Activity recognition for children using self-organizing map

Author

Suzuki, Satoshi ; Mitsukura, Yasue ; Igarashi, Hiroshi ; Kobayashi, Harumi ; Harashima, Fumio

Author_Institution

Dept. of Robot. & Mechatron., Tokyo Denki Univ., Tokyo, Japan

fYear

2012

fDate

9-13 Sept. 2012

Firstpage

653

Lastpage

658

Abstract

Based on a new concept of Kinder-GuaRdian which aims to realize a support system for kindergarten´s staffs and parents by watching over children´s activity and their growing process, activity recognition (AR) for children is treated in this paper. In case of children, smaller amount of sensors is better since easy fitting of the sensor device to child´s body is strongly preferable. In this study, using one acceleration sensor attached to the upper arm, AR in cases of adults and children were evaluated using several orthodox classifiers and self-organizing map (SOM). Through the several types of validation, effectiveness, issues, and benefits of their methods are discussed.

Keywords

acceleration measurement; body sensor networks; pattern classification; psychology; self-organising feature maps; wearable computers; Kinder-GuaRdian; acceleration sensor; child body; children activity recognition; growing process; kindergarten; orthodox classifiers; self-organizing map; sensor device; support system; Acceleration; Accuracy; Humans; Pediatrics; Robots; Sensors; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

RO-MAN, 2012 IEEE

Conference_Location

Paris

ISSN

1944-9445

Print_ISBN

978-1-4673-4604-7

Electronic_ISBN

1944-9445

Type

conf

DOI

10.1109/ROMAN.2012.6343825

Filename

6343825