EEG-induced Fear-type Emotion Classification through Wavelet Packet Decomposition, Wavelet Entropy and SVM

Among the most significant characteristics of human beings is their ability to feel emotions. In recent years, human-machine interface (HM) research has centered on ways empower classification Mainly, human-computer interaction (HCI) concentrates methods that enable computers reveal emotional states humans. this research, an emotion detection system based visual IAPPS pictures through EMOTIV EPOC EEG signals was proposed. We employed acquired from channels (AF3, F7, F3, FC5, T7, P7, O1, O2, P8, T8, FC6, F4, F8, AF4) for individuals in a induced setting (IAPS fear and neutral aroused pictures). The wavelet packet transform (WPT) combined with entropy algorithm applied signals. values were extracted every two classes. Finally, these feature matrices fed into SVM (Support Vector Machine) type classifier generate model. Also, we evaluated proposed as area under ROC (Receiver Operating Characteristic) curve, or simply AUC (Area curve) utilized alternative single-number measure. Overall accuracy obtained at 91.0%. For classification, value given 0.97. calculations confirmed approaches are successful stimuli via acceptable.