Related Experiment Video
Updated: Mar 17, 2026
10:56
Quantifying Infra-slow Dynamics of Spectral Power and Heart Rate in Sleeping Mice
Published on: August 2, 2017
10.6K
A decision support system for automatic sleep staging from EEG signals using tunable Q-factor wavelet transform and
Ahnaf Rashik Hassan1, Mohammed Imamul Hassan Bhuiyan1
1Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, Bangladesh.
Journal of Neuroscience Methods
|July 27, 2016
Summary
This study introduces an automated sleep scoring method using tunable-Q factor wavelet transform (TQWT) and random forest classification. The approach significantly improves sleep stage classification accuracy, aiding faster diagnosis and research.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Machine Learning
Background:
- Manual sleep scoring is time-consuming, labor-intensive, and prone to errors.
- Automated sleep staging is crucial for efficient and accurate diagnosis of sleep disorders.
Purpose of the Study:
- To develop and validate an automated sleep scoring system.
- To leverage spectral features from TQWT for improved sleep stage classification.
Main Methods:
- Sleep-EEG signal segments were decomposed using tunable-Q factor wavelet transform (TQWT).
- Spectral features were extracted from TQWT sub-bands.
- Random forest classifier was employed for sleep stage classification.
- Parameter optimization for TQWT and random forest was performed.
Main Results:
- The proposed method achieved high classification accuracies, ranging from 90.38% to 97.50% on the Sleep-EDF dataset.
- Statistical validation using ANOVA and Fisher criteria confirmed the efficacy of the feature generation scheme.
- Promising results were also observed on the DREAMS Subjects Data-set.
Conclusions:
- TQWT-derived spectral features effectively discriminate between various sleep stages.
- The automated scheme significantly outperforms existing methods in accuracy and Cohen's kappa coefficient.
- This approach can reduce physician workload, accelerate diagnosis, and advance sleep research.
