HEFMI-ICH: a hybrid EEG-fNIRS motor imagery dataset for brain-computer interface in intracerebral hemorrhage

This study introduces the first hybrid brain-computer interface dataset specifically designed for research on intracerebral hemorrhage (ICH) rehabilitation. It offers a novel data source through the synchronized acquisition of electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) signals. The dataset innovatively incorporated neural recordings from 17 normal subjects and 20 patients with ICH under standardized left-right hand motor imagery (MI) paradigms, featuring systematically collected and preprocessed dual-modality neural data. Beyond raw neural signals, the resource provides feature-engineered data optimized for classification algorithms and multidimensional signal decoding. The public availability of this dataset can facilitate the validation and optimization of MI decoding algorithms and advance the development of precision rehabilitation systems based on multimodal neural feedback.