EEG-based emotion recognition using regularized graph neural networks
Electroencephalography (EEG) measures the neuronal activities in different brain regions via electrodes. Many existing studies on EEG-based emotion recognition do not fully exploit the topology of EEG channels. In this paper, we propose a regularized graph neural network (RGNN) for EEG-based emot...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/152723 |
| _version_ | 1826114606543667200 |
|---|---|
| author | Zhong, Peixiang Wang, Di Miao, Chunyan |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Zhong, Peixiang Wang, Di Miao, Chunyan |
| author_sort | Zhong, Peixiang |
| collection | NTU |
| description | Electroencephalography (EEG) measures the neuronal activities in different
brain regions via electrodes. Many existing studies on EEG-based emotion
recognition do not fully exploit the topology of EEG channels. In this paper,
we propose a regularized graph neural network (RGNN) for EEG-based emotion
recognition. RGNN considers the biological topology among different brain
regions to capture both local and global relations among different EEG
channels. Specifically, we model the inter-channel relations in EEG signals via
an adjacency matrix in a graph neural network where the connection and
sparseness of the adjacency matrix are inspired by neuroscience theories of
human brain organization. In addition, we propose two regularizers, namely
node-wise domain adversarial training (NodeDAT) and emotion-aware distribution
learning (EmotionDL), to better handle cross-subject EEG variations and noisy
labels, respectively. Extensive experiments on two public datasets, SEED and
SEED-IV, demonstrate the superior performance of our model than
state-of-the-art models in most experimental settings. Moreover, ablation
studies show that the proposed adjacency matrix and two regularizers contribute
consistent and significant gain to the performance of our RGNN model. Finally,
investigations on the neuronal activities reveal important brain regions and
inter-channel relations for EEG-based emotion recognition. |
| first_indexed | 2024-10-01T03:41:51Z |
| format | Journal Article |
| id | ntu-10356/152723 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:41:51Z |
| publishDate | 2021 |
| record_format | dspace |
| spelling | ntu-10356/1527232021-12-09T08:22:12Z EEG-based emotion recognition using regularized graph neural networks Zhong, Peixiang Wang, Di Miao, Chunyan School of Computer Science and Engineering Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY) Alibaba-NTU Singapore Joint Research Institute Engineering::Computer science and engineering Affective Computing Electroencephalography Electroencephalography (EEG) measures the neuronal activities in different brain regions via electrodes. Many existing studies on EEG-based emotion recognition do not fully exploit the topology of EEG channels. In this paper, we propose a regularized graph neural network (RGNN) for EEG-based emotion recognition. RGNN considers the biological topology among different brain regions to capture both local and global relations among different EEG channels. Specifically, we model the inter-channel relations in EEG signals via an adjacency matrix in a graph neural network where the connection and sparseness of the adjacency matrix are inspired by neuroscience theories of human brain organization. In addition, we propose two regularizers, namely node-wise domain adversarial training (NodeDAT) and emotion-aware distribution learning (EmotionDL), to better handle cross-subject EEG variations and noisy labels, respectively. Extensive experiments on two public datasets, SEED and SEED-IV, demonstrate the superior performance of our model than state-of-the-art models in most experimental settings. Moreover, ablation studies show that the proposed adjacency matrix and two regularizers contribute consistent and significant gain to the performance of our RGNN model. Finally, investigations on the neuronal activities reveal important brain regions and inter-channel relations for EEG-based emotion recognition. AI Singapore Nanyang Technological University Accepted version This research is supported, in part, by the Alibaba-NTU Singapore Joint Research Institute (Alibaba-NTU-AIR2019B1), Nanyang Technological University, Singapore. 2021-12-09T08:22:12Z 2021-12-09T08:22:12Z 2020 Journal Article Zhong, P., Wang, D. & Miao, C. (2020). EEG-based emotion recognition using regularized graph neural networks. IEEE Transactions On Affective Computing. https://dx.doi.org/10.1109/TAFFC.2020.2994159 1949-3045 https://hdl.handle.net/10356/152723 10.1109/TAFFC.2020.2994159 en Alibaba-NTU-AIR2019B1 IEEE Transactions on Affective Computing © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TAFFC.2020.2994159. application/pdf |
| spellingShingle | Engineering::Computer science and engineering Affective Computing Electroencephalography Zhong, Peixiang Wang, Di Miao, Chunyan EEG-based emotion recognition using regularized graph neural networks |
| title | EEG-based emotion recognition using regularized graph neural networks |
| title_full | EEG-based emotion recognition using regularized graph neural networks |
| title_fullStr | EEG-based emotion recognition using regularized graph neural networks |
| title_full_unstemmed | EEG-based emotion recognition using regularized graph neural networks |
| title_short | EEG-based emotion recognition using regularized graph neural networks |
| title_sort | eeg based emotion recognition using regularized graph neural networks |
| topic | Engineering::Computer science and engineering Affective Computing Electroencephalography |
| url | https://hdl.handle.net/10356/152723 |
| work_keys_str_mv | AT zhongpeixiang eegbasedemotionrecognitionusingregularizedgraphneuralnetworks AT wangdi eegbasedemotionrecognitionusingregularizedgraphneuralnetworks AT miaochunyan eegbasedemotionrecognitionusingregularizedgraphneuralnetworks |