Fetal phonocardiography signal processing from abdominal records by non-adaptive methods

Rene Jaros; Radana Kahankova; Radek Martinek; Jan Nedoma; Marcel Fajkus; Zdenek Slanina

doi:10.1117/12.2501550

1 October 2018 Fetal phonocardiography signal processing from abdominal records by non-adaptive methods

Rene Jaros, Radana Kahankova, Radek Martinek, Jan Nedoma, Marcel Fajkus, Zdenek Slanina

Author Affiliations +

Proceedings Volume 10808, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2018; 108083E (2018) https://doi.org/10.1117/12.2501550
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2018, 2018, Wilga, Poland

Abstract

Fetal Phonocardiography (fPCG) is still secondary tool but provides very important information about fetal well-being that cannot be given by another fetal monitoring method. Independent Component Analysis (ICA) and Principal Component Analysis (PCA) were chosen for testing on synthetic data that are able to extract fPCG from abdominal signals. Results show that ICA and PCA could be used in clinical practice for fetal Heart Rate (fHR) monitoring, because after extraction of components it is easy to determine fHR. Signal to Noise Ratio (SNR) proved that after the extraction there was a significant improvement in estimated signal to compare with input abdominal signals. We found that ICA method works better than PCA method on this data, even though it changes the amplitude of the output components.

Citation Download Citation

Rene Jaros, Radana Kahankova, Radek Martinek, Jan Nedoma, Marcel Fajkus, and Zdenek Slanina "Fetal phonocardiography signal processing from abdominal records by non-adaptive methods", Proc. SPIE 10808, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2018, 108083E (1 October 2018); https://doi.org/10.1117/12.2501550

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE