Emotional Stress Recognition Using Electroencephalogram Signals Based on a Three-Dimensional Convolutional Gated Self-Attention Deep Neural Network
The brain is more sensitive to stress than other organs and can develop many diseases under excessive stress. In this study, we developed a method to improve the accuracy of emotional stress recognition using multi-channel electroencephalogram (EEG) signals. The method combines a three-dimensional (...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/21/11162 |
| _version_ | 1797469216264159232 |
|---|---|
| author | Hyoung-Gook Kim Dong-Ki Jeong Jin-Young Kim |
| author_facet | Hyoung-Gook Kim Dong-Ki Jeong Jin-Young Kim |
| author_sort | Hyoung-Gook Kim |
| collection | DOAJ |
| description | The brain is more sensitive to stress than other organs and can develop many diseases under excessive stress. In this study, we developed a method to improve the accuracy of emotional stress recognition using multi-channel electroencephalogram (EEG) signals. The method combines a three-dimensional (3D) convolutional neural network with an attention mechanism to build a 3D convolutional gated self-attention neural network. Initially, the EEG signal is decomposed into four frequency bands, and a 3D convolutional block is applied to each frequency band to obtain EEG spatiotemporal information. Subsequently, long-range dependencies and global information are learned by capturing prominent information from each frequency band via a gated self-attention mechanism block. Using frequency band mapping, complementary features are learned by connecting vectors from different frequency bands, which is reflected in the final attentional representation for stress recognition. Experiments conducted on three benchmark datasets for assessing the performance of emotional stress recognition indicate that the proposed method outperforms other conventional methods. The performance analysis of proposed methods confirms that EEG pattern analysis can be used for studying human brain activity and can accurately distinguish the state of stress. |
| first_indexed | 2024-03-09T19:17:13Z |
| format | Article |
| id | doaj.art-85483e635e1a4018b28b405661a2bf00 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T19:17:13Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-85483e635e1a4018b28b405661a2bf002023-11-24T03:39:09ZengMDPI AGApplied Sciences2076-34172022-11-0112211116210.3390/app122111162Emotional Stress Recognition Using Electroencephalogram Signals Based on a Three-Dimensional Convolutional Gated Self-Attention Deep Neural NetworkHyoung-Gook Kim0Dong-Ki Jeong1Jin-Young Kim2Department of Electronic Convergence Engineering, Kwangwoon University, 20 Gwangun-ro, Nowon-gu, Seoul 01897, KoreaDepartment of Electronic Convergence Engineering, Kwangwoon University, 20 Gwangun-ro, Nowon-gu, Seoul 01897, KoreaDepartment of ICT Convergence System Engineering, Chonnam National University, 77 Yongbong-ro, Buk-gu, Gwangju 61186, KoreaThe brain is more sensitive to stress than other organs and can develop many diseases under excessive stress. In this study, we developed a method to improve the accuracy of emotional stress recognition using multi-channel electroencephalogram (EEG) signals. The method combines a three-dimensional (3D) convolutional neural network with an attention mechanism to build a 3D convolutional gated self-attention neural network. Initially, the EEG signal is decomposed into four frequency bands, and a 3D convolutional block is applied to each frequency band to obtain EEG spatiotemporal information. Subsequently, long-range dependencies and global information are learned by capturing prominent information from each frequency band via a gated self-attention mechanism block. Using frequency band mapping, complementary features are learned by connecting vectors from different frequency bands, which is reflected in the final attentional representation for stress recognition. Experiments conducted on three benchmark datasets for assessing the performance of emotional stress recognition indicate that the proposed method outperforms other conventional methods. The performance analysis of proposed methods confirms that EEG pattern analysis can be used for studying human brain activity and can accurately distinguish the state of stress.https://www.mdpi.com/2076-3417/12/21/11162stress recognitionEEG3D convolutional neural networksself-attention |
| spellingShingle | Hyoung-Gook Kim Dong-Ki Jeong Jin-Young Kim Emotional Stress Recognition Using Electroencephalogram Signals Based on a Three-Dimensional Convolutional Gated Self-Attention Deep Neural Network Applied Sciences stress recognition EEG 3D convolutional neural networks self-attention |
| title | Emotional Stress Recognition Using Electroencephalogram Signals Based on a Three-Dimensional Convolutional Gated Self-Attention Deep Neural Network |
| title_full | Emotional Stress Recognition Using Electroencephalogram Signals Based on a Three-Dimensional Convolutional Gated Self-Attention Deep Neural Network |
| title_fullStr | Emotional Stress Recognition Using Electroencephalogram Signals Based on a Three-Dimensional Convolutional Gated Self-Attention Deep Neural Network |
| title_full_unstemmed | Emotional Stress Recognition Using Electroencephalogram Signals Based on a Three-Dimensional Convolutional Gated Self-Attention Deep Neural Network |
| title_short | Emotional Stress Recognition Using Electroencephalogram Signals Based on a Three-Dimensional Convolutional Gated Self-Attention Deep Neural Network |
| title_sort | emotional stress recognition using electroencephalogram signals based on a three dimensional convolutional gated self attention deep neural network |
| topic | stress recognition EEG 3D convolutional neural networks self-attention |
| url | https://www.mdpi.com/2076-3417/12/21/11162 |
| work_keys_str_mv | AT hyounggookkim emotionalstressrecognitionusingelectroencephalogramsignalsbasedonathreedimensionalconvolutionalgatedselfattentiondeepneuralnetwork AT dongkijeong emotionalstressrecognitionusingelectroencephalogramsignalsbasedonathreedimensionalconvolutionalgatedselfattentiondeepneuralnetwork AT jinyoungkim emotionalstressrecognitionusingelectroencephalogramsignalsbasedonathreedimensionalconvolutionalgatedselfattentiondeepneuralnetwork |