Abstract
The lower limb exoskeleton robot system is one of the significant tools for the rehabilitation of patients with knee arthritis, which helps to enhance the health of patients and upgrade their quality of life. However, the unexplained gait recognition model decreases the prediction accuracy of the exoskeleton system. The existing explainable models are seldom used in the domain of gait recognition due to their high complexity and large computation. To strengthen the transparency of the model, SHapley Additive exPlanations (SHAP) is applied to gait recognition for the first time in this paper, and an interpretable model framework that can be applied to any lower limb exoskeleton is proposed. Compared with the existing methods, SHAP has a more solid theoretical basis and more efficient calculation methods. The proposed framework can find the relationship between input features and gait prediction, to identify the optimal sensor combination. Additionally, The structure of the gait recognition model can be optimized by adjusting the feature attention of the model with the feature crossover method, and the accuracy of the model can be upgraded by more than 7.12% on average.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cross, M., et al.: The global burden of hip and knee osteoarthritis: estimates from the global burden of disease 2010 study. Ann. Rheum. Dis. 73(7), 1323–1330 (2014)
Tsai, H.-R., et al.: iKneeBraces: knee adduction moment evaluation measured by motion sensors in gait detection. In: Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp), pp. 386–391 (2016)
Shen, Y., et al.: A wearable sensor system for knee adduction moment measurement. In: Proceedings of IEEE International Conference on Real-Time Computing and Robotics (RCAR), pp. 7–12, June 2016
He, Z., Liu, T., Yi, J.: A wearable sensing and training system: towards gait rehabilitation for elderly patients with knee osteoarthritis. IEEE Sens. J. 19(14), 5936–5945 (2019)
Wang, C., et al.: Real-time estimation of knee adduction moment for gait retraining in patients with knee osteoarthritis. IEEE Trans. Neural Syst. Rehabil. Eng. 28(4), 888–894 (2020)
Heiden, E., et al.: NeuralSim: augmenting differentiable simulators with neural networks. arXiv:2011.04217, November 2020
Ming, Y., Qu, H., Bertini, E.: RuleMatrix: visualizing and understanding classifiers with rules. IEEE Trans. Vis. Comput. Graph. 25(1), 342–352 (2019)
Biran, O., Cotton, C.V.: Explanation and justification in machine learning: a survey (2017)
Lipton, Z.C.: The mythos of model interpretability. Commun. ACM 61(10) (2016)
Keneni, B.M., et al.: Evolving rule based explainable artificial intelligence for unmanned aerial vehicles. IEEE Access 7, 17001–17016 (2019)
Amruthnath, N.: Factor analysis in fault diagnostics using random forest. arXiv:1904.13366, April 2019
Lee, N., Azarian, M.H., Pecht, M.G.: An explainable deep learning-based prognostic model for rotating machinery. arXiv e-prints (2020)
Du, M., Liu, N., Hu, X.: Techniques for interpretable machine learning. arXiv:1808.00033, May 2019
Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should i trust you?”: explaining the predictions of any classifier. In: The 22nd ACM SIGKDD International Conference ACM, pp. 1135–1144 (2016)
Shapley, L.S.: A value for n-person games. In: Contributions to Theory Games, vol. 2, no. 28, pp. 307–317 (1953)
Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions. In: Proceedings of Advances in Neural Information Processing Systems, pp. 4765–4774 (2017)
Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery Data Mining (KDD), pp. 785–794 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, Y., Wang, X., Ye, Y., Sun, X. (2022). An Explainable Machine Learning Framework for Lower Limb Exoskeleton Robot System. In: Ma, H., Wang, X., Cheng, L., Cui, L., Liu, L., Zeng, A. (eds) Wireless Sensor Networks. CWSN 2022. Communications in Computer and Information Science, vol 1715. Springer, Singapore. https://doi.org/10.1007/978-981-19-8350-4_7
Download citation
DOI: https://doi.org/10.1007/978-981-19-8350-4_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-8349-8
Online ISBN: 978-981-19-8350-4
eBook Packages: Computer ScienceComputer Science (R0)