Presentation 2008-12-18
Activity Recognition from Interactions with Objects using Dynamic Bayesian Network
Tomohito Inomata, Futoshi Naya, Noriaki Kuwahara, Fumio Hattori, Kiyoshi Kogure,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A nursing activity recognition method has been developed that is based on a nurse's interactions with the tools and materials he/she touches and uses the Dynamic Bayesian Network (DBN) framework. This is aimed to prevent the cause of medical accident and incidents beforehand. This time, we focused on recognizing the 12 activity steps in the drip injection task which is one of the most related tasks to medical accidents and incidents. Activity recognition from the interactions with objects captured by RFID was done using DBN framework, and we obtained the 96% accuracy of the recognition of the 12 activity steps in the drip injection task.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # PRMU2008-163
Date of Issue

Conference Information
Committee PRMU
Conference Date 2008/12/11(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Activity Recognition from Interactions with Objects using Dynamic Bayesian Network
Sub Title (in English)
Keyword(1)
1st Author's Name Tomohito Inomata
1st Author's Affiliation ATR Knowledge Science Laboratories:Graduate School of Science and Engineering, Ritsumeikan University()
2nd Author's Name Futoshi Naya
2nd Author's Affiliation ATR Knowledge Science Laboratories
3rd Author's Name Noriaki Kuwahara
3rd Author's Affiliation Graduate School of Science and Technology, Kyoto Institute of Technology
4th Author's Name Fumio Hattori
4th Author's Affiliation Graduate School of Science and Engineering, Ritsumeikan University
5th Author's Name Kiyoshi Kogure
5th Author's Affiliation ATR Knowledge Science Laboratories
Date 2008-12-18
Paper # PRMU2008-163
Volume (vol) vol.108
Number (no) 363
Page pp.pp.-
#Pages 6
Date of Issue