An Algorithm for Gait Segmentation Using Surface Electromyography and Subsequence Dynamic Time Warping

Gait segmentation in surface electromyography (sEMG) studies is usually achieved through kinematics. However, there are occasions when this multimodal analysis cannot be implemented. This study presents an algorithm for automated gait segmentation using sEMG signals based on subsequence Dynamic Time Warping (sDTW). Stride templates were chosen from vastus lateralis (VL) muscle and applied to segment the sEMG signals from six healthy subjects walking at various speeds. Heel strike events were detected with high temporal precision (<70 ms) and high fidelity (F1-score > 0.9) across all velocities. This approach therefore shows promise for specific experimental conditions, particularly when multimodal gait analysis is impractical. Future work will focus on the validation of this method in elderly and pathological populations to further assess its robustness.