论文部分内容阅读
本文旨在结合小波分析与经验模态分解(EMD),充分提取音乐干预下的脑电(EEG)信号特征参数,提高情绪状态评估的分类准确率与可靠性,以期为辅助音乐治疗提供支持与帮助。采用音乐诱发情绪的多通道标准情感数据库(DEAP)中的数据,利用小波变换提取出额区(F3,F4)、颞区(T7,T8)和中央(C3,C4)通道的α波、β波以及θ波节律;对提取的脑电节律进行EMD以获得固有模态函数(IMF)分量,再进一步提取脑电节律波的IMF分量平均能量和幅度差特征值,即每种节律波中包含3个平均能量特征和2个幅度差特征值,以达到充分提取EEG特征信息的目的;最后基于支持向量机分类器实现情感状态评估。结果表明,利用该算法可以使无情绪、积极情绪、消极情绪之间分类最优正确率达到100%,使得积极与消极情绪之间的识别率提升10%左右,可以实现无情绪与积极、无情绪与消极情绪等情感状态的有效评估。处于不同情感状态下,音乐治疗效果差异较大,提高情感状态评估的分类正确率,将帮助提高音乐治疗的效果,更好地为音乐治疗提供支持。
The purpose of this paper is to combine the wavelet analysis and Empirical Mode Decomposition (EMD) to extract the characteristics of EEG signals under music intervention and to improve the classification accuracy and reliability of emotional state evaluation, in order to provide support and assistance to the music therapy help. Using the data of multi-channel music emotion-induced standard affective database (DEAP), wavelet transform was used to extract the α wave of β, F4, T7 and T8 and C3, C4 channels Wave and theta wave rhythm. The extracted EEG rhythms are subjected to EMD to obtain the intrinsic mode function (IMF) components, and then the average energy and amplitude difference eigenvalues of the IMF components of the EEG rhythms are further extracted, that is, each rhythm wave contains Three average energy features and two amplitude difference eigenvalues in order to achieve the purpose of fully extracting EEG feature information. Finally, based on the support vector machine classifier to achieve emotional state assessment. The results show that this algorithm can make the classification accuracy of no mood, positive emotion and negative emotion reach 100%, so that the recognition rate between positive and negative emotion can be increased by about 10%, and there is no emotion and positive emotion. Emotional and negative emotions and other emotional state of the effective assessment. Under different emotional states, the effect of music therapy is quite different, and improving the correct classification rate of emotional state evaluation will help improve the effect of music therapy and provide better support for music therapy.