SEFMEID: A Synchronous EEG-fNIRS Motor Execution and Imagery Dataset

The dataset includes resting baseline, left-right hand motor execution (ME), and left-right hand motor imagery (MI) conditions, with each subject performing 25 trials for the right task and 25 trials for the left task. We also provide single-modality and multimodal classification results, as well as neurovascular coupling analyses, to validate the usability and quality of the dataset.

In the deep learning results, the multimodal fusion algorithm achieves an improvement of approximately 10% over the best-performing unimodal approach. The public release of SEFMEID aims to serve as a valuable resource for advancing multimodal MI-BCI algorithms, investigating neurovascular coupling mechanisms underlying motor imagery, and accelerating clinical translation in neurological rehabilitation.