Sapienza University of Rome
Model weights not public. Contact creators for more information.
CNN-based arrhythmia classifier that fuses the magnitude (scalogram) and phase (phasogram) of the continuous wavelet transform (CWT) of ECG heartbeats, rather than relying on magnitude information alone as most prior 2D-representation approaches do. Several fusion strategies (input-level, intermediate-layer, and output-level fusion) were compared on the public PhysioNet MIT-BIH Arrhythmia database. Despite a simple CNN architecture, the best fusion strategy achieved about 98.5% overall accuracy, 98.5% sensitivity and 95.6% specificity, competitive with more complex state-of-the-art approaches.
Architecture
CNN (2D)
CNN-based architecture that fuses scalogram (CWT magnitude) and phasogram (CWT phase) representations of ECG heartbeats via input-, intermediate-, or output-level fusion strategies
Framework
Keras
Added to catalog
2026-08-14
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.
Multi-class heartbeat arrhythmia classification from fused scalogram/phasogram representations of MIT-BIH ECG