#EEG
2 related articles

·2 min
How to Make Single-Channel EEG Sleep Staging Explainable: A Comparison of Five XAI Methods
A study systematically compares five XAI methods' attribution faithfulness for single-channel EEG sleep staging, using AASM bands as a clinical reference, finding Integrated Gradients achieves the highest Spearman rank correlation faithfulness across all five Sleep-EDF sleep stages and DREAMT AHI groups.
Read more →
Tech Frontiers·1 min
GRFNet: A Lightweight PyTorch Model Designed for Multichannel Time-Series Classification
GRFNet is a lightweight PyTorch model for multichannel time-series classification, originating from EEG decoding research. With only 3,847 parameters, it is based on the ROCKET architecture, combining random convolution kernels with learnable spatial filters, supports arbitrary input lengths, and will soon be evaluated on the PhysioNet dataset.
Read more →