Human sleep must be carefully monitored due to its impact on health. Typically, time series data for sleep monitoring is multimodal, simultaneous, and continuous. Pre-training models based on self-supervised learning can identify internal data patterns without requiring external labelling. In this paper, we propose temporal neighbourhood-based self-supervised pre-training models for multi-modality sleep signals, including EEG, EOG, and Heart Rate Variability (HRV). Two neighbourhood formation approaches are based on 1) the stationarity or trend-stationarity of sleep signals; 2) the feature similarity of sleep signals to find neighbourhoods of a given query sleep signal fragment/window. Both time-domain and frequency-domain features have been extracted and processed. The proposed models will learn latent representations for time series via making binary predictions of whether a fragment/window of time series is a neighbour of the given query sleep signal fragment/window. Downstream sleep stage classifiers can incorporate the pre-training models for sleep stage classification. The experiments conducted on the large-scale multi-modality sleep monitoring data SHHS show that the proposed approaches outperform other baseline classification models, including CNN and LSTM.
|Title of host publication||ICBBT '23: Proceedings of the 2023 15th International Conference on Bioinformatics and Biomedical Technology|
|Subtitle of host publication||May 26–28, 2023, Xi’an, China.|
|Place of Publication||New York, NY, USA|
|Number of pages||7|
|Publication status||Published - 26 May 2023|