Exercise classification using CNN with image frames produced from time-series motion data

Authors
Hajime Itoh, Naohiko Hanajima, Yohei Muraoka, Makoto Ohata, Masato Mizukami, Yoshinori Fujihira
Corresponding Author
Hajime Itoh
Available Online 1 June 2017.
DOI
https://doi.org/10.2991/jrnal.2017.4.1.5
Keywords
CNN, Gray scale image, Exercises classification, Time-series data.
Abstract
Exercise support systems for the elderly have been developed and some were equipped with a motion sensor to evaluate their exercise motion. Normally, it provides three-dimensional time-series data of over 20 joints. In this study, we propose to apply Convolutional Neural Network (CNN) methodology to the motion evaluation. The method converts the motion data of one exercise interval into one gray scale image. From simulation results, the CNN was possible to classify the images into specified motions.

Copyright
© 2013, the Authors. Published by ALife Robotics Corp. Ltd.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)