A Brain Network Analysis-Based Double Way Deep Neural Network for Emotion Recognition
Constructing reliable and effective models to recognize human emotional states has become an important issue in recent years. In this article, we propose a double way deep residual neural network combined with brain network analysis, which enables the classification of multiple emotional states. To...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10016299/ |
| _version_ | 1827926994187190272 |
|---|---|
| author | Weixin Niu Chao Ma Xinlin Sun Mengyu Li Zhongke Gao |
| author_facet | Weixin Niu Chao Ma Xinlin Sun Mengyu Li Zhongke Gao |
| author_sort | Weixin Niu |
| collection | DOAJ |
| description | Constructing reliable and effective models to recognize human emotional states has become an important issue in recent years. In this article, we propose a double way deep residual neural network combined with brain network analysis, which enables the classification of multiple emotional states. To begin with, we transform the emotional EEG signals into five frequency bands by wavelet transform and construct brain networks by inter-channel correlation coefficients. These brain networks are then fed into a subsequent deep neural network block which contains several modules with residual connection and enhanced by channel attention mechanism and spatial attention mechanism. In the second way of the model, we feed the emotional EEG signals directly into another deep neural network block to extract temporal features. At the end of the two ways, the features are concatenated for classification. To verify the effectiveness of our proposed model, we carried out a series of experiments to collect emotional EEG from eight subjects. The average accuracy of the proposed model on our emotional dataset is 94.57%. In addition, the evaluation results on public databases SEED and SEED-IV are 94.55% and 78.91%, respectively, demonstrating the superiority of our model in emotion recognition tasks. |
| first_indexed | 2024-03-13T05:45:42Z |
| format | Article |
| id | doaj.art-528305fcf0f24436961b968dd55bd22e |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-13T05:45:42Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-528305fcf0f24436961b968dd55bd22e2023-06-13T20:10:30ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102023-01-013191792510.1109/TNSRE.2023.323643410016299A Brain Network Analysis-Based Double Way Deep Neural Network for Emotion RecognitionWeixin Niu0https://orcid.org/0000-0003-0630-178XChao Ma1https://orcid.org/0000-0001-6981-0165Xinlin Sun2https://orcid.org/0000-0002-5257-6285Mengyu Li3https://orcid.org/0000-0002-3591-5898Zhongke Gao4https://orcid.org/0000-0002-9551-202XSchool of Electrical and Information Engineering, Tianjin University, Tianjin, ChinaSchool of Electrical and Information Engineering, Tianjin University, Tianjin, ChinaSchool of Electrical and Information Engineering, Tianjin University, Tianjin, ChinaSchool of Electrical and Information Engineering, Tianjin University, Tianjin, ChinaSchool of Electrical and Information Engineering, Tianjin University, Tianjin, ChinaConstructing reliable and effective models to recognize human emotional states has become an important issue in recent years. In this article, we propose a double way deep residual neural network combined with brain network analysis, which enables the classification of multiple emotional states. To begin with, we transform the emotional EEG signals into five frequency bands by wavelet transform and construct brain networks by inter-channel correlation coefficients. These brain networks are then fed into a subsequent deep neural network block which contains several modules with residual connection and enhanced by channel attention mechanism and spatial attention mechanism. In the second way of the model, we feed the emotional EEG signals directly into another deep neural network block to extract temporal features. At the end of the two ways, the features are concatenated for classification. To verify the effectiveness of our proposed model, we carried out a series of experiments to collect emotional EEG from eight subjects. The average accuracy of the proposed model on our emotional dataset is 94.57%. In addition, the evaluation results on public databases SEED and SEED-IV are 94.55% and 78.91%, respectively, demonstrating the superiority of our model in emotion recognition tasks.https://ieeexplore.ieee.org/document/10016299/Brain networkdeep residual neural networkelectroencephalogram (EEG)emotion recognitionspearman correlation coefficient |
| spellingShingle | Weixin Niu Chao Ma Xinlin Sun Mengyu Li Zhongke Gao A Brain Network Analysis-Based Double Way Deep Neural Network for Emotion Recognition IEEE Transactions on Neural Systems and Rehabilitation Engineering Brain network deep residual neural network electroencephalogram (EEG) emotion recognition spearman correlation coefficient |
| title | A Brain Network Analysis-Based Double Way Deep Neural Network for Emotion Recognition |
| title_full | A Brain Network Analysis-Based Double Way Deep Neural Network for Emotion Recognition |
| title_fullStr | A Brain Network Analysis-Based Double Way Deep Neural Network for Emotion Recognition |
| title_full_unstemmed | A Brain Network Analysis-Based Double Way Deep Neural Network for Emotion Recognition |
| title_short | A Brain Network Analysis-Based Double Way Deep Neural Network for Emotion Recognition |
| title_sort | brain network analysis based double way deep neural network for emotion recognition |
| topic | Brain network deep residual neural network electroencephalogram (EEG) emotion recognition spearman correlation coefficient |
| url | https://ieeexplore.ieee.org/document/10016299/ |
| work_keys_str_mv | AT weixinniu abrainnetworkanalysisbaseddoublewaydeepneuralnetworkforemotionrecognition AT chaoma abrainnetworkanalysisbaseddoublewaydeepneuralnetworkforemotionrecognition AT xinlinsun abrainnetworkanalysisbaseddoublewaydeepneuralnetworkforemotionrecognition AT mengyuli abrainnetworkanalysisbaseddoublewaydeepneuralnetworkforemotionrecognition AT zhongkegao abrainnetworkanalysisbaseddoublewaydeepneuralnetworkforemotionrecognition AT weixinniu brainnetworkanalysisbaseddoublewaydeepneuralnetworkforemotionrecognition AT chaoma brainnetworkanalysisbaseddoublewaydeepneuralnetworkforemotionrecognition AT xinlinsun brainnetworkanalysisbaseddoublewaydeepneuralnetworkforemotionrecognition AT mengyuli brainnetworkanalysisbaseddoublewaydeepneuralnetworkforemotionrecognition AT zhongkegao brainnetworkanalysisbaseddoublewaydeepneuralnetworkforemotionrecognition |