Multilayer perceptron neural network classification for human vertical ground reaction forces

Kwang Leng Goh; King Hann Lim; Alpha Agape Gopalai; Yu Zheng Chong

doi:10.1109/IECBES.2014.7047559

Multilayer perceptron neural network classification for human vertical ground reaction forces

Kwang Leng Goh, King Hann Lim, Alpha Agape Gopalai, Yu Zheng Chong

Malaysia School of Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

10 Citations (Scopus)

Abstract

In this paper, human motion classification using multilayered neural network is proposed to classify motion signal based on vertical ground resultant force (VGRF). VRGF readings were acquired using an instrumented treadmill. The work presented in this paper seeks to classify six activities i.e. standing to walking, walking, walking to jogging, jogging, jogging to running and running, based on the measured VGRF. The data set involved 229 healthy Asians aged between 20 and 24, yielding a total of 740 activity classes. All activities varied as a result of subjects desired speed. However, it was observed that the VGRF of the last five strides reaction forces was sufficient to achieve 83 classification rate for the training set and 73 for testing set. The influence of number of hidden neurons was also analyzed to obtain optimal classification performance.

Original language	English
Title of host publication	Proceedings of the 2014 IEEE International Conference on Biomedical Engineering and Sciences
Editors	Fatimah Ibrahim
Place of Publication	New Jersey USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	536 - 540
Number of pages	5
ISBN (Print)	9781479940844
DOIs	https://doi.org/10.1109/IECBES.2014.7047559
Publication status	Published - 2015
Event	IEEE-EMBS International Conference on Biomedical Engineering and Sciences (IECBES) 2014 - University of Malaya, Kuala Lumpur, Malaysia Duration: 8 Dec 2014 → 10 Dec 2014 https://ieeexplore.ieee.org/xpl/conhome/7033073/proceeding (Proceedings)

Conference

Conference	IEEE-EMBS International Conference on Biomedical Engineering and Sciences (IECBES) 2014
Abbreviated title	IECBES 2014
Country/Territory	Malaysia
City	Kuala Lumpur
Period	8/12/14 → 10/12/14
Internet address	https://ieeexplore.ieee.org/xpl/conhome/7033073/proceeding (Proceedings)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/IECBES.2014.7047559

Cite this

Goh, K. L., Lim, K. H., Agape Gopalai, A., & Chong, Y. Z. (2015). Multilayer perceptron neural network classification for human vertical ground reaction forces. In F. Ibrahim (Ed.), Proceedings of the 2014 IEEE International Conference on Biomedical Engineering and Sciences (pp. 536 - 540). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IECBES.2014.7047559

Goh, Kwang Leng ; Lim, King Hann ; Agape Gopalai, Alpha et al. / Multilayer perceptron neural network classification for human vertical ground reaction forces. Proceedings of the 2014 IEEE International Conference on Biomedical Engineering and Sciences. editor / Fatimah Ibrahim. New Jersey USA : IEEE, Institute of Electrical and Electronics Engineers, 2015. pp. 536 - 540

@inproceedings{6f00196d06aa4ec2b01980c37e8fffc6,

title = "Multilayer perceptron neural network classification for human vertical ground reaction forces",

abstract = "In this paper, human motion classification using multilayered neural network is proposed to classify motion signal based on vertical ground resultant force (VGRF). VRGF readings were acquired using an instrumented treadmill. The work presented in this paper seeks to classify six activities i.e. standing to walking, walking, walking to jogging, jogging, jogging to running and running, based on the measured VGRF. The data set involved 229 healthy Asians aged between 20 and 24, yielding a total of 740 activity classes. All activities varied as a result of subjects desired speed. However, it was observed that the VGRF of the last five strides reaction forces was sufficient to achieve 83 classification rate for the training set and 73 for testing set. The influence of number of hidden neurons was also analyzed to obtain optimal classification performance.",

author = "Goh, {Kwang Leng} and Lim, {King Hann} and {Agape Gopalai}, Alpha and Chong, {Yu Zheng}",

year = "2015",

doi = "10.1109/IECBES.2014.7047559",

language = "English",

isbn = "9781479940844",

pages = "536 -- 540",

editor = "Fatimah Ibrahim",

booktitle = "Proceedings of the 2014 IEEE International Conference on Biomedical Engineering and Sciences",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "IEEE-EMBS International Conference on Biomedical Engineering and Sciences (IECBES) 2014, IECBES 2014 ; Conference date: 08-12-2014 Through 10-12-2014",

url = "https://ieeexplore.ieee.org/xpl/conhome/7033073/proceeding",

}

Goh, KL, Lim, KH, Agape Gopalai, A & Chong, YZ 2015, Multilayer perceptron neural network classification for human vertical ground reaction forces. in F Ibrahim (ed.), Proceedings of the 2014 IEEE International Conference on Biomedical Engineering and Sciences. IEEE, Institute of Electrical and Electronics Engineers, New Jersey USA, pp. 536 - 540, IEEE-EMBS International Conference on Biomedical Engineering and Sciences (IECBES) 2014, Kuala Lumpur, Malaysia, 8/12/14. https://doi.org/10.1109/IECBES.2014.7047559

Multilayer perceptron neural network classification for human vertical ground reaction forces. / Goh, Kwang Leng; Lim, King Hann; Agape Gopalai, Alpha et al.
Proceedings of the 2014 IEEE International Conference on Biomedical Engineering and Sciences. ed. / Fatimah Ibrahim. New Jersey USA: IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 536 - 540.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Multilayer perceptron neural network classification for human vertical ground reaction forces

AU - Goh, Kwang Leng

AU - Lim, King Hann

AU - Agape Gopalai, Alpha

AU - Chong, Yu Zheng

PY - 2015

Y1 - 2015

N2 - In this paper, human motion classification using multilayered neural network is proposed to classify motion signal based on vertical ground resultant force (VGRF). VRGF readings were acquired using an instrumented treadmill. The work presented in this paper seeks to classify six activities i.e. standing to walking, walking, walking to jogging, jogging, jogging to running and running, based on the measured VGRF. The data set involved 229 healthy Asians aged between 20 and 24, yielding a total of 740 activity classes. All activities varied as a result of subjects desired speed. However, it was observed that the VGRF of the last five strides reaction forces was sufficient to achieve 83 classification rate for the training set and 73 for testing set. The influence of number of hidden neurons was also analyzed to obtain optimal classification performance.

AB - In this paper, human motion classification using multilayered neural network is proposed to classify motion signal based on vertical ground resultant force (VGRF). VRGF readings were acquired using an instrumented treadmill. The work presented in this paper seeks to classify six activities i.e. standing to walking, walking, walking to jogging, jogging, jogging to running and running, based on the measured VGRF. The data set involved 229 healthy Asians aged between 20 and 24, yielding a total of 740 activity classes. All activities varied as a result of subjects desired speed. However, it was observed that the VGRF of the last five strides reaction forces was sufficient to achieve 83 classification rate for the training set and 73 for testing set. The influence of number of hidden neurons was also analyzed to obtain optimal classification performance.

U2 - 10.1109/IECBES.2014.7047559

DO - 10.1109/IECBES.2014.7047559

M3 - Conference Paper

SN - 9781479940844

SP - 536

EP - 540

BT - Proceedings of the 2014 IEEE International Conference on Biomedical Engineering and Sciences

A2 - Ibrahim, Fatimah

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - New Jersey USA

T2 - IEEE-EMBS International Conference on Biomedical Engineering and Sciences (IECBES) 2014

Y2 - 8 December 2014 through 10 December 2014

ER -

Goh KL, Lim KH, Agape Gopalai A, Chong YZ. Multilayer perceptron neural network classification for human vertical ground reaction forces. In Ibrahim F, editor, Proceedings of the 2014 IEEE International Conference on Biomedical Engineering and Sciences. New Jersey USA: IEEE, Institute of Electrical and Electronics Engineers. 2015. p. 536 - 540 doi: 10.1109/IECBES.2014.7047559