REM Sleep Stage Identification with Raw Single-Channel EEG

This paper focused on creating an interpretable model for automatic rapid eye movement (REM) and non-REM sleep stage scoring for a single-channel electroencephalogram (EEG). Many methods attempt to extract meaningful information to provide to a learning algorithm. This method attempts to let the model extract the meaningful interpretable information by providing a smaller number of time-invariant signal filters for five frequency ranges using five CNN algorithms. A bi-directional GRU algorithm was applied to the output to incorporate time transition information. Training and tests were run on the well-known sleep-EDF-expanded database. The best results produced 97% accuracy, 93% precision, and 89% recall.

Automated summary

This paper introduces an interpretable model for automatic scoring of REM and non-REM sleep stages in a single-channel EEG. By providing a smaller number of time-invariant signal filters and CNN algorithms, the model is able to extract meaningful interpretable information and incorporate time transition information into the output. The best results achieved in training and testing on the sleep-EDF-expanded database show 97% accuracy, 93% precision, and 89% recall.