Machine Learning Based Sleep Stage Classification using Multiple EEG Features

DOI

10.2991/978-94-6463-831-8_39How to use a DOI?

Keywords

Sleep Stage Classification; Machine Learning; K-Nearest Neighbor; Random Forest

Abstract

Sleep Stage Classification (SSC) is very important for analyzing different sleep disorders, such as sleep apnea, insomnia, and narcolepsy. Traditional SSC technique’s performance is limited due to complex network topology, class imbalance problems, lower feature discrimination, inferior long-term dependency, and temporal representation. This paper presents the automatic SSC using the multiple EEG features (MEGs) that provides the spectral, time domain and textural features of the EEG which describe the various sleep stages distinctively. It uses a generative Adversarial Network (GAN) for data augmentation to minimize the class imbalance problem arising from uneven training samples. The effectiveness of the features is estimated on the public SleepEDF dataset for different machine classifiers such as K- Nearest Neighbor, Support Vector Machine (SVM), Classification Tree (CT) and Random Forest (RF) Classifier. It provides overall accuracy of 93.1% for RF, 91.7% for CT, 87.8% for KNN (K = 3), 79.3% for Linear SVM, 82.4% for RBF SVM, and 79.8% for the Polynomial SVM for six-stage SSC.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Anjali Pise
AU  - Priti Rege
AU  - Shripad Bhatlawande
PY  - 2025
DA  - 2025/08/31
TI  - Machine Learning Based Sleep Stage Classification using Multiple EEG Features
BT  - Proceeding of the 1st International Conference on Lifespan Innovation (ICLI 2025)
PB  - Atlantis Press
SP  - 322
EP  - 330
SN  - 2468-5739
UR  - https://doi.org/10.2991/978-94-6463-831-8_39
DO  - 10.2991/978-94-6463-831-8_39
ID  - Pise2025
ER  -