PhysioCLR adds physiology-based positive/negative pair selection, heartbeat shuffling, and peak-aware reconstruction to ECG contrastive learning, improving downstream arrhythmia AUROC on Chapman, Georgia, and private ICU data.
A novel imbalanced-dataset mitigation and ECG classification model based on combined 1D CBAM autoen- coder and lightweight CNN,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Domain Knowledge is Power: Leveraging Physiological Priors for Self Supervised Representation Learning in Electrocardiography
PhysioCLR adds physiology-based positive/negative pair selection, heartbeat shuffling, and peak-aware reconstruction to ECG contrastive learning, improving downstream arrhythmia AUROC on Chapman, Georgia, and private ICU data.