The research described herein was undertaken to develop and test a novel tongue interface based on classification of tongue motions from the surface electromyography (EMG) signals of the suprahyoid muscles detected at the underside of the jaw. The EMG signals are measured via 22 active surface electrodes mounted onto a special flexible boomerang-shaped base. Because of the sensor's shape and flexibility, it can adapt to the underjaw skin contour. Tongue motion classification was achieved using a support vector machine (SVM) algorithm for pattern recognition where the root mean square (RMS) features and cepstrum coefficients (CC) features of the EMG signals were analyzed. The effectiveness of the approach was verified with a test for the classification of six tongue motions conducted with a group of five healthy adult volunteer subjects who had normal motor tongue functions. Results showed that the system classified all six tongue motions with high accuracy of 95.1 ± 1.9 %. The proposed method for control of assistive devices was evaluated using a test in which a computer simulation model of an electric wheelchair was controlled using six tongue motions. This interface system, which weighs only 13.6 g and which has a simple appearance, requires no installation of any sensor into the mouth cavity. Therefore, it does not hinder user activities such as swallowing, chewing, or talking. The number of tongue motions is sufficient for the control of most assistive devices.

In this study, we introduce a real-time method for tongue movement estimation based on the analysis of the surface electromyography (EMG) signals from the suprahyoid muscles, which usual function is to open the mouth and to control the position of the hyoid, the base of the tongue. Nine surface electrodes were affixed to the underside of the jaw and their signals were processed via multi-channel EMG system. The features of the EMG signals were extracted by using a root mean square (RMS) method. The dimension of the variables was reduced additionally from 108 to 10 by applying the Principal Component Analysis (PCA). The feature quantities of the reduced dimension set were associated with the tongue movements by using an artificial neural network. Results showed that the proposed method allows precise estimation of the tongue movements. For the test data set, the identification rate was greater than 97 % and the response time was less than 0.7 s. The proposed method could be implemented to facilitate novel approaches for alternative communication and control of assistive technology for supporting the independent living of people with severe quadriplegia.

In this paper, we introduce a new tongue-training system that can be used for improvement of the tongue's range of motion and muscle strength after dysphagia. The training process is organized in game-like manner. Initially, we analyzed surface electromyography (EMG) signals of the suprahyoid muscles of five subjects during tongue-training motions. This test revealed that four types tongue training motions and a swallowing motion could be classified with 93.5% accuracy. Recognized EMG signals during tongue motions were designed to allow control of a mouse cursor via intentional tongue motions. Results demonstrated that simple PC games could be played by tongue motions, achieving in this way efficient, enjoyable and pleasant tongue training. Using the proposed method, dysphagia patients can choose games that suit their preferences and/or state of mind. It is expected that the proposed system will be an efficient tool for long-term tongue motor training and maintaining patients' motivation.

No abstract