Stretchable and Durable HD-sEMG Electrodes for Accurate Swallowing Activity Recognition on Complex Epidermal Surfaces

Abstract

The utilization of Surface Electromyography (sEMG) is widespread for monitoring human health. Nonetheless, it is challenging to capture high-fidelity sEMG recordings in regions with intricate curved surfaces like the larynx, because regular sEMG electrodes have a stiff structure. In this paper, we develop a stretchable, high-density sEMG electrode array via a layer-by-layer printing and lamination process. The electrode offers a series of excellent human-machine interface features in terms of conformal adhesion to the skin, high electron-to-ionic conductivity (and thus lower contact impedance), prolonged environmental adaptability to resist water evaporation, and epidermal biocompatibility. This makes the electrode more appropriate than commercial electrodes for long-term wearable, high-fidelity recording of sEMG at complicated skin interfaces. Systematic in vivo studies investigate its practical functionality in swallowing activities classification, which is accomplished with high accuracy by decoding sEMG signals from the chin with the integration of an ear-mounted wearable system through machine learning algorithms. The results demonstrate clinical feasibility of the system in swallowing recognition-driven, non-invasive, user-comfortable dysphagia rehabilitation.