Research On EEG Emotion Recognition Methods Based On Convolutional Neural Networks

Emotion is a state that integrates human feelings,thoughts,and behaviors and plays an important role in human communication,human decision-making and cognitive processes.With the development of machine learning technology and in-depth understanding of emotions,automatic emotion recognition methods and systems have developed into research hotspots.Electroencephalographic(EEG),as an important way of expressing emotions,can represent the internal emotional state and is not affected by subjective human control.As emotion-related processes will involve changes in brain activity,they can be assessed by non-invasive and low-cost scalp EEG recordings,thereby providing a reasonable method of identifying emotions.The paper uses convolutional neural network and its evolution model to identify user emotions through EEG signals.The main innovative points and contributions of the paper are shown as follows:(1)The thesis proposes an emotion recognition method based on 3D feature maps and convolutional neural networks(named 3DCNER).Firstly,EEG data is calibrated with 3s baseline data and divided into segments with 6s time window,and then the wavelet energy ratio,wavelet entropy of 5 rhythms(?,?,?,?,? frequency band)and approximate entropy are extracted from each segment.Secondly,the extracted features are arranged according to EEG channels mapping,and then each segment is converted into a 3D feature map,which is used to simulate the relative position of electrode channels on the scalp and provides spatial information for emotion recognition.Finally,a convolutional neural networks framework is designed to learn local connections among electrode channels from 3D feature maps and to improve the accuracy of emotion recognition.The experimental results on DEAP data set demonstrate that the proposed method has better classification accuracy than the state-of-the-art methods.We attained the average classification accuracy of 93.61% and 94.04% for valence and arousal in subject-dependent experiments while 83.83% and 84.53% in subject-independent experiments.(2)The thesis proposes a novel emotion recognition method based on a novel deep learning model(ERDL).Firstly,EEG data is calibrated by 3s baseline data and divided into segments with 6s time window,and then differential entropy is extracted from each segment to construct feature cube.Secondly,the feature cube of each segment serves as input of the novel deep learning model which fuses graph convolutional neural network(GCNN)and long-short term memories neural networks(LSTM).In the fusion model,multiple GCNNs are applied to extract graph domain features while LSTM cells are used to memorize the change of the relationship between two channels within a specific time and extract temporal features,and Dense layer is used to attain the emotion classification results.At last,we conducted extensive experiments on DEAP dataset and experimental results demonstrate that the proposed method has better classification results than the state-of-the-art methods.We attained the average classification accuracy of 90.45% and 90.60%for valence and arousal in subject-dependent experiments while 84.81% and 85.27% in subject-independent experiments.In emotion recognition,compared with the traditional classification model,the recognition accuracy of the two deep learning models in this paper is higher than that of the traditional classification model,that is,the fitting of the deep learning model is higher than that of the traditional classification model.