RESUMO
In the present paper,wavelet transform and empirical mode decomposition(EMD)are combined to extracted the features of electroencephalogram(EEG)signal with music intervention,and to achieve a better classification accuracy rate and reliability in emotional assessment in order to provide a support for music therapy.The data were from Database for Emotion Analysis using Physiological Signals(DEAP).Based on wavelet transformα,ßandθrhythms were extracted at frontal(F3,F4),temporal(T7,T8)and central regions(C3,C4).Based on the EMD,the intrinsic mode function(IMF)was analyzed and extracted.Furthermore,average energy and amplitude difference of IMF were analyzed and obtained.The support vector machine was used to assess the state of emotion in order to support music therapy.According to this algorithm,the classification accuracy rate could reach 100% between no emotions,positive emotions and negative emotions,which made a 10%improvement between positive and negative emotion recognition.Effective evaluation result between positive and negative emotions was achieved.The states of emotion would influence the effect of music therapy,undoubtedly,the classification accuracy rate increasing of emotional assessment will further help improve the effect of music therapy and provide a better support to the therapy.