The tongue is one of the few organs with high mobility in the case of severe spinal cord injuries. However, most tongue-machine interfaces (TMIs) require the patient to wear obtrusive and unhygienic devices in and around the mouth. This paper aims to develop a TMI based on the glossokinetic potentials (GKPs), i.e. the electrical signals generated by the tongue when it touches the buccal walls. Ten participants were recruited for this research. The GKP patterns were classified by convolutional neural network (CNN) and support vector machine (SVM). It was observed that the CNN outperformed the SVM in individual and average scores for both raw and preprocessed datasets, reaching an accuracy of 97~99%. The CNN-based GKP processing method makes it easy to build a natural, appealing and robust TMI for the paralyzed. Being the first attempt to process GKPs with the CNN, our research offers an alternative to the traditional brain-computer interfaces (BCIs), which suffers from the instability and low signalto-noise ratio (SNR) of electroencephalography (EEG).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.