Depression Assessment Method: An EEG Emotion Recognition Framework Based on Spatiotemporal Neural Network
The main characteristic of depression is emotional dysfunction, manifested by increased levels of negative emotions and decreased levels of positive emotions. Therefore, accurate emotion recognition is an effective way to assess depression. Among the various signals used for emotion recognition, ele...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-03-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2021.837149/full |
| _version_ | 1819158864119988224 |
|---|---|
| author | Hongli Chang Hongli Chang Yuan Zong Wenming Zheng Chuangao Tang Jie Zhu Jie Zhu Xuejun Li |
| author_facet | Hongli Chang Hongli Chang Yuan Zong Wenming Zheng Chuangao Tang Jie Zhu Jie Zhu Xuejun Li |
| author_sort | Hongli Chang |
| collection | DOAJ |
| description | The main characteristic of depression is emotional dysfunction, manifested by increased levels of negative emotions and decreased levels of positive emotions. Therefore, accurate emotion recognition is an effective way to assess depression. Among the various signals used for emotion recognition, electroencephalogram (EEG) signal has attracted widespread attention due to its multiple advantages, such as rich spatiotemporal information in multi-channel EEG signals. First, we use filtering and Euclidean alignment for data preprocessing. In the feature extraction, we use short-time Fourier transform and Hilbert–Huang transform to extract time-frequency features, and convolutional neural networks to extract spatial features. Finally, bi-directional long short-term memory explored the timing relationship. Before performing the convolution operation, according to the unique topology of the EEG channel, the EEG features are converted into 3D tensors. This study has achieved good results on two emotion databases: SEED and Emotional BCI of 2020 WORLD ROBOT COMPETITION. We applied this method to the recognition of depression based on EEG and achieved a recognition rate of more than 70% under the five-fold cross-validation. In addition, the subject-independent protocol on SEED data has achieved a state-of-the-art recognition rate, which exceeds the existing research methods. We propose a novel EEG emotion recognition framework for depression detection, which provides a robust algorithm for real-time clinical depression detection based on EEG. |
| first_indexed | 2024-12-22T16:31:26Z |
| format | Article |
| id | doaj.art-2db691ef16684fe1b7103a17b103e765 |
| institution | Directory Open Access Journal |
| issn | 1664-0640 |
| language | English |
| last_indexed | 2024-12-22T16:31:26Z |
| publishDate | 2022-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj.art-2db691ef16684fe1b7103a17b103e7652022-12-21T18:20:03ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402022-03-011210.3389/fpsyt.2021.837149837149Depression Assessment Method: An EEG Emotion Recognition Framework Based on Spatiotemporal Neural NetworkHongli Chang0Hongli Chang1Yuan Zong2Wenming Zheng3Chuangao Tang4Jie Zhu5Jie Zhu6Xuejun Li7Key Laboratory of Child Development and Learning Science, Ministry of Education, Southeast University, Nanjing, ChinaSchool of Information Science and Engineering, Southeast University, Nanjing, ChinaKey Laboratory of Child Development and Learning Science, Ministry of Education, Southeast University, Nanjing, ChinaKey Laboratory of Child Development and Learning Science, Ministry of Education, Southeast University, Nanjing, ChinaKey Laboratory of Child Development and Learning Science, Ministry of Education, Southeast University, Nanjing, ChinaKey Laboratory of Child Development and Learning Science, Ministry of Education, Southeast University, Nanjing, ChinaSchool of Information Science and Engineering, Southeast University, Nanjing, ChinaKey Laboratory of Child Development and Learning Science, Ministry of Education, Southeast University, Nanjing, ChinaThe main characteristic of depression is emotional dysfunction, manifested by increased levels of negative emotions and decreased levels of positive emotions. Therefore, accurate emotion recognition is an effective way to assess depression. Among the various signals used for emotion recognition, electroencephalogram (EEG) signal has attracted widespread attention due to its multiple advantages, such as rich spatiotemporal information in multi-channel EEG signals. First, we use filtering and Euclidean alignment for data preprocessing. In the feature extraction, we use short-time Fourier transform and Hilbert–Huang transform to extract time-frequency features, and convolutional neural networks to extract spatial features. Finally, bi-directional long short-term memory explored the timing relationship. Before performing the convolution operation, according to the unique topology of the EEG channel, the EEG features are converted into 3D tensors. This study has achieved good results on two emotion databases: SEED and Emotional BCI of 2020 WORLD ROBOT COMPETITION. We applied this method to the recognition of depression based on EEG and achieved a recognition rate of more than 70% under the five-fold cross-validation. In addition, the subject-independent protocol on SEED data has achieved a state-of-the-art recognition rate, which exceeds the existing research methods. We propose a novel EEG emotion recognition framework for depression detection, which provides a robust algorithm for real-time clinical depression detection based on EEG.https://www.frontiersin.org/articles/10.3389/fpsyt.2021.837149/fulldepressionemotion recognitionelectroencephalogram (EEG)convolutional neural network (CNN)long-short term memory network (LSTM) |
| spellingShingle | Hongli Chang Hongli Chang Yuan Zong Wenming Zheng Chuangao Tang Jie Zhu Jie Zhu Xuejun Li Depression Assessment Method: An EEG Emotion Recognition Framework Based on Spatiotemporal Neural Network Frontiers in Psychiatry depression emotion recognition electroencephalogram (EEG) convolutional neural network (CNN) long-short term memory network (LSTM) |
| title | Depression Assessment Method: An EEG Emotion Recognition Framework Based on Spatiotemporal Neural Network |
| title_full | Depression Assessment Method: An EEG Emotion Recognition Framework Based on Spatiotemporal Neural Network |
| title_fullStr | Depression Assessment Method: An EEG Emotion Recognition Framework Based on Spatiotemporal Neural Network |
| title_full_unstemmed | Depression Assessment Method: An EEG Emotion Recognition Framework Based on Spatiotemporal Neural Network |
| title_short | Depression Assessment Method: An EEG Emotion Recognition Framework Based on Spatiotemporal Neural Network |
| title_sort | depression assessment method an eeg emotion recognition framework based on spatiotemporal neural network |
| topic | depression emotion recognition electroencephalogram (EEG) convolutional neural network (CNN) long-short term memory network (LSTM) |
| url | https://www.frontiersin.org/articles/10.3389/fpsyt.2021.837149/full |
| work_keys_str_mv | AT honglichang depressionassessmentmethodaneegemotionrecognitionframeworkbasedonspatiotemporalneuralnetwork AT honglichang depressionassessmentmethodaneegemotionrecognitionframeworkbasedonspatiotemporalneuralnetwork AT yuanzong depressionassessmentmethodaneegemotionrecognitionframeworkbasedonspatiotemporalneuralnetwork AT wenmingzheng depressionassessmentmethodaneegemotionrecognitionframeworkbasedonspatiotemporalneuralnetwork AT chuangaotang depressionassessmentmethodaneegemotionrecognitionframeworkbasedonspatiotemporalneuralnetwork AT jiezhu depressionassessmentmethodaneegemotionrecognitionframeworkbasedonspatiotemporalneuralnetwork AT jiezhu depressionassessmentmethodaneegemotionrecognitionframeworkbasedonspatiotemporalneuralnetwork AT xuejunli depressionassessmentmethodaneegemotionrecognitionframeworkbasedonspatiotemporalneuralnetwork |