A multi-layer EEG fusion decoding method with channel selection for multi-brain motor imagery

Traditional motor imagery-based single-brain computer interfaces(BCIs) face inherent limitations, such as unstable signals and low recognition accuracy. In contrast, multi-brain BCIs offer a promising solution by leveraging group electroencephalography (EEG) data. This paper presents a novel multi-layer EEG fusion method with channel selection for motor imagery-based multi-brain BCIs. We utilize mutual information convergent cross-mapping (MCCM) to identify channels that the represent causal relationships between brains; this strategy is combined with multiple linear discriminant analysis (MLDA) for decoding intentions via both data-layer and decision-layer strategies. Our experimental results demonstrate that the proposed method improves the accuracy of multi-brain motor imagery decoding by approximately 10% over that of the traditional methods, with a further 3%–5% accuracy increase due to the effective channel selection mechanism.