CardiacGen: A Hierarchical Deep Generative Model for Cardiac Signals

November 15, 2022 · Entered Twilight · 🏛 arXiv.org

Repo contents: .gitignore, .vscode, CardioGen, LICENSE, README.md, conda_requirements.yml, conda_requirements_linux.yml, data, demo_CC_ecg.ipynb, demo_augment_ppg.ipynb, experiments, modulators.py, pip_requirements.txt, pip_requirements_linux.txt, setup.py

Authors Tushar Agarwal, Emre Ertin arXiv ID 2211.08385 Category cs.LG: Machine Learning Cross-listed cs.AI, eess.SP, stat.ML Citations 3 Venue arXiv.org Repository https://github.com/SENSE-Lab-OSU/cardiac_gen_model ⭐ 4 Last Checked 3 months ago

Abstract

We present CardiacGen, a Deep Learning framework for generating synthetic but physiologically plausible cardiac signals like ECG. Based on the physiology of cardiovascular system function, we propose a modular hierarchical generative model and impose explicit regularizing constraints for training each module using multi-objective loss functions. The model comprises 2 modules, an HRV module focused on producing realistic Heart-Rate-Variability characteristics and a Morphology module focused on generating realistic signal morphologies for different modalities. We empirically show that in addition to having realistic physiological features, the synthetic data from CardiacGen can be used for data augmentation to improve the performance of Deep Learning based classifiers. CardiacGen code is available at https://github.com/SENSE-Lab-OSU/cardiac_gen_model.