Electromyography-based assistive and rehabilitation devices have shown potential for restoring mobility, especially for post-stroke patients. However, the variability of biological signals and the processing delays caused by signal acquisition and feature extraction influence myoelectric control systems’ real-time functionality and robustness. This study evaluates the classification performance of electromyographic (EMG) signals for six distinct hand gestures in healthy individuals and post-stroke patients. Different feature extraction methods and machine learning algorithms are employed to analyze the impact of acquisition time (0.5–4 s) and the number of channels (1–4) on model accuracy, robustness, and generalization. The best results are obtained using power spectral density and dimensionality reduction, reaching a classification accuracy of 94.79% with a 2 s signal and 95.31% for 4 s. Acquisition time has a greater effect on accuracy than the number of channels used with accuracy stabilizing at 2 s. We test for generalization using post-stroke patient data, evaluating two scenarios: intra-patient validation with 90% accuracy and cross-patient validation with 35–40% accuracy. This study contributes to developing effective real-time myoelectric control systems for neurorehabilitation.

Electromyography-based assistive and rehabilitation devices have shown potential for restoring mobility, especially for post-stroke patients. However, the variability of biological signals and the processing delays caused by signal acquisition and feature extraction influence myoelectric control systems’ real-time functionality and robustness. This study evaluates the classification performance of electromyographic (EMG) signals for six distinct hand gestures in healthy individuals and post-stroke patients. Different feature extraction methods and machine learning algorithms are employed to analyze the impact of acquisition time (0.5–4 s) and the number of channels (1–4) on model accuracy, robustness, and generalization. The best results are obtained using power spectral density and dimensionality reduction, reaching a classification accuracy of 94.79% with a 2 s signal and 95.31% for 4 s. Acquisition time has a greater effect on accuracy than the number of channels used, with accuracy stabilizing at 2 s. We test for generalization using post-stroke patient data, revealing a substantial accuracy drop from 90% (intra-patient validation) to 35–40% (cross-patient validation). This study paves the way for developing effective real-time myoelectric control systems for neurorehabilitation.

Stroke affects over 12 million people annually worldwide, with approximately 80% of survivors experiencing upper limb motor impairments that hinder daily activities. While assistive technologies offer promising alternatives to conventional rehabilitation, most studies rely on non-portable devices, lack experimental validation, or focus on isolated control strategies. This work presents an integrated framework for functional and control assessment of a hand exoskeleton designed to assist stroke survivors in performing grasping tasks. The framework combines a data-driven system identification approach, dynamic modeling, and experimental evaluation under realistic operating conditions, including object variability, external disturbances, sensor noise, and model uncertainty. As a case study, two linear controllers-a proportional controller and a lead-lag compensator-were implemented and compared on a unified hardware platform. Simulation and physical trials were conducted, evaluating settling time, steady-state error, and overshoot. Both controllers exhibited low settling times and stable steady-state behavior, despite the nonlinear nature of the system. The lead-lag compensator further reduced overshoot and steady-state error but showed increased sensitivity to gain variation. Beyond this comparison, the results highlight how physical constraints and modeling inaccuracies shape controller behavior, underscoring the importance of integrated evaluation methodologies in the development of assistive robotic systems.