A fully integrated, standalone stretchable device platform with in-sensor adaptive machine learning for rehabilitation

Abstract

Abstract Post-surgical treatments of the human throat and various diseases often require continuous monitoring of diverse vital and muscle activities. However, wireless, continuous monitoring and analysis of these activities directly from the (throat) skin still remain elusive. Here, we report the design and validation of a fully integrated standalone stretchable device platform that provides wireless measurements and cloud analysis of diverse vibrations and muscle electrical activities from the suprasternal throat. The modified composite hydrogel with low contact impedance and reduced adhesion provides high-quality long-term monitoring of local muscle electrical signals. The integrated triaxial broad-band accelerometer also measures large body movements and subtle physiological activities/vibrations. The combined data processed by a 2D-like sequential feature extractor with fully connected neurons facilitate the classification of various motion/speech features at a high accuracy of over 90%, which even adapts to the data with noise from motion artifacts or the data from new human subjects. The resulting standalone stretchable device with wireless monitoring and cloud processing capabilities paves the way to design and apply the next-generation wearable skin-interfaced systems for the remote monitoring and treatment evaluation of various diseases.