Multi-Channel Multi-Domain based Knowledge Distillation Algorithm for Sleep Staging with Single-Channel EEG
arXiv:2401.03430 · doi:10.1109/TCSII.2022.3187205
Abstract
This paper proposed a Multi-Channel Multi-Domain (MCMD) based knowledge distillation algorithm for sleep staging using single-channel EEG. Both knowledge from different domains and different channels are learnt in the proposed algorithm, simultaneously. A multi-channel pre-training and single-channel fine-tuning scheme is used in the proposed work. The knowledge from different channels in the source domain is transferred to the single-channel model in the target domain. A pre-trained teacher-student model scheme is used to distill knowledge from the multi-channel teacher model to the single-channel student model combining with output transfer and intermediate feature transfer in the target domain. The proposed algorithm achieves a state-of-the-art single-channel sleep staging accuracy of 86.5%, with only 0.6% deterioration from the state-of-the-art multi-channel model. There is an improvement of 2% compared to the baseline model. The experimental results show that knowledge from multiple domains (different datasets) and multiple channels (e.g. EMG, EOG) could be transferred to single-channel sleep staging.
arXiv comment5 pages, 2 figures, published by IEEE TCAS-II
References in corpus (7)
- Distilling the Knowledge in a Neural Network
- DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG
- SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging
- A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series
- Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification
- Towards More Accurate Automatic Sleep Staging via Deep Transfer Learning
- LightSleepNet: Design of a Personalized Portable Sleep Staging System Based on Single-Channel EEG