TransECG-SSL: Hybrid Self-Supervised Representation Learning for ECG Arrhythmia Classification
Read the original on arXiv Machine Learning →TransECG-SSL is a self‑supervised framework that learns transferable heartbeat representations from unlabelled ECG data using a Transformer encoder pretrained with a hybrid objective of masked signal reconstruction and contrastive learning. The pretrained model is frozen and evaluated via linear probing on patient‑disjoint splits across three public ECG databases, showing that Hybrid SSL outperforms randomly initialized Transformers and source‑supervised pretraining. While cross‑dataset transfer improves performance over random baselines, it still falls short of target‑specific self‑supervised pretraining, and minority arrhythmia classes remain difficult under severe class imbalance.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.