Abstract
—Brain-computer interface (BCI) establishes an interactive platform by translating brain activity patterns into commands of external devices. BCIs, especially motor imagery (MI)-based BCIs, have injected new vitality into the development of rehabilitation medicine and many other fields. In this work, one
convolutional neural network, named as Flashlight-Net model, is proposed for multi-class MI classification. Flashlight-Net model adopts modular design, in which channel fusion module and time domain module ensure the directions of feature extraction, while feature pool module reduces the loss of effective information. Given the multi-frequency nature of the brain, we combine three frequency bands and construct an ensemble Flashlight-Net model. During the model training, by means of transfer learning, pre-training and fine-tuning processes are designed to integrate training samples from multiple subjects. The experimental results on publicly available BCI Competition IV-2a dataset show that the proposed model can achieve good results on all nine subjects, with an average classification accuracy of 81.23% for four classes. All these demonstrate that the proposed Flashlight-Net model can effectively decode multi-channel and multi-class MI signals.
convolutional neural network, named as Flashlight-Net model, is proposed for multi-class MI classification. Flashlight-Net model adopts modular design, in which channel fusion module and time domain module ensure the directions of feature extraction, while feature pool module reduces the loss of effective information. Given the multi-frequency nature of the brain, we combine three frequency bands and construct an ensemble Flashlight-Net model. During the model training, by means of transfer learning, pre-training and fine-tuning processes are designed to integrate training samples from multiple subjects. The experimental results on publicly available BCI Competition IV-2a dataset show that the proposed model can achieve good results on all nine subjects, with an average classification accuracy of 81.23% for four classes. All these demonstrate that the proposed Flashlight-Net model can effectively decode multi-channel and multi-class MI signals.
Original language | English |
---|---|
Number of pages | 10 |
Journal | IEEE Transactions on Systems, Man, and Cybernetics: Systems |
Early online date | 19 Apr 2024 |
DOIs | |
Publication status | E-pub ahead of print - 19 Apr 2024 |
Keywords
- Motor imagery
- convolutional neural network
- transfer learning
- EEG signals
- brain-computer interface (BCI)