Decoding motor imagery-based electroencephalography (EEG) signals is a crucial step in brain-computer interface (BCI) technology. To address the challenge of capturing global EEG information, this study proposes a model that combines a multi-head self-attention mechanism with an improved depthwise separable convolutional network (EDSCNet) for multi-task classification of motor imagery. Firstly, spatial features of different subbands are extracted using a filter bank common spatial pattern technique to capture fine-grained characteristics of motor imagery EEG accurately. Secondly, an enhanced one-dimensional convolutional network, the EDSCNet, is employed to capture local spatial information and spatial correlation of EEG signals. The model further incorporates a multi-head self-attention mechanism better to capture the global spatial information of motor imagery EEG, enhancing feature representation and improving multi-task classification accuracy, while reducing model parameters and computational complexity. Finally, the proposed model is validated and evaluated on the BCI Competition IV2a motor imagery EEG dataset, and the visualizations of EEG features for the left hand, right hand, both feet, and tongue motor imagery tasks are presented. The results demonstrate that the model achieves average classification accuracies of 95.35% and 96.87%, with Kappa coefficients of 0.937 9 and 0.958 6, respectively, on the two motor imagery datasets. The feature visualizations show distinct patterns for different motor imagery tasks in the brain. Moreover, the model exhibits consistent performance across all subjects.
FENGYang, QIAOXiaoyan. Classification of motor imagery EEG signals based on transfer learning[J]. Journal of Test and Measurement Technology, 2022, 36(5): 376-383. (in Chinese)
[3]
LIAOW, LIJ, ZHANGX, et al. Motor imagery brain-computer interface rehabilitation system enhances upper limb performance and improves brain activity in stroke patients: a clinical study[J]. Frontiers in Human Neuroscience, 2023, 17: 1117670.
[4]
AL-QURAISHIM S, ELAMVAZUTHII, TANGT B, et al. Multimodal fusion approach based on EEG and EMG signals for lower limb movement recognition[J]. IEEE Sensors Journal, 2021, 21(24): 27640-27650.
DENGXin, XIAOLifeng, YANGPengfei, et al. Development of a robot arm control system using motor imagery electroencephalography and electrooculography[J]. CAAI Transactions on Intelligent Systems, 2022, 17(6): 1163-1172. (in Chinese)
[7]
KAWALA-STERNIUKA, BROWARSKAN, AL-BAKRIA, et al. Summary of over fifty years with brain-computer interfaces-a review[J]. Brain Sciences, 2021, 11(1): 43.
[8]
ALLISONB Z, BRUNNERC, ALTSTÄTTERC, et al. A hybrid ERD/SSVEP BCI for continuous simultaneous two dimensional cursor control[J]. Journal of Neuroscience Methods, 2012, 209(2): 299-307.
[9]
BLANKERTZB, TOMIOKAR, LEMMS, et al. Optimizing spatial filters for robust EEG single-trial analysis[J]. IEEE Signal Processing Magazine, 2008, 25(1): 41-56.
[10]
NOVIQ, GUANC, DATT H, et al.Sub-band common spatial pattern(SBCSP) for brain-computer interface[C]//2007 3rd International IEEE/EMBS Conference on Neural Engineering, 2007: 204-207.
[11]
ANGK K, CHINZ Y, ZHANGH, et al. Filter bank common spatial pattern (FBCSP) in brain-computer interface[C]//2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), 2008: 2390-2397.
[12]
LAWHERNV J, SOLONA J, WAYTOWICHN R, et al. EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces[J]. Journal of Neural Engineering, 2018, 15(5): 056013.
PENGYu, SONGYaolian, YANGJun. Motor imagery electroencephalography classification based on data augmentation[J]. Journal of Computer Applications, 2022, 42(11): 3625-3632. (in Chinese)
[15]
TORTORAS, GHIDONIS, CHISARIC, et al. Deep learning-based BCI for gait decoding from EEG with LSTM recurrent neural network[J]. Journal of Neural Engineering, 2020, 17(4): 046011.
[16]
SHOEIBIA, SADEGHID, MORIDIANP, et al. Automatic diagnosis of schizophrenia in EEG signals using CNN-LSTM models[J]. Frontiers in Neuroinformatics, 2021, 15: 777977.
[17]
XIEJ, ZHANGJ, SUNJ, et al. A transformer-based approach combining deep learning network and spatial-temporal information for raw EEG classification[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering: a Publication of the IEEE Engineering in Medicine and Biology Society, 2022, 30: 2126-2136.
[18]
SONGY, ZHENGQ, LIUB, et al. EEG conformer: convolutional transformer for EEG decoding and visualization[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, 31: 710-719.
[19]
RAMOSERH, MULLER-GERKINGJ, PFURTSCHELLERG. Optimal spatial filtering of single trial EEG during imagined hand movement[J]. IEEE Transactions on Rehabilitation Engineering, 2000, 8(4): 441-446.
[20]
HEJ, ZHAOL, YANGH, et al. HSI-BERT: hyperspectral image classification using the bidirectional encoder representation from transformers[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(1): 165-178.
[21]
TANGERMANNM, MÜLLERK R, AERTSENA, et al. Review of the BCI competition IV[J]. Frontiers in Neuroscience, 2012, 6: 55.
[22]
BLANKERTZB, MÜLLERK R, KRUSIENSKID J, et al. The BCI competition. III: Validating alternative approaches to actual BCI problems[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering: a Publication of the IEEE Engineering in Medicine and Biology Society, 2006, 14(2): 153-159.
[23]
SAKHAVIS, GUANC, YANS. Learning temporal information for brain-computer interface using convolutional neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(11): 5619-5629.
[24]
MANER, ROBINSONN, VINODA P, et al. A multi-view CNN with novel variance layer for motor imagery brain computer interface[C]//2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020: 2950-2953.