Preliminary Study of Virtual sEMG Signal-Assisted Classification

Surface electromyography (sEMG) is widely used in various fields to analyze user intentions. Conventional sEMG-based classifications are electrode-dependent; thus, trained classifiers cannot be applied to other electrodes that have different parameters. This defect degrades the practicability of sEMG-based applications. In this study, we propose a virtual sEMG signal-assisted classification to achieve electrode-independent classification. The virtual signal for any electrode configuration can be generated using muscle activation signals obtained from the proposed model. The feasibility of the virtual signal is demonstrated with regard to i) classifications using fewer sEMG channels by a pre-trained classifier without re-training and ii) electrode-independent classifications. This study focuses on preliminary tests of virtual sEMG signal-assisted classification. Future studies should consider model improvement and experiments involving more subjects to achieve plug-and-play classification.

Wireless sEMG System with a Microneedle-Based High-Density Electrode Array on a Flexible Substrate

Surface electromyography (sEMG) signals reflect muscle contraction and hence, can provide information regarding a user's movement intention. High-density sEMG systems have been proposed to measure muscle activity in small areas and to estimate complex motion using spatial patterns. However, conventional systems based on wet electrodes have several limitations. For example, the electrolyte enclosed in wet electrodes restricts spatial resolution, and these conventional bulky systems limit natural movements. In this paper, a microneedle-based high-density electrode array on a circuit integrated flexible substrate for sEMG is proposed. Microneedles allow for high spatial resolution without requiring conductive substances, and flexible substrates guarantee stable skin-electrode contact. Moreover, a compact signal processing system is integrated with the electrode array. Therefore, sEMG measurements are comfortable to the user and do not interfere with the movement. The system performance was demonstrated by testing its operation and estimating motion using a Gaussian mixture model-based, simplified 2D spatial pattern.