Using Deep Learning Methods to Predict Walking Intensity from Plantar Pressure Images

Hsing Chung Chen; Sunardi; Yih Kuen Jan; Ben Yi Liau; Chih Yang Lin; Jen Yung Tsai; Cheng Tsung Li; Chi Wen Lung

doi:10.1007/978-3-030-80713-9_35

Using Deep Learning Methods to Predict Walking Intensity from Plantar Pressure Images

Hsing Chung Chen
, Sunardi
, Yih Kuen Jan
, Ben Yi Liau
, Chih Yang Lin
, Jen Yung Tsai
, Cheng Tsung Li
, Chi Wen Lung

Department of Mechanical Engineering

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

5 Scopus citations

Abstract

People with diabetes are recommended to perform exercise such as brisk walking to maintain their health. However, a fast walking speed can increase plantar pressure, especially at the forefoot and rearfoot areas, thereby increasing the risk of diabetic foot ulcers (DFU). The deep learning model can identify plantar pressure patterns for an early detection of DFU when performing various intensities of exercise. Therefore, this study aimed to identify differences in walking speeds to the plantar pressure response using deep learning methods, including Resnet50, InceptionV3, and MobileNets. The deep learning models were used to classify the plantar pressure images of healthy people walking on a treadmill. The design consisted of three walking speeds (1.8 mph, 3.6 mph, and 5.4 mph). Through 5-fold cross-validation, accuracy, and robustness, the Resnet50 model had a better performance compared to the other two models in the image classification with a mean F1 score of 0.8646 and a standard deviation of 0.0466. The results indicated that the Resnet50 model can be used to analyze plantar pressure images for assessing risks of DFU.

Original language	English
Title of host publication	Advances in Physical, Social and Occupational Ergonomics - Proceedings of the AHFE 2021 Virtual Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics, and Cross-Cultural Decision Making, 2021
Editors	Ravindra S. Goonetilleke, Shuping Xiong, Henrijs Kalkis, Zenija Roja, Waldemar Karwowski, Atsuo Murata
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	270-277
Number of pages	8
ISBN (Print)	9783030807122
DOIs	https://doi.org/10.1007/978-3-030-80713-9_35
State	Published - 2021
Event	AHFE Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics, and Cross-Cultural Decision Making, 2021 - Virtual, Online Duration: 25 Jul 2021 → 29 Jul 2021

Publication series

Name	Lecture Notes in Networks and Systems
Volume	273
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	AHFE Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics, and Cross-Cultural Decision Making, 2021
City	Virtual, Online
Period	25/07/21 → 29/07/21

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Diabetic foot ulcers
InceptionV3
MobileNets
Resnet50

Access to Document

10.1007/978-3-030-80713-9_35

Cite this

Chen, H. C., Sunardi, Jan, Y. K., Liau, B. Y., Lin, C. Y., Tsai, J. Y., Li, C. T., & Lung, C. W. (2021). Using Deep Learning Methods to Predict Walking Intensity from Plantar Pressure Images. In R. S. Goonetilleke, S. Xiong, H. Kalkis, Z. Roja, W. Karwowski, & A. Murata (Eds.), Advances in Physical, Social and Occupational Ergonomics - Proceedings of the AHFE 2021 Virtual Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics, and Cross-Cultural Decision Making, 2021 (pp. 270-277). (Lecture Notes in Networks and Systems; Vol. 273). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-80713-9_35

Chen, Hsing Chung ; Sunardi ; Jan, Yih Kuen et al. / Using Deep Learning Methods to Predict Walking Intensity from Plantar Pressure Images. Advances in Physical, Social and Occupational Ergonomics - Proceedings of the AHFE 2021 Virtual Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics, and Cross-Cultural Decision Making, 2021. editor / Ravindra S. Goonetilleke ; Shuping Xiong ; Henrijs Kalkis ; Zenija Roja ; Waldemar Karwowski ; Atsuo Murata. Springer Science and Business Media Deutschland GmbH, 2021. pp. 270-277 (Lecture Notes in Networks and Systems).

@inproceedings{5cf13871be8e414cbb118a72a3d2fabc,

title = "Using Deep Learning Methods to Predict Walking Intensity from Plantar Pressure Images",

abstract = "People with diabetes are recommended to perform exercise such as brisk walking to maintain their health. However, a fast walking speed can increase plantar pressure, especially at the forefoot and rearfoot areas, thereby increasing the risk of diabetic foot ulcers (DFU). The deep learning model can identify plantar pressure patterns for an early detection of DFU when performing various intensities of exercise. Therefore, this study aimed to identify differences in walking speeds to the plantar pressure response using deep learning methods, including Resnet50, InceptionV3, and MobileNets. The deep learning models were used to classify the plantar pressure images of healthy people walking on a treadmill. The design consisted of three walking speeds (1.8 mph, 3.6 mph, and 5.4 mph). Through 5-fold cross-validation, accuracy, and robustness, the Resnet50 model had a better performance compared to the other two models in the image classification with a mean F1 score of 0.8646 and a standard deviation of 0.0466. The results indicated that the Resnet50 model can be used to analyze plantar pressure images for assessing risks of DFU.",

keywords = "Diabetic foot ulcers, InceptionV3, MobileNets, Resnet50",

author = "Chen, \{Hsing Chung\} and Sunardi and Jan, \{Yih Kuen\} and Liau, \{Ben Yi\} and Lin, \{Chih Yang\} and Tsai, \{Jen Yung\} and Li, \{Cheng Tsung\} and Lung, \{Chi Wen\}",

note = "Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.; AHFE Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics, and Cross-Cultural Decision Making, 2021 ; Conference date: 25-07-2021 Through 29-07-2021",

year = "2021",

doi = "10.1007/978-3-030-80713-9\_35",

language = "???core.languages.en\_GB???",

isbn = "9783030807122",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "270--277",

editor = "Goonetilleke, \{Ravindra S.\} and Shuping Xiong and Henrijs Kalkis and Zenija Roja and Waldemar Karwowski and Atsuo Murata",

booktitle = "Advances in Physical, Social and Occupational Ergonomics - Proceedings of the AHFE 2021 Virtual Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics, and Cross-Cultural Decision Making, 2021",

}

Chen, HC, Sunardi, Jan, YK, Liau, BY, Lin, CY, Tsai, JY, Li, CT & Lung, CW 2021, Using Deep Learning Methods to Predict Walking Intensity from Plantar Pressure Images. in RS Goonetilleke, S Xiong, H Kalkis, Z Roja, W Karwowski & A Murata (eds), Advances in Physical, Social and Occupational Ergonomics - Proceedings of the AHFE 2021 Virtual Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics, and Cross-Cultural Decision Making, 2021. Lecture Notes in Networks and Systems, vol. 273, Springer Science and Business Media Deutschland GmbH, pp. 270-277, AHFE Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics, and Cross-Cultural Decision Making, 2021, Virtual, Online, 25/07/21. https://doi.org/10.1007/978-3-030-80713-9_35

Using Deep Learning Methods to Predict Walking Intensity from Plantar Pressure Images. / Chen, Hsing Chung; Sunardi; Jan, Yih Kuen et al.
Advances in Physical, Social and Occupational Ergonomics - Proceedings of the AHFE 2021 Virtual Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics, and Cross-Cultural Decision Making, 2021. ed. / Ravindra S. Goonetilleke; Shuping Xiong; Henrijs Kalkis; Zenija Roja; Waldemar Karwowski; Atsuo Murata. Springer Science and Business Media Deutschland GmbH, 2021. p. 270-277 (Lecture Notes in Networks and Systems; Vol. 273).

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

TY - GEN

T1 - Using Deep Learning Methods to Predict Walking Intensity from Plantar Pressure Images

AU - Chen, Hsing Chung

AU - Sunardi,

AU - Jan, Yih Kuen

AU - Liau, Ben Yi

AU - Lin, Chih Yang

AU - Tsai, Jen Yung

AU - Li, Cheng Tsung

AU - Lung, Chi Wen

PY - 2021

Y1 - 2021

N2 - People with diabetes are recommended to perform exercise such as brisk walking to maintain their health. However, a fast walking speed can increase plantar pressure, especially at the forefoot and rearfoot areas, thereby increasing the risk of diabetic foot ulcers (DFU). The deep learning model can identify plantar pressure patterns for an early detection of DFU when performing various intensities of exercise. Therefore, this study aimed to identify differences in walking speeds to the plantar pressure response using deep learning methods, including Resnet50, InceptionV3, and MobileNets. The deep learning models were used to classify the plantar pressure images of healthy people walking on a treadmill. The design consisted of three walking speeds (1.8 mph, 3.6 mph, and 5.4 mph). Through 5-fold cross-validation, accuracy, and robustness, the Resnet50 model had a better performance compared to the other two models in the image classification with a mean F1 score of 0.8646 and a standard deviation of 0.0466. The results indicated that the Resnet50 model can be used to analyze plantar pressure images for assessing risks of DFU.

AB - People with diabetes are recommended to perform exercise such as brisk walking to maintain their health. However, a fast walking speed can increase plantar pressure, especially at the forefoot and rearfoot areas, thereby increasing the risk of diabetic foot ulcers (DFU). The deep learning model can identify plantar pressure patterns for an early detection of DFU when performing various intensities of exercise. Therefore, this study aimed to identify differences in walking speeds to the plantar pressure response using deep learning methods, including Resnet50, InceptionV3, and MobileNets. The deep learning models were used to classify the plantar pressure images of healthy people walking on a treadmill. The design consisted of three walking speeds (1.8 mph, 3.6 mph, and 5.4 mph). Through 5-fold cross-validation, accuracy, and robustness, the Resnet50 model had a better performance compared to the other two models in the image classification with a mean F1 score of 0.8646 and a standard deviation of 0.0466. The results indicated that the Resnet50 model can be used to analyze plantar pressure images for assessing risks of DFU.

KW - Diabetic foot ulcers

KW - InceptionV3

KW - MobileNets

KW - Resnet50

UR - https://www.scopus.com/pages/publications/85112260095

U2 - 10.1007/978-3-030-80713-9_35

DO - 10.1007/978-3-030-80713-9_35

M3 - 會議論文篇章

AN - SCOPUS:85112260095

SN - 9783030807122

T3 - Lecture Notes in Networks and Systems

SP - 270

EP - 277

BT - Advances in Physical, Social and Occupational Ergonomics - Proceedings of the AHFE 2021 Virtual Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics, and Cross-Cultural Decision Making, 2021

A2 - Goonetilleke, Ravindra S.

A2 - Xiong, Shuping

A2 - Kalkis, Henrijs

A2 - Roja, Zenija

A2 - Karwowski, Waldemar

A2 - Murata, Atsuo

PB - Springer Science and Business Media Deutschland GmbH

T2 - AHFE Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics, and Cross-Cultural Decision Making, 2021

Y2 - 25 July 2021 through 29 July 2021

ER -

Chen HC, Sunardi, Jan YK, Liau BY, Lin CY, Tsai JY et al. Using Deep Learning Methods to Predict Walking Intensity from Plantar Pressure Images. In Goonetilleke RS, Xiong S, Kalkis H, Roja Z, Karwowski W, Murata A, editors, Advances in Physical, Social and Occupational Ergonomics - Proceedings of the AHFE 2021 Virtual Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics, and Cross-Cultural Decision Making, 2021. Springer Science and Business Media Deutschland GmbH. 2021. p. 270-277. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-030-80713-9_35

Using Deep Learning Methods to Predict Walking Intensity from Plantar Pressure Images

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this