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

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

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...

Full description

Bibliographic Details
Main Authors: Hajime Itoh, Naohiko Hanajima, Yohei Muraoka, Makoto Ohata, Masato Mizukami, Yoshinori Fujihira
Format: Article
Language:English
Published: Atlantis Press 2017-05-01
Series:Journal of Robotics, Networking and Artificial Life (JRNAL)
Subjects:
CNN
Gray scale image
Exercises classification
Time-series data.
Online Access:https://www.atlantis-press.com/article/25878336.pdf
id doaj-4405145829c24616ade071bd64992423
record_format Article
spelling doaj-4405145829c24616ade071bd649924232020-11-24T21:55:50ZengAtlantis PressJournal of Robotics, Networking and Artificial Life (JRNAL)2352-63862017-05-014110.2991/jrnal.2017.4.1.5Exercise classification using CNN with image frames produced from time-series motion dataHajime ItohNaohiko HanajimaYohei MuraokaMakoto OhataMasato MizukamiYoshinori FujihiraExercise 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.https://www.atlantis-press.com/article/25878336.pdfCNNGray scale imageExercises classificationTime-series data.
collection DOAJ
language English
format Article
sources DOAJ
author Hajime Itoh
Naohiko Hanajima
Yohei Muraoka
Makoto Ohata
Masato Mizukami
Yoshinori Fujihira
spellingShingle Hajime Itoh
Naohiko Hanajima
Yohei Muraoka
Makoto Ohata
Masato Mizukami
Yoshinori Fujihira
Exercise classification using CNN with image frames produced from time-series motion data
Journal of Robotics, Networking and Artificial Life (JRNAL)
CNN
Gray scale image
Exercises classification
Time-series data.
author_facet Hajime Itoh
Naohiko Hanajima
Yohei Muraoka
Makoto Ohata
Masato Mizukami
Yoshinori Fujihira
author_sort Hajime Itoh
title Exercise classification using CNN with image frames produced from time-series motion data
title_short Exercise classification using CNN with image frames produced from time-series motion data
title_full Exercise classification using CNN with image frames produced from time-series motion data
title_fullStr Exercise classification using CNN with image frames produced from time-series motion data
title_full_unstemmed Exercise classification using CNN with image frames produced from time-series motion data
title_sort exercise classification using cnn with image frames produced from time-series motion data
publisher Atlantis Press
series Journal of Robotics, Networking and Artificial Life (JRNAL)
issn 2352-6386
publishDate 2017-05-01
description 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.
topic CNN
Gray scale image
Exercises classification
Time-series data.
url https://www.atlantis-press.com/article/25878336.pdf
work_keys_str_mv AT hajimeitoh exerciseclassificationusingcnnwithimageframesproducedfromtimeseriesmotiondata
AT naohikohanajima exerciseclassificationusingcnnwithimageframesproducedfromtimeseriesmotiondata
AT yoheimuraoka exerciseclassificationusingcnnwithimageframesproducedfromtimeseriesmotiondata
AT makotoohata exerciseclassificationusingcnnwithimageframesproducedfromtimeseriesmotiondata
AT masatomizukami exerciseclassificationusingcnnwithimageframesproducedfromtimeseriesmotiondata
AT yoshinorifujihira exerciseclassificationusingcnnwithimageframesproducedfromtimeseriesmotiondata
_version_ 1725861081630375936

Similar Items