Abstract
Because the tongue is controlled by the cranial nerve, even people with cervical cord injury can usually perform various voluntary tongue movements. With attention to voluntary tongue motion, which is capable of communicating the intentions of a person with a disability, we estimated the tongue movement using EMG signals of the underside of the jaw, where the suprahyoid muscles are crowded. Suprahyoid muscles usually function to open the mouth, and to control the position of the hyoid, the base of the tongue. We affixed a multi-channel electrode with nine electrodes to the underside of the jaw. Then, deriving many EMG signals using monopolar leads, we calculated 36 (=9C2) channel EMG signals between any two of the nine electrodes. Associating these EMG signals and tongue movements using a neural network, we confirmed our ability to estimate tongue movement with 91.5% precision. Furthermore, building a neural network for estimating mouth opening and deglutition, which are potential origins of false estimation, and discriminating that movement with 92.0% precision, we suggest precise extraction of only the signal of voluntary tongue movement from EMG signals of the suprahyoid muscles.
