EEG Based Emotion Recognition with Convolutional Neural Networks

Abstract

The use of multichannel electroencephalography (EEG) signals has become increasingly common in emotion recognition. However, studies have shown that due to the complexity of EEG signals, even the signals recorded from the same person may be disturbed. Therefore, EEG signals from the human brain need to be accurately and consistently analyzed and processed. With the method based on the Welch power spectral density estimation and a convolutional neural network, a high degree of classification accuracy was obtained on the SEED EEG dataset.