A Multi Constrained Transformer-BiLSTM Guided Network for Automated Sleep Stage Classification from Single-Channel EEG

TL;DR

This paper introduces DenseRTSleep-II, a novel deep learning model combining CNN, transformer, and BiLSTM for accurate sleep stage classification from single-channel EEG, outperforming existing methods.

Contribution

The paper presents a new multi-constrained deep learning architecture that integrates CNN, transformer, and BiLSTM with a multi-loss scheme for improved sleep scoring accuracy.

Findings

Outperforms state-of-the-art methods in accuracy, precision, and F1-score.

Effective in sleep stage classification from single-channel EEG.

Demonstrates robustness on the SleepEDFx dataset.

Abstract

Sleep stage classification from electroencephalogram (EEG) is significant for the rapid evaluation of sleeping patterns and quality. A novel deep learning architecture, ``DenseRTSleep-II'', is proposed for automatic sleep scoring from single-channel EEG signals. The architecture utilizes the advantages of Convolutional Neural Network (CNN), transformer network, and Bidirectional Long Short Term Memory (BiLSTM) for effective sleep scoring. Moreover, with the addition of a weighted multi-loss scheme, this model is trained more implicitly for vigorous decision-making tasks. Thus, the model generates the most efficient result in the SleepEDFx dataset and outperforms different state-of-the-art (IIT-Net, DeepSleepNet) techniques by a large margin in terms of accuracy, precision, and F1-score.