Background: Electromyography (EMG) is the study of muscle function through the inquiry of electrical signals that the muscles emanate. EMG signals collected from the surface of the skin (Surface Electromyogram: sEMG) can be used in different applications such as recognizing musculoskeletal neural based patterns intercepted for hand prosthesis movements. Current systems designed for controlling the prosthetic hands either have limited functions or can only be used to perform simple movements or use excessive amount of electrodes in order to achieve acceptable results. In an attempt to overcome these problems we have proposed an intelligent system to recognize hand movements and have provided a user assessment routine to evaluate the correctness of executed movements.
Methods: We propose to use an intelligent approach based on adaptive neuro-fuzzy inference system (ANFIS) integrated with a real-time learning scheme to identify hand motion commands. For this purpose and to consider the effect of user evaluation on recognizing hand movements, vision feedback is applied to increase the capability of our system. By using this scheme the user may assess the correctness of the performed hand movement. In this work a hybrid method for training fuzzy system, consisting of back-propagation (BP) and least mean square (LMS) is utilized. Also in order to optimize the number of fuzzy rules, a subtractive clustering algorithm has been developed. To design an effective system, we consider a conventional scheme of EMG pattern recognition system. To design this system we propose to use two different sets of EMG features, namely time domain (TD) and time-frequency representation (TFR). Also in order to decrease the undesirable effects of the dimension of these feature sets, principle component analysis (PCA) is utilized.
Results: In this study, the myoelectric signals considered for classification consists of six unique hand movements. Features chosen for EMG signal are time and time-frequency domain. In this work we demonstrate the capability of an EMG pattern recognition system using ANFIS as classifier with a real-time learning method. Our results reveal that the utilized real-time ANFIS approach along with the user evaluation provides a 96.7% average accuracy. This rate is superior to the previously reported result utilizing artificial neural networks (ANN) real-time method 1.
Conclusion: This study shows that ANFIS real-time learning method coupled with mixed time and time-frequency features as EMG features can provide acceptable results for designing sEMG pattern recognition system suitable for hand prosthesis control.