Visualization of Features in Multivariate Gait Data: Use of a Deep Learning for the Visualization of Body Parts and Their Timing During Gait Training

Yusuke Osawa; Keiichi Watanuki; Kazunori Kaede; Keiichi Muramatsu

doi:10.1007/978-3-030-51194-4_132

Visualization of Features in Multivariate Gait Data: Use of a Deep Learning for the Visualization of Body Parts and Their Timing During Gait Training

Yusuke Osawa^*, Keiichi Watanuki, Kazunori Kaede, Keiichi Muramatsu

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

In this study, we aimed to examine the usefulness of gait classification and feature visualization based on multivariate data for the development of a gait feedback training system capable of considering the physical differences among the trainees. The multivariate data considered in this study were the joint angles and the ground reaction forces. In addition, all multivariate gait data were labeled as gait “rarely associated with stumbling” or “frequently associated with stumbling”. A convolutional neural network was used to learn the gait features. Furthermore, the feature parts of the multivariate gait data used for classification were visualized on a heat map created using Grad-CAM. As the results indicate, a heatmap is able to show the feature parts of a gait frequently associated with stumbling, through which the trainee can adjust their gait.

Original language	English
Title of host publication	Advances in Industrial Design - Proceedings of the AHFE 2020 Virtual Conferences on Design for Inclusion, Affective and Pleasurable Design, Interdisciplinary Practice in Industrial Design, Kansei Engineering, and Human Factors for Apparel and Textile Engineering
Editors	Giuseppe Di Bucchianico, Cliff Sungsoo Shin, Scott Shim, Shuichi Fukuda, Gianni Montagna, Cristina Carvalho
Publisher	Springer
Pages	1007-1013
Number of pages	7
ISBN (Print)	9783030511937
DOIs	https://doi.org/10.1007/978-3-030-51194-4_132
Publication status	Published - 2020
Externally published	Yes
Event	AHFE Virtual Conference on Design for Inclusion, the Virtual Conference on Interdisciplinary Practice in Industrial Design, the Virtual Conference on Affective and Pleasurable Design, the Virtual Conference on Kansei Engineering, and the Virtual Conference on Human Factors for Apparel and Textile Engineering, 2020 - San Diego, United States Duration: 2020 Jul 16 → 2020 Jul 20

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	1202 AISC
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	AHFE Virtual Conference on Design for Inclusion, the Virtual Conference on Interdisciplinary Practice in Industrial Design, the Virtual Conference on Affective and Pleasurable Design, the Virtual Conference on Kansei Engineering, and the Virtual Conference on Human Factors for Apparel and Textile Engineering, 2020
Country/Territory	United States
City	San Diego
Period	20/7/16 → 20/7/20

Keywords

Gait training
Healthcare
Motion analysis

ASJC Scopus subject areas

Control and Systems Engineering
Computer Science(all)

Access to Document

10.1007/978-3-030-51194-4_132

Cite this

Osawa, Y., Watanuki, K., Kaede, K., & Muramatsu, K. (2020). Visualization of Features in Multivariate Gait Data: Use of a Deep Learning for the Visualization of Body Parts and Their Timing During Gait Training. In G. Di Bucchianico, C. S. Shin, S. Shim, S. Fukuda, G. Montagna, & C. Carvalho (Eds.), Advances in Industrial Design - Proceedings of the AHFE 2020 Virtual Conferences on Design for Inclusion, Affective and Pleasurable Design, Interdisciplinary Practice in Industrial Design, Kansei Engineering, and Human Factors for Apparel and Textile Engineering (pp. 1007-1013). (Advances in Intelligent Systems and Computing; Vol. 1202 AISC). Springer. https://doi.org/10.1007/978-3-030-51194-4_132

Visualization of Features in Multivariate Gait Data : Use of a Deep Learning for the Visualization of Body Parts and Their Timing During Gait Training. / Osawa, Yusuke; Watanuki, Keiichi; Kaede, Kazunori et al.

Advances in Industrial Design - Proceedings of the AHFE 2020 Virtual Conferences on Design for Inclusion, Affective and Pleasurable Design, Interdisciplinary Practice in Industrial Design, Kansei Engineering, and Human Factors for Apparel and Textile Engineering. ed. / Giuseppe Di Bucchianico; Cliff Sungsoo Shin; Scott Shim; Shuichi Fukuda; Gianni Montagna; Cristina Carvalho. Springer, 2020. p. 1007-1013 (Advances in Intelligent Systems and Computing; Vol. 1202 AISC).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Osawa, Y, Watanuki, K, Kaede, K & Muramatsu, K 2020, Visualization of Features in Multivariate Gait Data: Use of a Deep Learning for the Visualization of Body Parts and Their Timing During Gait Training. in G Di Bucchianico, CS Shin, S Shim, S Fukuda, G Montagna & C Carvalho (eds), Advances in Industrial Design - Proceedings of the AHFE 2020 Virtual Conferences on Design for Inclusion, Affective and Pleasurable Design, Interdisciplinary Practice in Industrial Design, Kansei Engineering, and Human Factors for Apparel and Textile Engineering. Advances in Intelligent Systems and Computing, vol. 1202 AISC, Springer, pp. 1007-1013, AHFE Virtual Conference on Design for Inclusion, the Virtual Conference on Interdisciplinary Practice in Industrial Design, the Virtual Conference on Affective and Pleasurable Design, the Virtual Conference on Kansei Engineering, and the Virtual Conference on Human Factors for Apparel and Textile Engineering, 2020, San Diego, United States, 20/7/16. https://doi.org/10.1007/978-3-030-51194-4_132

Osawa Y, Watanuki K, Kaede K, Muramatsu K. Visualization of Features in Multivariate Gait Data: Use of a Deep Learning for the Visualization of Body Parts and Their Timing During Gait Training. In Di Bucchianico G, Shin CS, Shim S, Fukuda S, Montagna G, Carvalho C, editors, Advances in Industrial Design - Proceedings of the AHFE 2020 Virtual Conferences on Design for Inclusion, Affective and Pleasurable Design, Interdisciplinary Practice in Industrial Design, Kansei Engineering, and Human Factors for Apparel and Textile Engineering. Springer. 2020. p. 1007-1013. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-030-51194-4_132

Osawa, Yusuke ; Watanuki, Keiichi ; Kaede, Kazunori et al. / Visualization of Features in Multivariate Gait Data : Use of a Deep Learning for the Visualization of Body Parts and Their Timing During Gait Training. Advances in Industrial Design - Proceedings of the AHFE 2020 Virtual Conferences on Design for Inclusion, Affective and Pleasurable Design, Interdisciplinary Practice in Industrial Design, Kansei Engineering, and Human Factors for Apparel and Textile Engineering. editor / Giuseppe Di Bucchianico ; Cliff Sungsoo Shin ; Scott Shim ; Shuichi Fukuda ; Gianni Montagna ; Cristina Carvalho. Springer, 2020. pp. 1007-1013 (Advances in Intelligent Systems and Computing).

@inproceedings{41dd11fe40e2483f8eafbe0d27fedc68,

title = "Visualization of Features in Multivariate Gait Data: Use of a Deep Learning for the Visualization of Body Parts and Their Timing During Gait Training",

abstract = "In this study, we aimed to examine the usefulness of gait classification and feature visualization based on multivariate data for the development of a gait feedback training system capable of considering the physical differences among the trainees. The multivariate data considered in this study were the joint angles and the ground reaction forces. In addition, all multivariate gait data were labeled as gait “rarely associated with stumbling” or “frequently associated with stumbling”. A convolutional neural network was used to learn the gait features. Furthermore, the feature parts of the multivariate gait data used for classification were visualized on a heat map created using Grad-CAM. As the results indicate, a heatmap is able to show the feature parts of a gait frequently associated with stumbling, through which the trainee can adjust their gait.",

keywords = "Gait training, Healthcare, Motion analysis",

author = "Yusuke Osawa and Keiichi Watanuki and Kazunori Kaede and Keiichi Muramatsu",

note = "Publisher Copyright: {\textcopyright} 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; AHFE Virtual Conference on Design for Inclusion, the Virtual Conference on Interdisciplinary Practice in Industrial Design, the Virtual Conference on Affective and Pleasurable Design, the Virtual Conference on Kansei Engineering, and the Virtual Conference on Human Factors for Apparel and Textile Engineering, 2020 ; Conference date: 16-07-2020 Through 20-07-2020",

year = "2020",

doi = "10.1007/978-3-030-51194-4_132",

language = "English",

isbn = "9783030511937",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer",

pages = "1007--1013",

editor = "{Di Bucchianico}, Giuseppe and Shin, {Cliff Sungsoo} and Scott Shim and Shuichi Fukuda and Gianni Montagna and Cristina Carvalho",

booktitle = "Advances in Industrial Design - Proceedings of the AHFE 2020 Virtual Conferences on Design for Inclusion, Affective and Pleasurable Design, Interdisciplinary Practice in Industrial Design, Kansei Engineering, and Human Factors for Apparel and Textile Engineering",

}

TY - GEN

T1 - Visualization of Features in Multivariate Gait Data

T2 - AHFE Virtual Conference on Design for Inclusion, the Virtual Conference on Interdisciplinary Practice in Industrial Design, the Virtual Conference on Affective and Pleasurable Design, the Virtual Conference on Kansei Engineering, and the Virtual Conference on Human Factors for Apparel and Textile Engineering, 2020

AU - Osawa, Yusuke

AU - Watanuki, Keiichi

AU - Kaede, Kazunori

AU - Muramatsu, Keiichi

N1 - Publisher Copyright: © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2020

Y1 - 2020

N2 - In this study, we aimed to examine the usefulness of gait classification and feature visualization based on multivariate data for the development of a gait feedback training system capable of considering the physical differences among the trainees. The multivariate data considered in this study were the joint angles and the ground reaction forces. In addition, all multivariate gait data were labeled as gait “rarely associated with stumbling” or “frequently associated with stumbling”. A convolutional neural network was used to learn the gait features. Furthermore, the feature parts of the multivariate gait data used for classification were visualized on a heat map created using Grad-CAM. As the results indicate, a heatmap is able to show the feature parts of a gait frequently associated with stumbling, through which the trainee can adjust their gait.

AB - In this study, we aimed to examine the usefulness of gait classification and feature visualization based on multivariate data for the development of a gait feedback training system capable of considering the physical differences among the trainees. The multivariate data considered in this study were the joint angles and the ground reaction forces. In addition, all multivariate gait data were labeled as gait “rarely associated with stumbling” or “frequently associated with stumbling”. A convolutional neural network was used to learn the gait features. Furthermore, the feature parts of the multivariate gait data used for classification were visualized on a heat map created using Grad-CAM. As the results indicate, a heatmap is able to show the feature parts of a gait frequently associated with stumbling, through which the trainee can adjust their gait.

KW - Gait training

KW - Healthcare

KW - Motion analysis

UR - http://www.scopus.com/inward/record.url?scp=85088513064&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85088513064&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-51194-4_132

DO - 10.1007/978-3-030-51194-4_132

M3 - Conference contribution

AN - SCOPUS:85088513064

SN - 9783030511937

T3 - Advances in Intelligent Systems and Computing

SP - 1007

EP - 1013

BT - Advances in Industrial Design - Proceedings of the AHFE 2020 Virtual Conferences on Design for Inclusion, Affective and Pleasurable Design, Interdisciplinary Practice in Industrial Design, Kansei Engineering, and Human Factors for Apparel and Textile Engineering

A2 - Di Bucchianico, Giuseppe

A2 - Shin, Cliff Sungsoo

A2 - Shim, Scott

A2 - Fukuda, Shuichi

A2 - Montagna, Gianni

A2 - Carvalho, Cristina

PB - Springer

Y2 - 16 July 2020 through 20 July 2020

ER -

Visualization of Features in Multivariate Gait Data: Use of a Deep Learning for the Visualization of Body Parts and Their Timing During Gait Training

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this