A Novel Artifact Removal Strategy and Spatial Attention-based Multiscale CNN for MI Recognition

The brain-computer interface (BCI) based on motor imagery (MI) is a promising technology aimed at assisting individuals with motor impairments in regaining their motor abilities by capturing brain signals during specific tasks. However, non-invasive electroencephalogram (EEG) signals collected using EEG caps often contain large numbers of artifacts. Automatically and effectively removing these artifacts while preserving task-related brain components is a key issue for MI de-coding. Additionally, multi-channel EEG signals encompass temporal, frequency and spatial domain features. Although deep learning has achieved better results in extracting features and de-coding motor imagery EEG (MI-EEG) signals, obtaining a high-performance network on MI that achieves optimal matching of feature extraction, thus classification algorithms is still a challenging issue. In this study, we propose a scheme that combines a novel automatic artifact removal strategy with a spatial attention-based multiscale CNN (SA-MSCNN). This work obtained independent component analysis (ICA) weights from the first subject in the dataset and used K-means clustering to determine the best feature combination, which was then applied to other subjects for artifact removal. Additionally, this work designed an SA-MSCNN which includes multiscale convolution modules capable of extracting information from multiple frequency bands, spatial attention modules weighting spatial information, and separable convolution modules reducing feature information. This work validated the performance of the proposed model using a real-world public dataset, the BCI competition IV dataset 2a. The average accuracy of the method was 79.83%. This work conducted ablation experiments to demonstrate the effectiveness of the proposed artifact removal method and SA-MSCNN network and compared the results with outstanding models and state-of-the-art (SOTA) studies. The results confirm the effectiveness of the proposed method and provide a theoretical and experimental foundation for the development of new MI-BCI systems, which is very useful in helping people with disabilities regain their independence and improve their quality of life.