EEG Sleep Stage Classification with Continuous Wavelet Transform and Deep Learning

2025-10-08

AI Summary

To address the time-consuming nature of manual sleep-stage annotation and the poor interpretability of traditional handcrafted-feature methods, this paper proposes an automated sleep-stage classification framework integrating continuous wavelet transform (CWT) with deep ensemble learning. CWT is employed to generate high-resolution time-frequency representations that faithfully capture stage-specific transient activities and rhythmic oscillations. A convolutional neural network (CNN) is then applied to extract discriminative local time-frequency patterns, while an ensemble strategy enhances model robustness and decision interpretability. Evaluated on the Sleep-EDF dataset, the framework achieves an overall accuracy of 88.37% and a macro-averaged F1-score of 73.15%, matching state-of-the-art deep learning methods and significantly outperforming conventional machine learning approaches. Crucially, the method preserves clinical interpretability through physiologically grounded time-frequency features, offering both high predictive performance and transparency for practical deployment in sleep medicine.

Technology Category

• Machine Learning: Ensemble Methods
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Accurate classification of sleep stages is crucial for the diagnosis and management of sleep disorders. Conventional approaches for sleep scoring rely on manual annotation or features extracted from EEG signals in the time or frequency domain. This study proposes a novel framework for automated sleep stage scoring using time-frequency analysis based on the wavelet transform. The Sleep-EDF Expanded Database (sleep-cassette recordings) was used for evaluation. The continuous wavelet transform (CWT) generated time-frequency maps that capture both transient and oscillatory patterns across frequency bands relevant to sleep staging. Experimental results demonstrate that the proposed wavelet-based representation, combined with ensemble learning, achieves an overall accuracy of 88.37 percent and a macro-averaged F1 score of 73.15, outperforming conventional machine learning methods and exhibiting comparable or superior performance to recent deep learning approaches. These findings highlight the potential of wavelet analysis for robust, interpretable, and clinically applicable sleep stage classification.

Problem

• Automating sleep stage classification using wavelet transform analysis
• Improving accuracy over conventional EEG time-frequency feature methods
• Enhancing clinical sleep disorder diagnosis with interpretable deep learning

Innovation

• Continuous wavelet transform creates time-frequency maps
• Ensemble learning combines multiple models for classification
• Wavelet-based representation outperforms conventional machine learning methods