Evolutionary-Based Quantum Classification for Surface Electromyography Signals

The classification of surface electromyography (sEMG) signals represents a key objective in the domain of rehabilitation and prosthetic control. This task is particularly challenging due to several factors, including the high dimensionality of the data and the high computational cost of the currently used deep learning models. In this context, quantum computing methods may prove advantageous due to their capacity to process a substantial amount of data facilitated by quantum phenomena such as superposition. In light of these considerations, the objective of this study is to demonstrate the feasibility of quantum computing by performing a comparison between evolutionarybased quantum classifiers for sEMG signals. In particular, the considered quantum classifiers are based on variational quantum circuits trained using evolutionary algorithms such as genetic algorithms, differential evolution and particle swarm optimization. As demonstrated in the experimental session utilizing a wellknown hand gesture dataset, quantum classifiers, and especially those based on genetic algorithms, are effective for sEMG signal classification.