Deep learning model to recognize the different progression condition patterns of manual wheelchair users for prevention of shoulder pain

Jen Yung Tsai, Yih-Kuen Jan, Ben Yi Liau, Chien Liang Chen, Peng Je Chen, Chih Yang Lin, Yi Chun Liu, Chi Wen Lung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Wheelchair user will use different propulsion strategies to control in a variety of progression conditions that may induce the shoulder pain. The hypothesis of this study is that wheelchair user in different progression conditions has different ways to control the wheelchair. The purpose of this study is to use the accelerometer to recognize the movement of the wheelchair. It can be easily used to define the different progression condition in order to know the cause of the inducement of shoulder pain. The researchers collected acceleration data during the wheelchair progression in rough and smooth distinguishing surfaces: (1) outdoor grassland and; (2) indoor flatland. Researchers transformed the acceleration data into spectrogram files and training convolutional neural network (CNN) deep learning model to accurately recognize and predict wheelchair user’s wheelchair location. As the results, the wheelchair user’s medial-lateral direction of acceleration is expected to present more significant features than the front-back motion when being related to progression condition. At the same time, the vertical direction of acceleration also reflected the wheelchair vibration during different surface of progression condition.

Original languageEnglish (US)
Title of host publicationAdvances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2019 International Conference on Physical Ergonomics and Human Factors
EditorsRavindra S. Goonetilleke, Waldemar Karwowski
PublisherSpringer-Verlag
Pages3-13
Number of pages11
ISBN (Print)9783030201418
DOIs
StatePublished - Jan 1 2020
EventAHFE International Conference on Physical Ergonomics and Human Factors, 2019 - Washington D.C., United States
Duration: Jul 24 2019Jul 28 2019

Publication series

NameAdvances in Intelligent Systems and Computing
Volume967
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

ConferenceAHFE International Conference on Physical Ergonomics and Human Factors, 2019
CountryUnited States
CityWashington D.C.
Period7/24/197/28/19

Fingerprint

Wheelchairs
Deep learning
Accelerometers
Propulsion
Neural networks

Keywords

  • Acceleration
  • Convolutional neural network
  • Propulsion strategy
  • Spectrogram

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Tsai, J. Y., Jan, Y-K., Liau, B. Y., Chen, C. L., Chen, P. J., Lin, C. Y., ... Lung, C. W. (2020). Deep learning model to recognize the different progression condition patterns of manual wheelchair users for prevention of shoulder pain. In R. S. Goonetilleke, & W. Karwowski (Eds.), Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2019 International Conference on Physical Ergonomics and Human Factors (pp. 3-13). (Advances in Intelligent Systems and Computing; Vol. 967). Springer-Verlag. https://doi.org/10.1007/978-3-030-20142-5_1

Deep learning model to recognize the different progression condition patterns of manual wheelchair users for prevention of shoulder pain. / Tsai, Jen Yung; Jan, Yih-Kuen; Liau, Ben Yi; Chen, Chien Liang; Chen, Peng Je; Lin, Chih Yang; Liu, Yi Chun; Lung, Chi Wen.

Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2019 International Conference on Physical Ergonomics and Human Factors. ed. / Ravindra S. Goonetilleke; Waldemar Karwowski. Springer-Verlag, 2020. p. 3-13 (Advances in Intelligent Systems and Computing; Vol. 967).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tsai, JY, Jan, Y-K, Liau, BY, Chen, CL, Chen, PJ, Lin, CY, Liu, YC & Lung, CW 2020, Deep learning model to recognize the different progression condition patterns of manual wheelchair users for prevention of shoulder pain. in RS Goonetilleke & W Karwowski (eds), Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2019 International Conference on Physical Ergonomics and Human Factors. Advances in Intelligent Systems and Computing, vol. 967, Springer-Verlag, pp. 3-13, AHFE International Conference on Physical Ergonomics and Human Factors, 2019, Washington D.C., United States, 7/24/19. https://doi.org/10.1007/978-3-030-20142-5_1
Tsai JY, Jan Y-K, Liau BY, Chen CL, Chen PJ, Lin CY et al. Deep learning model to recognize the different progression condition patterns of manual wheelchair users for prevention of shoulder pain. In Goonetilleke RS, Karwowski W, editors, Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2019 International Conference on Physical Ergonomics and Human Factors. Springer-Verlag. 2020. p. 3-13. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-030-20142-5_1
Tsai, Jen Yung ; Jan, Yih-Kuen ; Liau, Ben Yi ; Chen, Chien Liang ; Chen, Peng Je ; Lin, Chih Yang ; Liu, Yi Chun ; Lung, Chi Wen. / Deep learning model to recognize the different progression condition patterns of manual wheelchair users for prevention of shoulder pain. Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2019 International Conference on Physical Ergonomics and Human Factors. editor / Ravindra S. Goonetilleke ; Waldemar Karwowski. Springer-Verlag, 2020. pp. 3-13 (Advances in Intelligent Systems and Computing).
@inproceedings{b74e5dc652e54cd890bdb288a8378570,
title = "Deep learning model to recognize the different progression condition patterns of manual wheelchair users for prevention of shoulder pain",
abstract = "Wheelchair user will use different propulsion strategies to control in a variety of progression conditions that may induce the shoulder pain. The hypothesis of this study is that wheelchair user in different progression conditions has different ways to control the wheelchair. The purpose of this study is to use the accelerometer to recognize the movement of the wheelchair. It can be easily used to define the different progression condition in order to know the cause of the inducement of shoulder pain. The researchers collected acceleration data during the wheelchair progression in rough and smooth distinguishing surfaces: (1) outdoor grassland and; (2) indoor flatland. Researchers transformed the acceleration data into spectrogram files and training convolutional neural network (CNN) deep learning model to accurately recognize and predict wheelchair user’s wheelchair location. As the results, the wheelchair user’s medial-lateral direction of acceleration is expected to present more significant features than the front-back motion when being related to progression condition. At the same time, the vertical direction of acceleration also reflected the wheelchair vibration during different surface of progression condition.",
keywords = "Acceleration, Convolutional neural network, Propulsion strategy, Spectrogram",
author = "Tsai, {Jen Yung} and Yih-Kuen Jan and Liau, {Ben Yi} and Chen, {Chien Liang} and Chen, {Peng Je} and Lin, {Chih Yang} and Liu, {Yi Chun} and Lung, {Chi Wen}",
year = "2020",
month = "1",
day = "1",
doi = "10.1007/978-3-030-20142-5_1",
language = "English (US)",
isbn = "9783030201418",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer-Verlag",
pages = "3--13",
editor = "Goonetilleke, {Ravindra S.} and Waldemar Karwowski",
booktitle = "Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2019 International Conference on Physical Ergonomics and Human Factors",

}

TY - GEN

T1 - Deep learning model to recognize the different progression condition patterns of manual wheelchair users for prevention of shoulder pain

AU - Tsai, Jen Yung

AU - Jan, Yih-Kuen

AU - Liau, Ben Yi

AU - Chen, Chien Liang

AU - Chen, Peng Je

AU - Lin, Chih Yang

AU - Liu, Yi Chun

AU - Lung, Chi Wen

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Wheelchair user will use different propulsion strategies to control in a variety of progression conditions that may induce the shoulder pain. The hypothesis of this study is that wheelchair user in different progression conditions has different ways to control the wheelchair. The purpose of this study is to use the accelerometer to recognize the movement of the wheelchair. It can be easily used to define the different progression condition in order to know the cause of the inducement of shoulder pain. The researchers collected acceleration data during the wheelchair progression in rough and smooth distinguishing surfaces: (1) outdoor grassland and; (2) indoor flatland. Researchers transformed the acceleration data into spectrogram files and training convolutional neural network (CNN) deep learning model to accurately recognize and predict wheelchair user’s wheelchair location. As the results, the wheelchair user’s medial-lateral direction of acceleration is expected to present more significant features than the front-back motion when being related to progression condition. At the same time, the vertical direction of acceleration also reflected the wheelchair vibration during different surface of progression condition.

AB - Wheelchair user will use different propulsion strategies to control in a variety of progression conditions that may induce the shoulder pain. The hypothesis of this study is that wheelchair user in different progression conditions has different ways to control the wheelchair. The purpose of this study is to use the accelerometer to recognize the movement of the wheelchair. It can be easily used to define the different progression condition in order to know the cause of the inducement of shoulder pain. The researchers collected acceleration data during the wheelchair progression in rough and smooth distinguishing surfaces: (1) outdoor grassland and; (2) indoor flatland. Researchers transformed the acceleration data into spectrogram files and training convolutional neural network (CNN) deep learning model to accurately recognize and predict wheelchair user’s wheelchair location. As the results, the wheelchair user’s medial-lateral direction of acceleration is expected to present more significant features than the front-back motion when being related to progression condition. At the same time, the vertical direction of acceleration also reflected the wheelchair vibration during different surface of progression condition.

KW - Acceleration

KW - Convolutional neural network

KW - Propulsion strategy

KW - Spectrogram

UR - http://www.scopus.com/inward/record.url?scp=85067247864&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067247864&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-20142-5_1

DO - 10.1007/978-3-030-20142-5_1

M3 - Conference contribution

AN - SCOPUS:85067247864

SN - 9783030201418

T3 - Advances in Intelligent Systems and Computing

SP - 3

EP - 13

BT - Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2019 International Conference on Physical Ergonomics and Human Factors

A2 - Goonetilleke, Ravindra S.

A2 - Karwowski, Waldemar

PB - Springer-Verlag

ER -