Presentation 2008-07-18
Contribution of Personalization to Activity Recognition Accuracy Using Accelerometers in Daily Life
Naoyuki HASHIDA, Ren OHMURA, Michita IMAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In activity recognition techniques with accelerometers, there has been a question that which model should be used, a user-specific model obtained from a subject or a general model obtained from unspecified many subjects. While a past research concluded that a user-specific model gives better accuracy, there is the matter of an enforced load for a subject to obtain its training data. We, thus, focused on personalization techniques and evaluated the effectiveness by some experiments with personalized general models. From these evaluations, we confirmed that the personalization techniques increase the accuracy of general model and is useful in activity recognition using accelerometers.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) daily activity recognition / accelerometer / pattern recognition / personalization
Paper # USN2008-23
Date of Issue

Conference Information
Committee USN
Conference Date 2008/7/10(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 Ubiquitous and Sensor Networks(USN)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Contribution of Personalization to Activity Recognition Accuracy Using Accelerometers in Daily Life
Sub Title (in English)
Keyword(1) daily activity recognition
Keyword(2) accelerometer
Keyword(3) pattern recognition
Keyword(4) personalization
1st Author's Name Naoyuki HASHIDA
1st Author's Affiliation Graduate School of Science and Technology, Keio University()
2nd Author's Name Ren OHMURA
2nd Author's Affiliation Faculty of Science and Technology, Keio University
3rd Author's Name Michita IMAI
3rd Author's Affiliation Faculty of Science and Technology, Keio University
Date 2008-07-18
Paper # USN2008-23
Volume (vol) vol.108
Number (no) 138
Page pp.pp.-
#Pages 6
Date of Issue