EEGEncoder: Advancing BCI with Transformer-Based Motor Imagery Classification

arXiv:2404.14869v1 Announce Type: cross
Abstract: 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 transformer models to surmount these limitations. Our innovative multi-scale fusion architecture captures both immediate and extended temporal features, thereby enhancing MI task classification …

abstract arxiv bci benefit brain challenges classification computer control cs.hc cs.lg devices eeg extraction feature feature extraction harness interfaces machine machine learning noise paper traditional machine learning transformer type