Presentation	2012/5/10 Automated Recognition of Indoor Activity based on Multi-Sensing NOBUHIKO NISHIO, HARUMITSU FUJII, TAKUYA AZUMI,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	This article proposes a method to recognize user's fine-grain activity recognition using multiple sensor and creating sampled topological map. This method turned out to require two threshold values for determining to create a new sample cluster and to update existing sample clusters. We conducted some experiments and obtained result of under 0.1% miss recognition ratio through relatively short term sensing and automated updating of topological map.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	activity recognition / sensor fusion / Wi-Fi AP positioning / accelerometer
Paper #	Vol.2012-UBI-34 No.30
Date of Issue

Conference Information
Committee	USN
Conference Date	2012/5/10(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)	Automated Recognition of Indoor Activity based on Multi-Sensing
Sub Title (in English)
Keyword(1)	activity recognition
Keyword(2)	sensor fusion
Keyword(3)	Wi-Fi AP positioning
Keyword(4)	accelerometer
1st Author's Name	NOBUHIKO NISHIO
1st Author's Affiliation	Ritsumeikan University()
2nd Author's Name	HARUMITSU FUJII
2nd Author's Affiliation	Graduate School of Ritsumeikan University
3rd Author's Name	TAKUYA AZUMI
3rd Author's Affiliation	Ritsumeikan University
Date	2012/5/10
Paper #	Vol.2012-UBI-34 No.30
Volume (vol)	vol.112
Number (no)	31
Page	pp.pp.-
#Pages	6
Date of Issue