Development of Wearable Optical Fiber Sensors Integrated with Machine Learning Monitoring for Rehabilitation Gait Analysis
DOI:
https://doi.org/10.56532/mjsat.v6i1.722Keywords:
Wearable Sensors, Gait Analysis, Fiber Optic Insole, Machine Learning, Rehabilitation MonitoringAbstract
A wearable optical fiber sensor system integrated with machine learning is developed to support rehabilitation gait analysis. Human gait monitoring plays a crucial role in evaluating the recovery progress of individuals with lower limb injuries or neurological disorders. Conventional gait analysis methods are often expensive, non-portable, and reliant on expert interpretation, which limits their practicality for continuous use. To overcome these challenges, a flexible insole embedded with six fiber optic pressure sensors is designed to capture plantar pressure data during walking. The collected data is wirelessly transmitted to a MATLAB interface, where it is processed and analysed using a decision tree classifier to identify gait phases and detect abnormalities. The output is visualized through graphical representations and classification trends, enabling clinicians to monitor and interpret patient progress effectively. This system enables the assessment of gait patterns in both healthy individuals and those undergoing rehabilitation. Expected outcomes include a cost-effective, portable, and intelligent solution capable of distinguishing between normal and abnormal gait patterns, identifying stages of rehabilitation, and offering interpretable feedback for improved clinical decision-making. The approach aims to advance non-invasive, automated, and personalized rehabilitation monitoring.
References
Kian, G. Widanapathirana, A. M. Joseph, D. T. Lai, and R. Begg, “Application of wearable sensors in actuation and control of powered ankle exoskeletons: A comprehensive review,” Sensors, vol. 22, no. 6, p. 2244, 2022. doi: https://doi.org/10.3390/s22062244
M. Bonanno, A. M. De Nunzio, A. Quartarone, A. Militi, F. Petralito, and R. S. Calabrò, “Gait analysis in neurorehabilitation: From research to clinical practice,” Bioengineering, vol. 10, no. 7, p. 785, 2023. doi: https://doi.org/10.3390/bioengineering10070785
G. Marino, F. De Capitani, P. Adamo, L. Bolzoni, R. Gatti, and F. Temporiti, “Long-term gait analysis in patients after total knee arthroplasty: A systematic review and meta-analysis,” Gait & Posture, vol. 113, pp. 75–98, 2024. doi: https://doi.org/10.1016/j.gaitpost.2024.06.002
N. Ben Chaabane, P. H. Conze, M. Lempereur, G. Quellec, O. Rémy-Néris, S. Brochard, et al., “Quantitative gait analysis and prediction using artificial intelligence for patients with gait disorders,” Scientific Reports, vol. 13, no. 1, p. 23099, 2023. doi: https://doi.org/10.1038/s41598-023-49883-8
P. Khera and N. Kumar, “Role of machine learning in gait analysis: A review,” J. Med. Eng. Technol., vol. 44, no. 8, pp. 441–467, 2020. doi: https://doi.org/10.1080/03091902.2020.1822940
Y. Hutabarat, D. Owaki, and M. Hayashibe, “Recent advances in quantitative gait analysis using wearable sensors: A review,” IEEE Sensors J., vol. 21, no. 23, pp. 26470–26487, 2021. doi: https://doi.org/10.1109/JSEN.2021.3119658
D. Slijepcevic, F. Horst, S. Lapuschkin, B. Horsak, A. M. Raberger, A. Kranzl, et al., “Explaining machine learning models for clinical gait analysis,” ACM Trans. Comput. Healthcare, vol. 3, no. 2, pp. 1–27, 2021. doi: https://doi.org/10.1145/3474121
L. Bachar, R. Klein, M. Tur, and J. Bortman, “Fault diagnosis of gear transmissions via optic fiber Bragg grating strain sensors,” Mech. Syst. Signal Process., vol. 169, p. 108629, 2022. doi: https://doi.org/10.1016/j.ymssp.2021.108629
C. Kai, H. Yingping, S. Dandan, L. Wenyi, and Z. Huixin, “A lossless fiber pressure sensor based on PDMS,” IEEE Access, vol. 8, pp. 189036–189042, 2020. doi: https://doi.org/10.1109/ACCESS.2020.3031931
A. M. Tahir, M. E. Chowdhury, A. Khandakar, S. Al-Hamouz, M. Abdalla, S. Awadallah, et al., “A systematic approach to the design and characterization of a smart insole for detecting vertical ground reaction force (VGRF) in gait analysis,” Sensors, vol. 20, no. 4, p. 957, 2020. doi: https://doi.org/10.3390/s20040957
N. Lovecchio, M. Zago, and C. Sforza, “Gait analysis in the rehabilitation process,” in Rehabilitation After Limb Salvage Surgery, 2021, pp. 109–118. doi: https://doi.org/10.1007/978-3-030-66352-0_13
I. Rojek, P. Prokopowicz, J. Dorożyński, and D. Mikołajewski, “Novel methods of AI-based gait analysis in post-stroke patients,” Appl. Sci., vol. 13, no. 10, p. 6258, 2023. doi: https://doi.org/10.3390/app13106258
L. M. S. D. Nascimento, L. V. Bonfati, M. L. B. Freitas, J. J. A. Mendes Junior, H. V. Siqueira, and S. L. Stevan Jr., “Sensors and systems for physical rehabilitation and health monitoring—A review,” Sensors, vol. 20, no. 15, p. 4063, 2020. doi: https://doi.org/10.3390/s20154063
P. Arens, C. Siviy, J. Bae, D. K. Choe, N. Karavas, T. Baker, et al., “Real-time gait metric estimation for everyday gait training with wearable devices in people poststroke,” Wearable Technol., vol. 2, p. e2, 2021. doi: https://doi.org/10.1017/wtc.2020.11
T. Jo and T. Jo, “Decision tree,” in Machine Learning Foundations: Supervised, Unsupervised, and Advanced Learning, 2021, pp. 141–165. doi: https://doi.org/10.1007/978-3-030-65900-4
Priyanka and D. Kumar, “Decision tree classifier: A detailed survey,” Int. J. Inf. Decis. Sci., vol. 12, no. 3, pp. 246–269, 2020. doi: https://doi.org/10.1504/IJIDS.2020.108141
B. Charbuty and A. Abdulazeez, “Classification based on decision tree algorithm for machine learning,” J. Appl. Sci. Technol. Trends, vol. 2, no. 1, pp. 20–28, 2021. doi: https://doi.org/10.38094/jastt20165
L. Fraiwan and O. Hassanin, “Computer-aided identification of degenerative neuromuscular diseases based on gait dynamics and ensemble decision tree classifiers,” PLoS One, vol. 16, no. 6, p. e0252380, 2021. doi: https://doi.org/10.1371/journal.pone.0252380
T. Fujita, Y. Ohashi, M. Kurita, K. Yamane, Y. Yamamoto, T. Sone, et al., “Functions necessary for gait independence in patients with stroke: A study using decision tree,” J. Stroke Cerebrovasc. Dis., vol. 29, no. 8, p. 104998, 2020. doi: https://doi.org/10.1016/j.jstrokecerebrovasdis.2020.104998
T. Imura, Y. Iwamoto, T. Inagawa, N. Imada, R. Tanaka, H. Toda, et al., “Decision tree algorithm identifies stroke patients likely discharge home after rehabilitation using functional and environmental predictors,” J. Stroke Cerebrovasc. Dis., vol. 30, no. 4, p. 105636, 2021. doi: https://doi.org/10.1016/j.jstrokecerebrovasdis.2021.105636
Y. Inoue, T. Imura, R. Tanaka, J. Matsuba, and K. Harada, “Developing a clinical prediction rule for gait independence at discharge in patients with stroke: A decision-tree algorithm analysis,” J. Stroke Cerebrovasc. Dis., vol. 31, no. 6, p. 106441, 2022. doi: https://doi.org/10.1016/j.jstrokecerebrovasdis.2022.106441
M. Asif, M. A. Tayyab, M. H. Shahid, U. Arif, M. I. Tiwana, U. S. Khan, and W. S. Qureshi, “Analysis of human gait cycle with body equilibrium based on leg orientation,” IEEE Access, vol. 10, pp. 123177–123189, 2022. doi: https://doi.org/10.1109/ACCESS.2022.3222859
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Nur Nadiah Mazlan, Wan Suhaimizan Wan Zaki, Ariffuddin Joret, Ashok Vajravelu, Muhammad Mahadi Abdul Jamil
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
