Two-Stream Squeeze-and-Excitation Network for Multi-modal Sleep Staging

Abstract

Sleep staging is the basis of sleep medicine for diagnosing psychiatric and neurodegenerative diseases. However, the existing sleep staging methods ignore the fact that multi-modal physiological signals are heterogeneous, and different modalities contribute to sleep staging with distinct impacts on specific stages. Therefore, how to model the heterogeneity of multi-modal signals and adaptively utilize the multi-modal signals for sleep staging remains challenging. To address the above challenges, we design a Two-Stream Squeeze-and-Excitation Network (TSSEN) to capture the features of electroencephalogram (EEG) and electrooculogram (EOG) for sleep staging. The TS-SEN is made up of two independent feature extraction networks for modeling the heterogeneity and a Multi-modal Squeeze-and-Excitation feature fusion module for adaptively utilizing the multi-modal signals. Experiments demonstrate that the TSSEN is superior to the baseline models on the public sleep staging dataset. The implementation code of TS-SEN available at https://github.com/xiyangcai/TS-SEN