Flexible Throat Patch for Phonetic Recognition and Ingestion Monitoring via Sensory Transition based on Machine Learning

Abstract

AbstractThe throat is an organ that includes the larynx, esophagus, and bronchi. Vocalization or deglutition triggers micro‐movements of muscles around the throat. In this study, based on machine learning using a flexible patch, pronunciation is identified by analyzing the vibration and movement of the laryngeal muscles, and the type of food consumed is determined through peristalsis analysis. Previously, voices are recognized through cochlea hair cells, and the type of food intake is identified through taste receptors. However, this study converted auditory or gustatory senses to tactile stage through sensory transition and finally visualized. Using a customized throat patch with segmented nodes, the pronunciation of [a], [e], [i], [o], and [u], representative vowels of languages worldwide, are distinguished with an accuracy of 85.9% based on the polynomial kernel algorithm. In addition, cookies, water, gummies, and chocolate are distinguished with 91.1% accuracy by detecting differences in the esophagus's peristalsis. Transformation of auditory or gustatory sensations to tactile information and visualization is expected to be used for communication in noisy environments or soundless environments such as outer space. This approach can also provide significant potential for determining the type of ingestion for users who have lost their sense of taste.