The Research Of Affect Recognition Based On EMG Signal

At present, emotion recognition based on physiological signals has become an important research topic in the field of affective computing. In the 1990s, Professor Picard, member of the Affective Computing Group in MIT Media Lab, took the lead to extract features from physiological signals to recognize affect states and prove that it is feasible to recognize affect states using physiological signalsAs is well known, EMG signal is the bioelectricity signal produced by Neuromuscular during the independent movement of human body. EMG represents the comprehensive performance of action potential of muscle group on skin surface in both time and space. EMG signal reflects the states of nerve and muscle, and shows the mood changes in some respects. There is great significance to apply EMG signals to affect recognition. This study is on the affect recognition based on electromyography (EMG) signal.The following work is discussed in this paper:(1) Data acquisition is the first step of the whole study. Whether the target emotion is elicited is the key issue to gain corresponding affective data, so data acquisition is as important as feature extraction and selection. EMG signals from multiple subjects were collected when film clips were shown to them. And the corresponding original data were stored in the database.(2) Then wavelet transform method was used for de-noised effective EMG signals, after noise reduction, statistical features in time-domain were obtained, Daubechies5 wavelet with orthogonality and compact support was adopted as basic function to do 5-layer decomposition of EMG signal after noise, then 21 statistical features of each layer's detail coefficients were extracted. So we can obtain 126 original features in total.(3) However, not all features make contributes to emotion recognition, so it is necessary to find affective features from them, namely feature selection. Feature selection in emotion recognition is a combinatorial optimization problem thus a NP problem. So an effective intelligent optimization algorithm is advisable to find a satisfying solution to the problem. Then feature selection was done using the Tabu search (TS) algorithm and the Sequential Backward Selection (SBS) combined with Fisger classifier.(4) EMG signals were used to recognize 6 kinds of emotion (happiness, surprise, disgust, grief, anger and fear). According to the characteristics of EMG signals, wavelet transform was used for noise reduction and feature extraction, and TS algorithm combined with backward selection algorithm for feature selection. The stimulation result shows that obtaining feature fusion related to emotions from EMG signals is totally doable. While selecting features, we used backward selection algorithm to optimize TS algorithm, therefore, feature-dimension was reduced, good recognition effect was obtained, and the problem of TS algorithm's dependency on the initial solution was also solved.