Adaptive Spike-Like Representation of EEG Signals for Sleep Stages Scoring

TL;DR

This paper introduces an adaptive, probabilistic encoding scheme for EEG signals that, combined with a transformer model, improves automatic sleep stage scoring without extensive manual feature engineering.

Contribution

The study presents a novel adaptive encoding method for EEG signals and integrates it with a transformer model for enhanced sleep stage classification.

Findings

Outperforms existing state-of-the-art methods on a large public dataset.

Demonstrates the effectiveness of probabilistic adaptive encoding for EEG analysis.

Provides promising directions for future sleep stage scoring research.

Abstract

Recently there has seen promising results on automatic stage scoring by extracting spatio-temporal features from electroencephalogram (EEG). Such methods entail laborious manual feature engineering and domain knowledge. In this study, we propose an adaptive scheme to probabilistically encode, filter and accumulate the input signals and weight the resultant features by the half-Gaussian probabilities of signal intensities. The adaptive representations are subsequently fed into a transformer model to automatically mine the relevance between features and corresponding stages. Extensive experiments on the largest public dataset against state-of-the-art methods validate the effectiveness of our proposed method and reveal promising future directions.