Presentation 2014-03-06
An Estimation Method and Its Evaluation of Human Action using Multiple Sensors in Portable Devices and Knowledge Processing
Ayaka SUZUKI, Toru ABE, Takuo SUGANUMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Existing estimation techniques of human action have some problems such as high installation costs of sensors and restriction of user's daily life. To solve these problems, we propose an estimation method of human action by using a portable device such as a smartphone. Our proposed method estimates basic action based on various kinds of sensor data collected by multiple sensors in the portable device. The proposed method utilizes knowledge base including action time and location to enhance estimation accuracy by combining the knowledge processing and sensor data. In this paper, we explain the detailed design of our estimation method and its implementation. We also carry out its experimentation to confirm effectiveness of our proposed estimation method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Portable device / Sensors / Estimation of human action / Machine learning / Knowledge processing
Paper # IN2013-158
Date of Issue

Conference Information
Committee IN
Conference Date 2014/2/27(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Information Networks (IN)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An Estimation Method and Its Evaluation of Human Action using Multiple Sensors in Portable Devices and Knowledge Processing
Sub Title (in English)
Keyword(1) Portable device
Keyword(2) Sensors
Keyword(3) Estimation of human action
Keyword(4) Machine learning
Keyword(5) Knowledge processing
1st Author's Name Ayaka SUZUKI
1st Author's Affiliation Graduate School of Information Sciences, Tohoku University()
2nd Author's Name Toru ABE
2nd Author's Affiliation Graduate School of Information Sciences, Tohoku University:Cyberscience Center, Tohoku University
3rd Author's Name Takuo SUGANUMA
3rd Author's Affiliation Graduate School of Information Sciences, Tohoku University:Cyberscience Center, Tohoku University
Date 2014-03-06
Paper # IN2013-158
Volume (vol) vol.113
Number (no) 473
Page pp.pp.-
#Pages 6
Date of Issue