Assessing a Smart-Insole-Based System in Stroke Gait Pattern Recognition

Yu-Huan Chien; Chun-Chung Chang; Jia-Yu Li; Kai-Li Fang; Wen-Yuan Lee; Mi-Hsuan Lin; Yi-Yin Lai; Luigi D'Acro; Alastair Martin; Katy Pedlow; Haying Wang; Huiru Zheng; Che-Lun Hung

doi:10.1109/bibm66473.2025.11356058

Assessing a Smart-Insole-Based System in Stroke Gait Pattern Recognition

Yu-Huan Chien
, Chun-Chung Chang
, Jia-Yu Li
, Kai-Li Fang
, Wen-Yuan Lee
, Mi-Hsuan Lin
, Yi-Yin Lai
, Luigi D'Acro
, Alastair Martin
, Katy Pedlow
, Haying Wang
, Huiru Zheng
, Che-Lun Hung

Ulster University

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

3 Downloads (Pure)

Abstract

Stroke commonly leads to long-term gait impairments, underscoring the need for objective and continuous functional assessment during rehabilitation. This study employs machine learning methods to assess a smart insole-based system in stroke gait recognition. Data were collected from stroke survivors and healthy control participants during Walk and Timed-Up-and-Go tasks. After preprocessing, group differences were quantified using Hedges' g, and multiple machine learning models were applied to classify two participant groups. Support Vector Machine and KNN achieved the best performance, with accuracies of 0.88. The results demonstrate that sensor-based gait features can be used to distinguish stroke gait patterns from control gait patterns, highlighting the potential of this approach for future homebased monitoring and personalised rehabilitation.

Original language	English
Title of host publication	2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Publisher	IEEE
Pages	6543-6550
Number of pages	8
ISBN (Electronic)	979-8-3315-1557-7
ISBN (Print)	979-8-3315-1558-4
DOIs	https://doi.org/10.1109/bibm66473.2025.11356058
Publication status	Published online - 29 Jan 2026
Event	2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) - Wuhan, China Duration: 15 Dec 2025 → 18 Dec 2025

Publication series

Name	2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Publisher	IEEE Control Society
ISSN (Print)	2156-1125
ISSN (Electronic)	2156-1133

Conference

Conference	2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Country/Territory	China
City	Wuhan
Period	15/12/25 → 18/12/25

Funding

This work is supported by the National Science and Technology Council (NSTC) of Taiwan under Grants No. NSTC 112-2314-B-A49 -049-MY3, NSTC 112-2927-I-A49A-502, NSTC 113-2927-I-A49A-502, and Royal Society International Exchange Grant EPSRC EP/W000679/1 secondary project 20001397 R00287.

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Machine Learning
Stroke
Gait

Access to Document

10.1109/bibm66473.2025.11356058

stroke_V314Author Accepted Manuscript, 462 KB

Cite this

Chien, Y.-H., Chang, C.-C., Li, J.-Y., Fang, K.-L., Lee, W.-Y., Lin, M.-H., Lai, Y.-Y., D'Acro, L., Martin, A., Pedlow, K., Wang, H., Zheng, H., & Hung, C.-L. (2026). Assessing a Smart-Insole-Based System in Stroke Gait Pattern Recognition. In 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 6543-6550). (2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)). IEEE. Advance online publication. https://doi.org/10.1109/bibm66473.2025.11356058

@inproceedings{f19ead71beda442b98a6bb8baff61acf,

title = "Assessing a Smart-Insole-Based System in Stroke Gait Pattern Recognition",

abstract = "Stroke commonly leads to long-term gait impairments, underscoring the need for objective and continuous functional assessment during rehabilitation. This study employs machine learning methods to assess a smart insole-based system in stroke gait recognition. Data were collected from stroke survivors and healthy control participants during Walk and Timed-Up-and-Go tasks. After preprocessing, group differences were quantified using Hedges' g, and multiple machine learning models were applied to classify two participant groups. Support Vector Machine and KNN achieved the best performance, with accuracies of 0.88. The results demonstrate that sensor-based gait features can be used to distinguish stroke gait patterns from control gait patterns, highlighting the potential of this approach for future homebased monitoring and personalised rehabilitation.",

keywords = "Machine Learning, Stroke, Gait",

author = "Yu-Huan Chien and Chun-Chung Chang and Jia-Yu Li and Kai-Li Fang and Wen-Yuan Lee and Mi-Hsuan Lin and Yi-Yin Lai and Luigi D'Acro and Alastair Martin and Katy Pedlow and Haying Wang and Huiru Zheng and Che-Lun Hung",

year = "2026",

month = jan,

day = "29",

doi = "10.1109/bibm66473.2025.11356058",

language = "English",

isbn = "979-8-3315-1558-4",

series = "2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)",

publisher = "IEEE",

pages = "6543--6550",

booktitle = "2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)",

address = "United States",

note = "2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) ; Conference date: 15-12-2025 Through 18-12-2025",

}

Chien, Y-H, Chang, C-C, Li, J-Y, Fang, K-L, Lee, W-Y, Lin, M-H, Lai, Y-Y, D'Acro, L, Martin, A, Pedlow, K, Wang, H, Zheng, H & Hung, C-L 2026, Assessing a Smart-Insole-Based System in Stroke Gait Pattern Recognition. in 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, pp. 6543-6550, 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Wuhan, China, 15/12/25. https://doi.org/10.1109/bibm66473.2025.11356058

Assessing a Smart-Insole-Based System in Stroke Gait Pattern Recognition. / Chien, Yu-Huan; Chang, Chun-Chung; Li, Jia-Yu et al.
2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2026. p. 6543-6550 (2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)).

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

TY - GEN

T1 - Assessing a Smart-Insole-Based System in Stroke Gait Pattern Recognition

AU - Chien, Yu-Huan

AU - Chang, Chun-Chung

AU - Li, Jia-Yu

AU - Fang, Kai-Li

AU - Lee, Wen-Yuan

AU - Lin, Mi-Hsuan

AU - Lai, Yi-Yin

AU - D'Acro, Luigi

AU - Martin, Alastair

AU - Pedlow, Katy

AU - Wang, Haying

AU - Zheng, Huiru

AU - Hung, Che-Lun

PY - 2026/1/29

Y1 - 2026/1/29

N2 - Stroke commonly leads to long-term gait impairments, underscoring the need for objective and continuous functional assessment during rehabilitation. This study employs machine learning methods to assess a smart insole-based system in stroke gait recognition. Data were collected from stroke survivors and healthy control participants during Walk and Timed-Up-and-Go tasks. After preprocessing, group differences were quantified using Hedges' g, and multiple machine learning models were applied to classify two participant groups. Support Vector Machine and KNN achieved the best performance, with accuracies of 0.88. The results demonstrate that sensor-based gait features can be used to distinguish stroke gait patterns from control gait patterns, highlighting the potential of this approach for future homebased monitoring and personalised rehabilitation.

AB - Stroke commonly leads to long-term gait impairments, underscoring the need for objective and continuous functional assessment during rehabilitation. This study employs machine learning methods to assess a smart insole-based system in stroke gait recognition. Data were collected from stroke survivors and healthy control participants during Walk and Timed-Up-and-Go tasks. After preprocessing, group differences were quantified using Hedges' g, and multiple machine learning models were applied to classify two participant groups. Support Vector Machine and KNN achieved the best performance, with accuracies of 0.88. The results demonstrate that sensor-based gait features can be used to distinguish stroke gait patterns from control gait patterns, highlighting the potential of this approach for future homebased monitoring and personalised rehabilitation.

KW - Machine Learning

KW - Stroke

KW - Gait

U2 - 10.1109/bibm66473.2025.11356058

DO - 10.1109/bibm66473.2025.11356058

M3 - Conference contribution

SN - 979-8-3315-1558-4

T3 - 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

SP - 6543

EP - 6550

BT - 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

PB - IEEE

T2 - 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

Y2 - 15 December 2025 through 18 December 2025

ER -

Chien YH, Chang CC, Li JY, Fang KL, Lee WY, Lin MH et al. Assessing a Smart-Insole-Based System in Stroke Gait Pattern Recognition. In 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE. 2026. p. 6543-6550. (2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)). Epub 2026 Jan 29. doi: 10.1109/bibm66473.2025.11356058

Assessing a Smart-Insole-Based System in Stroke Gait Pattern Recognition

Abstract

Publication series

Conference

Funding

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this