Presentation 2002/2/28
Situation Recognition considering the Temporal Granularity
Hiroki SUZUKI, Kiyotaka OTSUJI, Toshiaki SUGIMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The authors propose an approach to the categorization of user situations that utilizes temporal granularity. Temporal granularity represents, in this paper, a measure for quantifying the time scale over which an object is observed. Increasing the temporal granularity means that the object is observed over shorter periods. User situations and applications have their own inherent temporal granularity and for an application to suit a situation its it granularity must match that of the situation. We collect the user's behavior with sensors and recognize the string of situations by assessing the data with different levels of granularity. In addition, we introduce a method of correcting recognition mistakes by using the correlation between situations with different granularity classes. This will allow many services to offer better user support in different situations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) situation recognition / context-aware / temporal granurarity / wearable sensors / correction with different granurarity classes
Paper # HCS2001-53
Date of Issue

Conference Information
Committee HCS
Conference Date 2002/2/28(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 Human Communication Science (HCS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Situation Recognition considering the Temporal Granularity
Sub Title (in English)
Keyword(1) situation recognition
Keyword(2) context-aware
Keyword(3) temporal granurarity
Keyword(4) wearable sensors
Keyword(5) correction with different granurarity classes
1st Author's Name Hiroki SUZUKI
1st Author's Affiliation Multimedia Labs., NTT DoCoMo, Inc.()
2nd Author's Name Kiyotaka OTSUJI
2nd Author's Affiliation Multimedia Labs., NTT DoCoMo, Inc.
3rd Author's Name Toshiaki SUGIMURA
3rd Author's Affiliation Multimedia Labs., NTT DoCoMo, Inc.
Date 2002/2/28
Paper # HCS2001-53
Volume (vol) vol.101
Number (no) 693
Page pp.pp.-
#Pages 8
Date of Issue