Simulated Fetal PCGs

This data set, and the software used to generate it, are described in

1. Cesarelli M, Ruffo M, Romano M, Bifulco P. Simulation of foetal phonocardiographic recordings for testing of FHR extraction algorithms. Comput Methods Programs Biomed 2012 Sep;107(3):513-23.


2. Ruffo M, Cesarelli M, Romano M, Bifulco P, Fratini A. An algorithm for FHR estimation from foetal phonocardiographic signals. Biomedical Signal Processing and Control 2010 Jan; 5:131-141.

When referencing this material, please include at least one of the citations above, and also include the standard citation for PhysioNet:

Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PCh, Mark RG, Mietus JE, Moody GB, Peng C-K, Stanley HE. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation 101(23):e215-e220 [Circulation Electronic Pages;]; 2000 (June 13).

This data set is a series of synthetic fetal phonocardiographic signals (PCGs) relative to different fetal states and recording conditions, generated using simulation software described in [1] (above).

The simulation software can simulate different physiological and pathological fetal conditions and recording situations by simply modifying some system parameters. Thanks to this feature, it can be useful as a teaching tool for medical students and others, and also for testing algorithms of fetal heart rate extraction from fetal phonocardiographic recordings, as described in [2] (above).

Before developing the simulation software, a data collection pilot study was conducted with the purpose of specifically identifying the characteristics of the waveforms of the fetal and maternal heart sounds, since the available literature is not rigorous in this area.

Simulated PCGs were generated as a sequence of frames, each of them including simulated S1 and S2 wavelets, corrupted by noise. The noise is a sum of different contributions that simulate vibrations created by maternal heart sounds, maternal body organs sound (due to maternal digestion, respiratory muscular movements, placental blood turbulence), fetal movements, surrounding environment and additive white Gaussian noise. Different levels of noise were simulated. In particular, these simulated PCGs are characterized by a range of SNR values that could be typically found in real recordings.

All the details about the pilot study and the simulation of the PCG signals are described in [1].

Project collaborators: Mariano Ruffo, Mario Cesarelli, Maria Romano, and Paolo Bifulco, all from the University of Naples, Department of Electrical Engineering and Information Technology, Napoli, Italy.

Recording information: