Data-efficient Deep Learning Approach for Single-Channel EEG-Based Sleep Stage Classification with Model Interpretability

Sleep, a fundamental physiological process, occupies a significant portion of our lives. Accurate classification of sleep stages serves as a crucial tool for evaluating sleep quality and identifying probable sleep disorders. Our work introduces a novel methodology that utilizes a SE-Resnet-Bi-LSTM architecture to classify sleep into five separate stages. The classification process is based on the analysis of single-channel electroencephalograms (EEGs). The suggested framework consists of two fundamental elements: a feature extractor that utilizes SE-ResNet, and a temporal context encoder that uses stacks of Bi-LSTM units. The effectiveness of our approach is substantiated by thorough assessments conducted on three different datasets, namely SleepEDF-20, SleepEDF-78, and SHHS. The proposed methodology achieves significant model performance, with Macro-F1 scores of 82.5, 78.9, and 81.9 for the respective datasets. We employ 1D-GradCAM visualization as a methodology to elucidate the decision-making process inherent in our model in the realm of sleep stage classification. This visualization method not only provides valuable insights into the model's classification rationale but also aligns its outcomes with the annotations made by sleep experts. One notable feature of our research lies in the incorporation of an efficient training approach, which adeptly upholds the model's resilience in terms of performance. The experimental evaluations provide a comprehensive evaluation of the effectiveness of our proposed model in comparison to the existing approaches, highlighting its potential for practical applications.

mulEEG: A Multi-View Representation Learning on EEG Signals

Modeling effective representations using multiple views that positively influence each other is challenging, and the existing methods perform poorly on Electroencephalogram (EEG) signals for sleep-staging tasks. In this paper, we propose a novel multi-view self-supervised method (mulEEG) for unsupervised EEG representation learning. Our method attempts to effectively utilize the complementary information available in multiple views to learn better representations. We introduce diverse loss that further encourages complementary information across multiple views. Our method with no access to labels beats the supervised training while outperforming multi-view baseline methods on transfer learning experiments carried out on sleep-staging tasks. We posit that our method was able to learn better representations by using complementary multi-views.