MECASA: Motor Execution Classification using Additive Self-Attention for Hybrid EEG-fNIRS Data

TL;DR

This paper introduces MECASA, a novel deep learning architecture using additive self-attention for improved classification of motor execution states by fusing EEG and fNIRS data, outperforming existing methods.

Contribution

The paper proposes MECASA, a new convolutional self-attention model that effectively fuses multimodal EEG and fNIRS data for motor execution classification.

Findings

MECASA outperforms traditional unimodal classifiers across all modalities.

Fusion of EEG and fNIRS improves accuracy over single modalities.

Optimal configurations identified for embedding dimensions and optical density.

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.