Frontiers in Neuroscience | |
EEGformer: A transformer–based brain activity classification method using EEG signal | |
Neuroscience | |
Jiajin Huang1  Hai Tan2  Shichang Liu3  Manyu Li4  Wenfeng Duan5  Zhijiang Wan6  | |
[1] Faculty of Information Technology, Beijing University of Technology, Beijing, China;School of Computer Science, Nanjing Audit University, Nanjing, Jiangsu, China;School of Computer Science, Shaanxi Normal University, Xi’an, Shaanxi, China;School of Information Engineering, Nanchang University, Nanchang, Jiangxi, China;The First Affiliated Hospital of Nanchang University, Nanchang University, Nanchang, Jiangxi, China;The First Affiliated Hospital of Nanchang University, Nanchang University, Nanchang, Jiangxi, China;School of Information Engineering, Nanchang University, Nanchang, Jiangxi, China;Industrial Institute of Artificial Intelligence, Nanchang University, Nanchang, Jiangxi, China; | |
关键词: brain activity classification; SSVEPs; EEGformer; EEG characteristics; deep learning; | |
DOI : 10.3389/fnins.2023.1148855 | |
received in 2023-01-20, accepted in 2023-03-06, 发布年份 2023 | |
来源: Frontiers | |
【 摘 要 】
BackgroundThe effective analysis methods for steady-state visual evoked potential (SSVEP) signals are critical in supporting an early diagnosis of glaucoma. Most efforts focused on adopting existing techniques to the SSVEPs-based brain–computer interface (BCI) task rather than proposing new ones specifically suited to the domain.MethodGiven that electroencephalogram (EEG) signals possess temporal, regional, and synchronous characteristics of brain activity, we proposed a transformer–based EEG analysis model known as EEGformer to capture the EEG characteristics in a unified manner. We adopted a one-dimensional convolution neural network (1DCNN) to automatically extract EEG-channel-wise features. The output was fed into the EEGformer, which is sequentially constructed using three components: regional, synchronous, and temporal transformers. In addition to using a large benchmark database (BETA) toward SSVEP-BCI application to validate model performance, we compared the EEGformer to current state-of-the-art deep learning models using two EEG datasets, which are obtained from our previous study: SJTU emotion EEG dataset (SEED) and a depressive EEG database (DepEEG).ResultsThe experimental results show that the EEGformer achieves the best classification performance across the three EEG datasets, indicating that the rationality of our model architecture and learning EEG characteristics in a unified manner can improve model classification performance.ConclusionEEGformer generalizes well to different EEG datasets, demonstrating our approach can be potentially suitable for providing accurate brain activity classification and being used in different application scenarios, such as SSVEP-based early glaucoma diagnosis, emotion recognition and depression discrimination.
【 授权许可】
Unknown
Copyright © 2023 Wan, Li, Liu, Huang, Tan and Duan.
【 预 览 】
Files | Size | Format | View |
---|---|---|---|
RO202310102707751ZK.pdf | 4134KB | download |