Presentation 2012-01-20
Extracting Eigenpatterns from Office Workers Behavior Using Long Term Sensor Data
Yusaku SATO, Shogo OKADA, Yuki KAMIYA, Katsumi NITTA, Kazuo KUNIEDA, Keiji YAMADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposed an approach to analyze worker's activities in office. We investigated typical patterns during some office activities using dataset from a sensor network located in office. At first, data samples in office activities data are classified to three categories by using location of infrared sensors and a PC logger. Three categories are (1): desk work using PC, (2): meeting with the other people, and (3): otherwise. Time series data of office activities are converted to label sequences. Second, PCA can be done by singular value decomposition of a data matrix obtained by label sequences. Typical activity patterns are defined as eigenvectors of data matrix. We collected 23 months activity dataset from a sensor network for experiments. Experimental results show that typical activity patterns represent a character of individual activity in office.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Lifelog / Sensor Network / Behavior Analysis / Eigen Decomposition / PCA
Paper # ICM2011-37,LOIS2011-62
Date of Issue

Conference Information
Committee LOIS
Conference Date 2012/1/12(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 Life Intelligence and Office Information Systems (LOIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Extracting Eigenpatterns from Office Workers Behavior Using Long Term Sensor Data
Sub Title (in English)
Keyword(1) Lifelog
Keyword(2) Sensor Network
Keyword(3) Behavior Analysis
Keyword(4) Eigen Decomposition
Keyword(5) PCA
1st Author's Name Yusaku SATO
1st Author's Affiliation Tokyo Institute of Technology()
2nd Author's Name Shogo OKADA
2nd Author's Affiliation Tokyo Institute of Technology
3rd Author's Name Yuki KAMIYA
3rd Author's Affiliation C&C Innovation Research Lab, NEC Corporation
4th Author's Name Katsumi NITTA
4th Author's Affiliation Tokyo Institute of Technology
5th Author's Name Kazuo KUNIEDA
5th Author's Affiliation C&C Innovation Research Lab, NEC Corporation
6th Author's Name Keiji YAMADA
6th Author's Affiliation C&C Innovation Research Lab, NEC Corporation
Date 2012-01-20
Paper # ICM2011-37,LOIS2011-62
Volume (vol) vol.111
Number (no) 383
Page pp.pp.-
#Pages 6
Date of Issue