Human emotion classification using wavelet transform and KNN

Emotion is one of the most important features of humans. Without the ability of emotions processing, computers and robots cannot communicate with human in natural way. In this paper we presented the classification of human emotions using Electroencephalogram (EEG) signals. EEG signals are collected from 20 subjects through 62 active electrodes, which are placed over the entire scalp based on International 10-10 system. An audio-visual (video clips) stimuli based protocol has been designed for evoking the discrete emotions. The raw EEG signals are preprocessed through Surface Laplacian filtering method and decomposed into five different EEG frequency bands (delta, theta, alpha, beta and gamma) using Wavelet Transform (WT). We have considered three different wavelet functions namely: “db4”, “db8”, “sym8” and “coif5” for extracting the statistical features from the preprocessed signal. In this work, we have investigated the efficacy of emotion classification for two different set of EEG channels (62 channels & 24 channels). The validation of statistical features is performed using 5 fold cross validation and classified by using linear non-linear (KNN - K Nearest Neighbor) classifier. KNN gives a maximum average classification rate of 82.87 % on 62 channels and 78.57% on 24 channels, respectively. Finally we present the average classification accuracy and individual classification accuracy of KNN for justifying the performance of our emotion recognition system.