Interface for Real-Time Monitoring of Anthropomorphic Gait Using Instrumented Piezoresistive Insoles

• Wesley Ramos dos Santos UEFS
• Armando S. Sanca UEFS

DOI: https://doi.org/10.5753/erbase.2025.13589

Abstract

This work presents an interface for monitoring anthropomorphic gait, with estimation and analysis of movement kinematics based on data collected by sixteen prefabricated piezoresistive sensors arranged in insoles. The instrumented system also includes six inertial measurement units attached to the articular segments of the lower limbs, enabling the tracking of joint trajectories. For the estimation of these trajectories, four non-parametric machine learning computational models were evaluated: k-NN, ANN, decision tree, and random forest. The results demonstrate the feasibility of applying pattern classification-based models to estimate joint angles, with potential applications in driving active orthosis joints or rehabilitation devices.

References

Aggarwal, A., Gupta, R., and Agarwal, R. (2018). Design and development of integrated insole system for gait analysis. In Proceedings of the 2018 Eleventh International Conference on Contemporary Computing (IC3), pages 2–4, Noida, India. IEEE. © 2018 IEEE.

Ansah, S., Olugbon, F., Arthanat, S., LaRoche, D., and Chen, D. (2023). Smart insole based shuffling detection system for improved gait analysis in parkinson’s disease. In 2023 IEEE 19th International Conference on Body Sensor Networks (BSN), pages 1–6, Durham, USA. IEEE.

Antoniou, N., Hadjiantonis, A., Kyriacou, C., and Konstantinidis, A. (2023). A cost effective smart insole system for real time gait analysis. In 2023 IEEE SENSORS, pages 979–8.

Breiman, L. (2001). Random Forest., volume 45, pages 5–32.

Chen, D., Cai, Y., Qian, X., Ansari, R., Xu, W., Chu, K.-C., and Huang, M.-C. (2020). Bring gait lab to everyday life: Gait analysis in terms of activities of daily living. IEEE Internet of Things Journal, 7(2):1298–1307.

Cunningham, P. and Delany, S. (2007). k-nearest neighbour classifiers. Mult Classif Syst, 54.

Duong, T. T. H., Uher, D., Montes, J., and Zanotto, D. (2022). Ecological validation of machine learning models for spatiotemporal gait analysis in free-living environments using instrumented insoles. IEEE Robotics and Automation Letters, 7(4):10834–10841.

Hao, Z., Cook, K., Canning, J., Chen, H.-T., and Martelli, C. (2020). 3-d printed smart orthotic insoles: Monitoring a person’s gait step by step. Sensor Integration, 4(1).

Haykin, S. (2001). Redes Neurais: Princípios e Prática. Bookman Editora.

Leal-Junior, A. G., Frizera, A., Avellar, L. M., Marques, C., and Pontes, M. J. (2018). Polymer optical fiber for in-shoe monitoring of ground reaction forces during the gait. IEEE Sensors Journal, 18(6):2362–2368.

Lin, F., Wang, A., Zhuang, Y., Tomita, M. R., and Xu, W. (2016). Smart insole: A wearable sensor device for unobtrusive gait monitoring in daily life. IEEE Transactions on Industrial Informatics, 12(6):2281–2291.

Nguyen, N. D., Bui, D. T., Truong, P. H., and Jeong, G.-M. (2018). Classification of five ambulatory activities regarding stair and incline walking using smart shoes. IEEE Sensors Journal, 18(13):5422–5428.

Rokach, L. and Maimon, O. (2005). Decision Trees, volume 6, pages 165–192.

Zhang, H., Zanotto, D., and Agrawal, S. K. (2017). Estimating cop trajectories and kinematic gait parameters in walking and running using instrumented insoles. IEEE Robotics and Automation Letters, 2(4):2159–2166.