🤖 AI Summary
This study addresses the challenge of accurate discrimination between motor execution states (rest vs. task), overcoming the limitations of low signal-to-noise ratio in EEG and limited spatiotemporal resolution in fNIRS when used individually. We propose an end-to-end EEG–fNIRS bimodal collaborative modeling framework, whose core innovations are a Convolutional Additive Self-Attention (CASA) module and a dual-stream hybrid feature fusion mechanism, incorporating 1D convolution, additive self-attention, and OD128 upsampled input support. Built upon the CAS-ViT architecture, our method achieves significantly higher fusion accuracy than unimodal baselines on the SMR Hybrid BCI dataset. Notably, fNIRS alone outperforms EEG, and optimal EEG embedding dimensions lie within 64–128. The proposed framework establishes a robust, interpretable multimodal paradigm for motor brain–computer interfaces and underlying neurocognitive mechanism investigation.
📝 Abstract
Motor execution, a fundamental aspect of human behavior, has been extensively studied using BCI technologies. EEG and fNIRS have been utilized to provide valuable insights, but their individual limitations have hindered performance. This study investigates the effectiveness of fusing electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) data for classifying rest versus task states in a motor execution paradigm. Using the SMR Hybrid BCI dataset, this work compares unimodal (EEG and fNIRS) classifiers with a multimodal fusion approach. It proposes Motor Execution using Convolutional Additive Self-Attention Mechanisms (MECASA), a novel architecture leveraging convolutional operations and self-attention to capture complex patterns in multimodal data. MECASA, built upon the CAS-ViT architecture, employs a computationally efficient, convolutional-based self-attention module (CASA), a hybrid block design, and a dedicated fusion network to combine features from separate EEG and fNIRS processing streams. Experimental results demonstrate that MECASA consistently outperforms established methods across all modalities (EEG, fNIRS, and fused), with fusion consistently improving accuracy compared to single-modality approaches. fNIRS generally achieved higher accuracy than EEG alone. Ablation studies revealed optimal configurations for MECASA, with embedding dimensions of 64-128 providing the best performance for EEG data and OD128 (upsampled optical density) yielding superior results for fNIRS data. This work highlights the potential of deep learning, specifically MECASA, to enhance EEG-fNIRS fusion for BCI applications.