Emotion Classification from Multi-Band Electroencephalogram Data Using Dynamic Simplifying Graph Convolutional Network and Channel Style Recalibration Module
Because of its ability to objectively reflect people’s emotional states, electroencephalogram (EEG) has been attracting increasing research attention for emotion classification. The classification method based on spatial-domain analysis is one of the research hotspots. However, most previous studies...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/4/1917 |
| _version_ | 1797618315098587136 |
|---|---|
| author | Xiaoliang Zhu Gendong Liu Liang Zhao Wenting Rong Junyi Sun Ran Liu |
| author_facet | Xiaoliang Zhu Gendong Liu Liang Zhao Wenting Rong Junyi Sun Ran Liu |
| author_sort | Xiaoliang Zhu |
| collection | DOAJ |
| description | Because of its ability to objectively reflect people’s emotional states, electroencephalogram (EEG) has been attracting increasing research attention for emotion classification. The classification method based on spatial-domain analysis is one of the research hotspots. However, most previous studies ignored the complementarity of information between different frequency bands, and the information in a single frequency band is not fully mined, which increases the computational time and the difficulty of improving classification accuracy. To address the above problems, this study proposes an emotion classification method based on dynamic simplifying graph convolutional (SGC) networks and a style recalibration module (SRM) for channels, termed SGC-SRM, with multi-band EEG data as input. Specifically, first, the graph structure is constructed using the differential entropy characteristics of each sub-band and the internal relationship between different channels is dynamically learned through SGC networks. Second, a convolution layer based on the SRM is introduced to recalibrate channel features to extract more emotion-related features. Third, the extracted sub-band features are fused at the feature level and classified. In addition, to reduce the redundant information between EEG channels and the computational time, (1) we adopt only 12 channels that are suitable for emotion classification to optimize the recognition algorithm, which can save approximately 90.5% of the time cost compared with using all channels; (2) we adopt information in the θ, α, β, and γ bands, consequently saving 23.3% of the time consumed compared with that in the full bands while maintaining almost the same level of classification accuracy. Finally, a subject-independent experiment is conducted on the public SEED dataset using the leave-one-subject-out cross-validation strategy. According to experimental results, SGC-SRM improves classification accuracy by 5.51–15.43% compared with existing methods. |
| first_indexed | 2024-03-11T08:11:24Z |
| format | Article |
| id | doaj.art-f351c72d002f4fd3a81afa37265efcfa |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T08:11:24Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f351c72d002f4fd3a81afa37265efcfa2023-11-16T23:07:51ZengMDPI AGSensors1424-82202023-02-01234191710.3390/s23041917Emotion Classification from Multi-Band Electroencephalogram Data Using Dynamic Simplifying Graph Convolutional Network and Channel Style Recalibration ModuleXiaoliang Zhu0Gendong Liu1Liang Zhao2Wenting Rong3Junyi Sun4Ran Liu5National Engineering Research Center of Educational Big Data, Central China Normal University, Wuhan 430079, ChinaNational Engineering Research Center of Educational Big Data, Central China Normal University, Wuhan 430079, ChinaNational Engineering Research Center of Educational Big Data, Central China Normal University, Wuhan 430079, ChinaNational Engineering Research Center of Educational Big Data, Central China Normal University, Wuhan 430079, ChinaNational Engineering Research Center of Educational Big Data, Central China Normal University, Wuhan 430079, ChinaEngineering Product Development Pillar, Singapore University of Technology and Design, Singapore 487372, SingaporeBecause of its ability to objectively reflect people’s emotional states, electroencephalogram (EEG) has been attracting increasing research attention for emotion classification. The classification method based on spatial-domain analysis is one of the research hotspots. However, most previous studies ignored the complementarity of information between different frequency bands, and the information in a single frequency band is not fully mined, which increases the computational time and the difficulty of improving classification accuracy. To address the above problems, this study proposes an emotion classification method based on dynamic simplifying graph convolutional (SGC) networks and a style recalibration module (SRM) for channels, termed SGC-SRM, with multi-band EEG data as input. Specifically, first, the graph structure is constructed using the differential entropy characteristics of each sub-band and the internal relationship between different channels is dynamically learned through SGC networks. Second, a convolution layer based on the SRM is introduced to recalibrate channel features to extract more emotion-related features. Third, the extracted sub-band features are fused at the feature level and classified. In addition, to reduce the redundant information between EEG channels and the computational time, (1) we adopt only 12 channels that are suitable for emotion classification to optimize the recognition algorithm, which can save approximately 90.5% of the time cost compared with using all channels; (2) we adopt information in the θ, α, β, and γ bands, consequently saving 23.3% of the time consumed compared with that in the full bands while maintaining almost the same level of classification accuracy. Finally, a subject-independent experiment is conducted on the public SEED dataset using the leave-one-subject-out cross-validation strategy. According to experimental results, SGC-SRM improves classification accuracy by 5.51–15.43% compared with existing methods.https://www.mdpi.com/1424-8220/23/4/1917EEGemotion classificationgraph neural networkSRMchannel selection |
| spellingShingle | Xiaoliang Zhu Gendong Liu Liang Zhao Wenting Rong Junyi Sun Ran Liu Emotion Classification from Multi-Band Electroencephalogram Data Using Dynamic Simplifying Graph Convolutional Network and Channel Style Recalibration Module Sensors EEG emotion classification graph neural network SRM channel selection |
| title | Emotion Classification from Multi-Band Electroencephalogram Data Using Dynamic Simplifying Graph Convolutional Network and Channel Style Recalibration Module |
| title_full | Emotion Classification from Multi-Band Electroencephalogram Data Using Dynamic Simplifying Graph Convolutional Network and Channel Style Recalibration Module |
| title_fullStr | Emotion Classification from Multi-Band Electroencephalogram Data Using Dynamic Simplifying Graph Convolutional Network and Channel Style Recalibration Module |
| title_full_unstemmed | Emotion Classification from Multi-Band Electroencephalogram Data Using Dynamic Simplifying Graph Convolutional Network and Channel Style Recalibration Module |
| title_short | Emotion Classification from Multi-Band Electroencephalogram Data Using Dynamic Simplifying Graph Convolutional Network and Channel Style Recalibration Module |
| title_sort | emotion classification from multi band electroencephalogram data using dynamic simplifying graph convolutional network and channel style recalibration module |
| topic | EEG emotion classification graph neural network SRM channel selection |
| url | https://www.mdpi.com/1424-8220/23/4/1917 |
| work_keys_str_mv | AT xiaoliangzhu emotionclassificationfrommultibandelectroencephalogramdatausingdynamicsimplifyinggraphconvolutionalnetworkandchannelstylerecalibrationmodule AT gendongliu emotionclassificationfrommultibandelectroencephalogramdatausingdynamicsimplifyinggraphconvolutionalnetworkandchannelstylerecalibrationmodule AT liangzhao emotionclassificationfrommultibandelectroencephalogramdatausingdynamicsimplifyinggraphconvolutionalnetworkandchannelstylerecalibrationmodule AT wentingrong emotionclassificationfrommultibandelectroencephalogramdatausingdynamicsimplifyinggraphconvolutionalnetworkandchannelstylerecalibrationmodule AT junyisun emotionclassificationfrommultibandelectroencephalogramdatausingdynamicsimplifyinggraphconvolutionalnetworkandchannelstylerecalibrationmodule AT ranliu emotionclassificationfrommultibandelectroencephalogramdatausingdynamicsimplifyinggraphconvolutionalnetworkandchannelstylerecalibrationmodule |