EEG-MFTNet: An Enhanced EEGNet Architecture with Multi-Scale Temporal Convolutions and Transformer Fusion for Cross-Session Motor Imagery Decoding

TL;DR

EEG-MFTNet is a deep learning model that enhances EEG-based motor imagery decoding by integrating multi-scale temporal convolutions and Transformer fusion, showing improved accuracy on cross-session EEG data.

Contribution

The paper introduces EEG-MFTNet, a novel architecture combining multi-scale convolutions and Transformer encoding to improve cross-session EEG motor imagery classification.

Findings

Achieves 58.9% accuracy on SHU dataset for MI decoding.

Outperforms baseline models like EEGNet in cross-session tests.

Maintains low computational complexity suitable for real-time BCI.

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.