EEGEncoder: Advancing BCI with Transformer-Based Motor Imagery Classification
This work addresses EEG-based motor imagery classification for individuals with motor impairments, representing an incremental improvement over existing methods.
The paper tackled motor imagery classification in brain-computer interfaces by introducing EEGEncoder, a deep learning framework with a fusion architecture, achieving state-of-the-art results on the BCI Competition IV-2a dataset.
Brain-computer interfaces (BCIs) harness electroencephalographic signals for direct neural control of devices, offering a significant benefit for individuals with motor impairments. Traditional machine learning methods for EEG-based motor imagery (MI) classification encounter challenges such as manual feature extraction and susceptibility to noise.This paper introduces EEGEncoder, a deep learning framework that employs modified transformers and TCNs to surmount these limitations. We innovatively propose a fusion architecture, namely Dual-Stream Temporal-Spatial Block (DSTS), to capture temporal and spatial features, improving the accuracy of Motor Imagery classification task. Additionally, we use multiple parallel structures to enhance the performance of the model. When tested on the BCI Competition IV-2a dataset, our model results outperform current state-of-the-art techniques.