# State-Dependent CNN–GRU Reinforcement Framework for Robust EEG-Based Sleep Stage Classification

## TL;DR

This paper introduces a new AI framework that improves sleep stage classification using EEG data, achieving high accuracy with fewer sensors and faster processing.

## Contribution

A novel CNN–GRU reinforcement learning framework that uses biomimetic features for robust sleep stage classification.

## Key findings

- The proposed framework achieved 98% classification accuracy using an optimized feature set.
- The model uses fewer EEG channels and reduces processing time, making it suitable for real-time applications.
- Biomimetic principles in feature extraction and model design enhance sleep monitoring effectiveness.

## Abstract

Recent advances in automated learning techniques have enhanced the analysis of biomedical signals for detecting sleep stages and related health abnormalities. However, many existing models face challenges with imbalanced datasets and the dynamic nature of evolving sleep states. In this study, we present a robust algorithm for classifying sleep states using electroencephalogram (EEG) data collected from 33 healthy participants. We extracted dynamic, brain-inspired features, such as microstates and Lempel–Ziv complexity, which replicate intrinsic neural processing patterns and reflect temporal changes in brain activity during sleep. An optimal feature set was identified based on significant spectral ranges and classification performance. The classifier was developed using a convolutional neural network (CNN) combined with gated recurrent units (GRUs) within a reinforcement learning framework, which models adaptive decision-making processes similar to those in biological neural systems. Our proposed biomimetic framework illustrates that a multivariate feature set provides strong discriminative power for sleep state classification. Benchmark comparisons with established approaches revealed a classification accuracy of 98% using the optimized feature set, with the framework utilizing fewer EEG channels and reducing processing time, underscoring its potential for real-time deployment. These findings indicate that applying biomimetic principles in feature extraction and model design can improve automated sleep monitoring and facilitate the development of novel therapeutic and diagnostic tools for sleep-related disorders.