Exploiting Spatial-temporal Data for Sleep Stage Classification via Hypergraph Learning

TL;DR

This paper introduces a hypergraph-based dynamic learning framework called STHL that effectively models multimodal, heterogeneous, and spatial-temporal data for improved sleep stage classification.

Contribution

The paper presents a novel hypergraph learning framework that captures spatial-temporal and multimodal data interactions for sleep analysis, surpassing existing models.

Findings

STHL outperforms state-of-the-art sleep classification models.

Hypergraphs effectively encode multimodal and heterogeneous data.

The framework improves classification accuracy by modeling complex data correlations.

Abstract

Sleep stage classification is crucial for detecting patients' health conditions. Existing models, which mainly use Convolutional Neural Networks (CNN) for modelling Euclidean data and Graph Convolution Networks (GNN) for modelling non-Euclidean data, are unable to consider the heterogeneity and interactivity of multimodal data as well as the spatial-temporal correlation simultaneously, which hinders a further improvement of classification performance. In this paper, we propose a dynamic learning framework STHL, which introduces hypergraph to encode spatial-temporal data for sleep stage classification. Hypergraphs can construct multi-modal/multi-type data instead of using simple pairwise between two subjects. STHL creates spatial and temporal hyperedges separately to build node correlations, then it conducts type-specific hypergraph learning process to encode the attributes into the embedding space. Extensive experiments show that our proposed STHL outperforms the state-of-the-art models in sleep stage classification tasks.