Biomedical Engineering
Vol. 39 No. 10 (2024): Proceedings of Faculty of Technical Sciences
CONTROL OF MULTIPLE DEGREES OF FREEDOM USING MACHINE LEARNING TECHNIQUES
Abstract
In this paper, the control of a myoelectric hand prosthesis is presented, which involves the classification of 9 hand movements based on input EMG signals collected from four forearm muscles. The machine learning classification algorithms discussed in this paper are LDA, SVM and ANN. The metrics used for evaluating classifiers performance are accuracy, recall, specificity and precision.
References
[1] F. Mereu, F. Leone, C. Gentile, F. Cordella, E. Gruppioni, and L. Zollo, “Control Strategies and Performance Assessment of Upper-Limb TMR Prostheses: A Review,” Sensors, Vol. 21, no. 6, p. 1953, Mar. 2021.
[2] A. Marinelli et al., “Active upper limb prostheses: a review on current state and upcoming breakthroughs”, Progress in Biomedical Engineering, Vol. 5, no. 1, p. 012001, Jan. 2023.
[3] M. Legrand, “Upper limb prostheses control based on user’s body compensations,” theses.hal.science, Mar. 2021.
[4] M. Hakonen, H. Piitulainen, and A. Visala, “Current state of digital signal processing in myoelectric interfaces and related applications,” Biomedical Signal Processing and Control, Vol. 18, pp. 334–359, Apr. 2015.
[5] G. Li, “Electromyography Pattern-Recognition-Based Control of Powered Multifunctional Upper-Limb Prostheses,” Advances in Applied Electromyography, Aug. 2011.
[6] Tijana Nosek, Branko Brkljač, Danica Despotović, Milan Sečujski, Tatjana Lončar-Turukalo, “Praktikum iz mašinskog učenja”, Univerzitet u Novom Sadu, 2020.
[7] Yang, Li, and Abdallah Shami. “On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice.” Neurocomputing, Vol. 415, pp. 295–316, Nov. 2020.