A CNN-based classifier for detecting rhythm disorders, premature contractions, and conduction abnormalities from ECG

Sudhanshu Gaurhar, Anil Kumar Tiwari, Surender Deora

Abstract: Highlights•Arrhythmias are categorized as conduction, rhythm, or premature contraction types.•A unified 1D CNN is evaluated across Chapman, TNMG, and CPSC 2018 datasets.•Large kernels are used to capture QRS morphology for arrhythmia detection.•Model complexity is evaluated using MACs and FLOPs.

External IDs:doi:10.1016/j.bspc.2025.108834