Key result
STFT-CNN achieves ~86% accuracy for automatic sleep stage classification on single-channel EEG.
Why the study?
Manual sleep stage scoring is expert-dependent, tedious, and time-consuming, motivating the development of automatic sleep stage classification using deep learning on single-channel EEG.
Deep learning models using single-channel EEG and time-frequency spectra provide high accuracy for automated sleep stage scoring.
May support automated sleep staging research; leaves open prospective clinical validation before practice change.
Sleep stage scoring is fundamental for the examination and analysis of sleep problems. Sleep experts score sleep by analyzing brain activity, muscle activity and eye activity. Manual sleep stage scoring is an expert-dependent, tedious and time-consuming process. Automatic sleep stage classification (ASSC) has gained particular attention due to sleep awareness over the last few years. In this research, ASSC is proposed using deep learning methods using single-channel electroencephalogram (EEG) signal. EEG signals contain lots of information about brain functions during sleep. The EEG features were extracted using the convolution neural network (CNN) method. Different deep learning architectures are investigated using the raw EEG epochs and their time-frequency spectra using short-time Fourier transform (STFT) and stationary wavelet transform (SWT). The end-to-end classification pipeline classifies 30s EEG epochs into five sleep stages by extracting features from raw EEG epoch and their time-frequency representations. Deep learning models give good classification accuracy compared to the current state-of-the-art methods. It gives an overall accuracy of (Fpz-Cz: 83.7%, Pz-Oz: 83.5%), (Fpz-Cz: 85.6%, Pz-Oz: 83.6%) and (Fpz-Cz: 85.7 %, Pz-Oz: 83.2%) on 20 fold subjectwise cross-validation of the sleep-EDF-v1 dataset using 1D-CNN, SWT-CNN and STFT-CNN respectively. The subjectwise cross-validation performed shows more consistent performance across different subjects. The model size and performance are investigated to develop a less complex and smaller deep learning model.
No takes yet. Share an insight, caveat, or question.
Jadhav et al. (2022) studied Sleep problems. Deep learning methods (1D-CNN, SWT-CNN, STFT-CNN) vs. Current state-of-the-art methods was evaluated on Overall classification accuracy. Automatic sleep stage classification using STFT-CNN achieved an overall accuracy of 85.7% (Fpz-Cz) and 83.2% (Pz-Oz) on 20-fold subjectwise cross-validation of the sleep-EDF-v1 dataset.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: