Reproduce “A Multimodal fNIRS-EEG Dataset for Unilateral Limb Motor Imagery” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Lufeng Feng, Baomin Xu, Haoran Zhang, Bihai Lin, Zuxuan Deng, Sidi Tao, Chenyu Liu, Shifan Jia and 2 more
MIND introduces a public dataset pairing EEG and fNIRS during four-class directional motor-imagery tasks performed with one arm. The authors test classification using three-second moving windows and cross-validation across participants. The maximum mean accuracy is 31.92% for combined EEG and fNIRS, versus 30.68% for EEG alone; these are peaks from potentially different windows, not evidence of control or generalization to new people.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.