Presentation	2011/7/7 ALATA : An Active-Learning-based Annotation Tool for Activity Recognition Systems KIYOHIKO YOSHISAKU, REN OHMURA,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Recently, automatic activity log taking is realized by activity recognition techniques with body area sensor networks, and there are some studies to improve working style by looking back on the logs. In activity recognition, supervised-learning method is generally used. However, collecting of labeled data is an obstacle for the system to be practical due to the load. Therefore, we propose ALATA, a annotation tool based on active learning approach to reduce the labeling effort. The ALATA provide an environment where huge amount of annotation data are easily obtained and the labeled data can be continuously collected by linking confirming task and annotating task seamlessly. We conducted an experiment to evaluate the usefulness of the ALATA. The experiment showed that ALATA can reduce the time of labeling.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)
Paper #
Date of Issue

Conference Information
Committee	USN
Conference Date	2011/7/7(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)	ALATA : An Active-Learning-based Annotation Tool for Activity Recognition Systems
Sub Title (in English)
Keyword(1)
1st Author's Name	KIYOHIKO YOSHISAKU
1st Author's Affiliation	Toyohashi University of Technology()
2nd Author's Name	REN OHMURA
2nd Author's Affiliation	Toyohashi University of Technology
Date	2011/7/7
Paper #
Volume (vol)	vol.111
Number (no)	134
Page	pp.pp.-
#Pages	8
Date of Issue