DE3S: Dual-Enhanced Soft-Sparse-Shape Learning for Medical Early Time-Series Classification
By: Tao Xie , Zexi Tan , Haoyi Xiao and more
Potential Business Impact:
Finds sickness early to save lives.
Early time-series classification (ETSC) in medical applications is crucial for time-sensitive scenarios such as sepsis prediction in intensive care units (ICUs), where a large number of deaths are caused by delayed prediction. ETSC can significantly improve ICU resource utilization efficiency and healthcare precision. However, it faces conflicting goals of accuracy and earliness, with existing methods often trading one for the other, struggling to capture subtle early-stage patterns due to weak initial signals and class imbalance. The key to solve these challenges is to find shapelets, which are discriminative subsequences (or shapes) with high interpretability in time-series classification. This paper proposes Dual-Enhanced Soft-Sparse-Shape Learning for Medical Early Time-Series Classification (DE3S), which introduces a novel Dual-Enhanced Soft-Shape Learning framework to figure out shapelets precisely through three innovations: (1) a comprehensive dual-enhancement strategy combines traditional temporal augmentation with attention-based global temporal enhancement for robust representation learning, (2) an attention-score-based soft shapelet sparsification mechanism dynamically preserves discriminative patterns while aggregating less important shapelets into representative tokens, and (3) a dual-path Mixture of Experts Network (MoE) and Inception modules fusion architecture where MoE performs local learning within shapelets and multi-scale Inception modules capture global patterns across shapelets. The framework employs weighted cross-entropy loss for class imbalance handling and demonstrates robustness on subject-consistency datasets. Extensive experiments on six real-world medical datasets show state-of-the-art performance, with ablation studies confirming component efficacy.
Similar Papers
Learning Soft Sparse Shapes for Efficient Time-Series Classification
Machine Learning (CS)
Finds important patterns in data to make predictions.
SigTime: Learning and Visually Explaining Time Series Signatures
Machine Learning (CS)
Finds hidden patterns in health data.
ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models
Machine Learning (CS)
Shows why time-based computer guesses are right.