Problem
Research questions and friction points this paper is trying to address.
motor imagery decoding
cross-session variability
EEG
brain-computer interface
noise
EEG-MFTNet: An Enhanced EEGNet Architecture with Multi-Scale Temporal Convolutions and Transformer Fusion for Cross-Session Motor Imagery Decoding
🤖 AI Summary
This study addresses the challenge of low decoding accuracy in cross-session motor imagery electroencephalography (EEG) classification, primarily caused by noise and inter-session variability. To tackle this issue, the authors propose a dual-stream architecture built upon EEGNet that integrates multi-scale temporal convolutions with a Transformer encoder to jointly model both short- and long-range temporal dependencies in EEG signals. The proposed method maintains low computational complexity while significantly enhancing the model’s robustness and adaptability to cross-session EEG data. Evaluated on the SHU dataset, the approach achieves an average classification accuracy of 58.9%, outperforming existing baselines and demonstrating strong potential for real-time brain–computer interface applications.
📝 Abstract
Brain-computer interfaces (BCIs) enable direct communication between the brain and external devices, providing critical support for individuals with motor impairments. However, accurate motor imagery (MI) decoding from electroencephalography (EEG) remains challenging due to noise and cross-session variability. This study introduces EEG-MFTNet, a novel deep learning model based on the EEGNet architecture, enhanced with multi-scale temporal convolutions and a Transformer encoder stream. These components are designed to capture both short and long-range temporal dependencies in EEG signals. The model is evaluated on the SHU dataset using a subject-dependent cross-session setup, outperforming baseline models, including EEGNet and its recent derivatives. EEG-MFTNet achieves an average classification accuracy of 58.9% while maintaining low computational complexity and inference latency. The results highlight the model's potential for real-time BCI applications and underscore the importance of architectural innovations in improving MI decoding. This work contributes to the development of more robust and adaptive BCI systems, with implications for assistive technologies and neurorehabilitation.
Innovation
Methods, ideas, or system contributions that make the work stand out.
multi-scale temporal convolutions
Transformer fusion
cross-session motor imagery decoding
EEGNet enhancement
real-time BCI
🔎 Similar Papers
No similar papers found.
