24 September 2024 in IEEE Access
Surface electromyography (sEMG), the electrical signals generated by muscle activity, plays an important role in prosthetics, orthotics, and human-computer interaction because of its non-invasive signal acquisition, real-time responsiveness, and ability to provide rich information for decoding complex movements. However, the complexity and nonlinear characteristics of sEMG signals present challenges in implementing sEMG-based tasks, such as hand gesture classification. Motivated by effectively addressing the challenges and extending the applicability of sEMG signals, we propose a nearest-centroid-based hand gesture classification framework using sEMG signals. We utilize the Dynamic Time Warping Barycenter Averaging (DBA) algorithm to generate centroids of sEMG signals and leverage Dynamic Time Warping (DTW) to measure signal discrepancies. Our pipeline features an effective data preprocessing approach and a heuristic, repeatable, optimal parameter search process. Additionally, our framework supports interpretability analysis using Shapley values. Through our extensive experiments, we demonstrate that our framework has achieved an average accuracy of 90.0% and a peak accuracy of 91.25% on a public dataset Mendeley data-sEMG, which outperforms the surveyed existing methods and establishes our framework as state-of-the-art on such dataset.
8 July 2025 in IEEE Access
Providing real-time visual feedback during standing balance training has been shown to enhance balance ability. For example, displaying images of the trainee’s body or center-of-pressure (COP) trajectories while maintaining a standing posture facilitates the detection of postural sway, thereby improving balance. However, it remains unclear whether the spatial arrangement of such visual feedback influences the degree of balance improvement. Therefore, this study examined whether varying the display configuration of identical visual feedback affects balance enhancement. Specifically, we employed two fundamental ballet movements, “relevé” and “plié,” to investigate how different arrangements of body images and COP trajectories influence balance. Experimental results revealed that: (1) when a single visual feedback element was provided, placing it at eye level in front led to greater improvements in balance, and (2) when two visual feedback elements were presented simultaneously, arranging them side by side or overlapping yielded better balance outcomes. These findings highlight the significance of considering visual feedback arrangement to optimize balance enhancement.