Towards Robust and Accurate Myoelectric Controller Design based on Multi-objective Optimization using Evolutionary Computation

TL;DR

This study tackles energy-efficient myoelectric control by formulating SVM-based sEMG gesture classification as a constrained multi-objective optimization problem. It employs NSGA-II to optimize SVM hyperparameters, balancing accuracy with reduced Rest-state false negatives, and validates the approach on a dataset of 11 subjects across multiple limb positions. The results show Pareto-optimal solutions that trade off performance metrics, with FN-dominant fronts significantly lowering false rest movements while preserving accuracy, indicating practical benefits for robust, low-power prosthetic control. The work highlights the value of Pareto-based model selection in wearable EMG systems and outlines avenues for future efficiency-focused enhancements such as TinyML deployment and data-driven preprocessing.

Abstract

Myoelectric pattern recognition is one of the important aspects in the design of the control strategy for various applications including upper-limb prostheses and bio-robotic hand movement systems. The current work has proposed an approach to design an energy-efficient EMG-based controller by considering a kernelized SVM classifier for decoding the information of surface electromyography (sEMG) signals to infer the underlying muscle movements. In order to achieve the optimized performance of the EMG-based controller, our main strategy of classifier design is to reduce the false movements of the overall system (when the EMG-based controller is at the `Rest' position). To this end, we have formulated the training algorithm of the proposed supervised learning system as a general constrained multi-objective optimization problem. An elitist multi-objective evolutionary algorithm $-$ the non-dominated sorting genetic algorithm II (NSGA-II) has been used to tune the hyperparameters of SVM. We have presented the experimental results by performing the experiments on a dataset consisting of the sEMG signals collected from eleven subjects at five different upper limb positions. Furthermore, the performance of the trained models based on the two-objective metrics, namely classification accuracy, and false-negative have been evaluated on two different test sets to examine the generalization capability of the proposed training approach while implementing limb-position invariant EMG classification. It is evident from the presented result that the proposed approach provides much more flexibility to the designer in selecting the parameters of the classifier to optimize the energy efficiency of the EMG-based controller.

Figures (5)

• Figure 1: Robotic hand movement system based on sEMG signal classification.
• Figure 2: Multi-class Classification based on SVM: one-vs.-rest (OvR) strategy
• Figure 3: An illustrated confusion matrix of one of the binary classifiers
• Figure 4: NSGA-II Plots (Accuracy vs. FN for class 8) for Subject 10
• Figure 5: Effect of Multi-objective Optimization on Accuracy and FN of class 8