Ukrainian Catholic University (Machine Learning Lab) (Petryshak, Kachko, Maksymenko, Dobosevych)
Model weights not public. Contact creators for more information.
Two-stage deep learning pipeline that localizes premature ventricular contraction (PVC) beats directly from raw, unsegmented ECG signal, without relying on hand-crafted features or pre-existing R-peak annotations. An encoder-decoder network first localizes the R-peak of every heartbeat (normal or anomalous); the resulting R-peak positions are then passed to CardioIncNet, a 1D InceptionTime-based classifier, which delineates each beat as healthy or PVC. Evaluated with both single-dataset and cross-dataset protocols across three public ECG databases, the pipeline reached F1 scores above 0.99 (single-dataset) and 0.979 (cross-dataset) for R-peak localization, and above 0.96 and 0.85 respectively for PVC beat classification.
Architecture
Hybrid
Encoder-decoder network for R-peak localization (both normal and anomalous beats) feeding into CardioIncNet, a 1D InceptionTime-style convolutional classifier that delineates each localized beat as normal or PVC
Added to catalog
2026-08-13
48 half-hour excerpts of two-channel ambulatory ECG recordings from 47 subjects studied by the BIH Arrhythmia Laboratory; used as a cross-dataset, lead-missing/noise-robustness benchmark distinct from the pretraining data.
R-peak localization and PVC vs. normal beat classification from raw ECG