EEG-FMCNN: A fusion multi-branch 1D convolutional neural network for EEG-based motor imagery classification

• Published in: Medical & biological engineering & computing Vol. 62; no. 1; pp. 107 - 120
• Main Authors: Wang, Wenlong, Li, Baojiang, Wang, Haiyan, Wang, Xichao, Qin, Yuxin, Shi, Xingbin, Liu, Shuxin
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.01.2024; Springer Nature B.V
• Subjects: Ablation; Artificial neural networks; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Brain; Computer Applications; data collection; Decoding; EEG; Electroencephalography; Frequencies; Human Physiology; Human-computer interface; humans; Image classification; Imaging; Implants; Industrial development; industry; Mental task performance; Neural networks; Noise tolerance; Original Article; Radiology; Signal to noise ratio; Motor imagery (MI); Residual connection; Brain-computer interface (BCI); Squeeze-and-excitation (SE) blocks; Feature fusion; One-dimensional convolutional neural networks (1D-CNN)
• ISSN: 0140-0118; 1741-0444; 1741-0444
• DOI: 10.1007/s11517-023-02931-x

Motor imagery (MI) electroencephalogram (EEG) signal is recognized as a promising paradigm for brain-computer interface (BCI) systems and has been extensively employed in various BCI applications, including assisting disabled individuals, controlling devices and environments, and enhancing human capabilities. The high-performance decoding capability of MI-EEG signals is a key issue that impacts the development of the industry. However, decoding MI-EEG signals is challenging due to the low signal-to-noise ratio and inter-subject variability. In response to the aforementioned core problems, this paper proposes a novel end-to-end network, a fusion multi-branch 1D convolutional neural network (EEG-FMCNN), to decode MI-EEG signals without pre-processing. The utilization of multi-branch 1D convolution not only exhibits a certain level of noise tolerance but also addresses the issue of inter-subject variability to some extent. This is attributed to the ability of multi-branch architectures to capture information from different frequency bands, enabling the establishment of optimal convolutional scales and depths. Furthermore, we incorporate 1D squeeze-and-excitation (SE) blocks and shortcut connections at appropriate locations to further enhance the generalization and robustness of the network. In the BCI Competition IV-2a dataset, our proposed model has obtained good experimental results, achieving accuracies of 78.82% and 68.41% for subject-dependent and subject-independent modes, respectively. In addition, extensive ablative experiments and fine-tuning experiments were conducted, resulting in a notable 7% improvement in the average performance of the network, which holds significant implications for the generalization and application of the network. Graphical Abstract