Abstract
Brain computer interface (BCI) based on motor imagery Electroencephalogram (EEG) has been widely used in various applications. Despite the previous efforts, the remained major challenges are effective feature extraction and time consuming calibration procedure. To address these issues, a novel Multi-Attention Adaptation Network integrating multiple attentions mechanism and transfer learning is proposed to classify the EEG signals. Firstly, the multi-attention layer is introduced to automatically capture the dominant brain regions relevant to mental tasks without incorporating any prior knowledge about
the physiology. Then, a multi-attention convolutional neural network is employed to extract deep representation from raw EEG signals. Especially, a domain discriminator is applied to deep representation to reduce the differences between sessions for target subjects. The extensive experiments are conducted on three public EEG datasets (Dataset IIa and IIb of BCI Competition IV, High Gamma dataset), achieving the competitive performance with average classification accuracy of 81.48%, 82.54% and 93.97%, respectively. All the results outperform the state-of-theart algorithms demonstrate the effectiveness and robustness of the proposed method. Importantly, we confirm that it is easier and more appropriate to transfer the information from local brain regions than from the whole brain. This enhances the transfer ability of deep features and hence it improves the performance of BCI systems.
the physiology. Then, a multi-attention convolutional neural network is employed to extract deep representation from raw EEG signals. Especially, a domain discriminator is applied to deep representation to reduce the differences between sessions for target subjects. The extensive experiments are conducted on three public EEG datasets (Dataset IIa and IIb of BCI Competition IV, High Gamma dataset), achieving the competitive performance with average classification accuracy of 81.48%, 82.54% and 93.97%, respectively. All the results outperform the state-of-theart algorithms demonstrate the effectiveness and robustness of the proposed method. Importantly, we confirm that it is easier and more appropriate to transfer the information from local brain regions than from the whole brain. This enhances the transfer ability of deep features and hence it improves the performance of BCI systems.
Original language | English |
---|---|
Article number | 5127 - 5139 |
Number of pages | 13 |
Journal | IEEE Transactions on Systems, Man, and Cybernetics: Systems |
Volume | 52 |
Issue number | 8 |
Early online date | 28 Oct 2021 |
DOIs | |
Publication status | Published - 1 Aug 2022 |
Bibliographical note
This work was supported in part by the National Natural Science Foundation of China under Grants Nos. 61873181 and 61922062Keywords
- Brain-computer interface (BCI)
- Deep learning
- electroencephalogram (EEG)
- Electroencephalography
- Feature extraction
- motor imagery (MI)
- multiple attentions mechanism
- Signal resolution
- Task analysis
- Training
- transfer learning
- Transfer learning