Introduces first reproducible ECoG dataset from rat models for Parkinson's disease prediction. Swap-Adversarial Framework (SAF) uses channel swapping and domain-adversarial training to tackle inter-subject variability and HDLSS issues. Outperforms baselines in cross-subject, cross-session, and cross-dataset settings, generalizing to EEG.
Key Points
- 1.New PD benchmark dataset
- 2.Inter-subject channel swap augmentation
- 3.Domain-adversarial training for generalization
Impact Analysis
Enables robust, reproducible PD early detection research. Public dataset and code accelerate BCI advancements across ECoG and EEG.