1
p.27-30
© Copyright 1997 Elsevier Science
[5]
EDITED BOOK
Groupware and Authoring
/
Rada, Roy
1996
p.369
Academic Press
1. Introduction
2. A Review of Collaborative Authoring Tools
+ Michailidis, Antonios
+ Rada, Roy
3. Collaborative Authoring Dynamics
+ Chen, Chaomei
+ Rada, Roy
4. A Portrait of the Author as an Interacting Group
+ Oravec, Jo Ann
5. Coordination and Reuse
+ Rada, Roy
6. The Effectiveness of Simple Shared Electronic Workspaces
+ Olson, Gary M.
+ Olson, Judith S.
7. Computer-mediated Communication for Intellectual Teamwork: An Experiment in Group Writing
+ Galegher, Jolene
+ Kraut, Robert E.
8. Learning to Write Together
+ Posner, Ilona
+ Mitchell, Alex
+ Baecker, Ronald
9. Flexible Diff-ing in a Collaborative Writing System
+ Neuwirth, Christine M.
+ Chandhok, Ravinder
+ Kaufer, David S.
+ Erion, Paul
+ Morris, James
+ Miller, Dale
10. Collaborative Writing with Synchronous and Asynchronous Support Environments
+ Sasse, Martina Angela
+ Handley, Mark James
11. Using Multimedia to Support Cooperative Editing
+ Santos, A.
+ Tritsch, B.
12. SEPIA: A Cooperative Hypermedia Authoring Environment
+ Streitz, Norbert
+ Haake, Jorg
+ Hannemann, Jorg
+ Lemke, Andreas
+ Schuler, Wolfgang
+ Schutt, Helge
+ Thuring, Manfred
13. Structured and Distributed Cooperative Editing in a Large Scale Network
+ Decouchant, Dominique
+ Quint, Vincent
+ Salcedo, Manuel Romero
14. A Three-Level Binding for Collaborative Editing Semantics
+ Stotts, David
+ Dewan, Prasun
+ Munson, Jonathan
+ Navon, Jaime
15. SAGE: A High Structure System for Helping Teams Find Wisdom (within themselves)
+ Capron, Michael
+ Desimone, Jacqueline
+ Lacomis-Cote, Karen
16. Multimedia and Multi-party Desktop Conference System: MERMAID as Groupware Platform
+ Sakata, Shiro
+ Maeno, Kazutoshi
+ Fukuoka, Hideyuki
+ Abe, Toyoko
+ Mizuno, Hiromi
[6]
Two Learning Schemes in Information Retrieval
Quantitative Models (1)
/
Yu, Clement T.
/
Mizuno, Hirotaka
Proceedings of the Eleventh Annual International ACM SIGIR Conference on
Research and Development in Information Retrieval
1988-06-13
p.201-218
© Copyright 1988 Association for Computing Machinery
Summary: Two methods are given to improve weighting schemes by using relevance
information of a set of queries. The first method is to estimate parameter
values of two independence models in information retrieval -- the binary
independence model and the non-binary independence model. The parameters
estimated here are used to calculate optimal weights for terms in a different
set of queries. Performance of this estimation is compared to the inverse
document frequency method, the cosine measure, and the statistical similarity
measure. The second method is to learn optimal weights of the non-binary
independence model adaptively by a learning formula. Experiments are performed
on three different document collections CISI, MEDLARS, and CRN4NUL for both
methods, and results are reported. Both methods show improvements compared to
the existing weighting schemes. Experimental results show that the second
method gives slightly better performance than the first one, and has simpler
implementation.