Fetal electrocardiogram extraction and R-peak detection for fetal heart rate monitoring using artificial neural network and correlation

Hasan , M. A. and Reaz, Mamun Bin Ibne and Ibrahimy, Muhammad Ibn (2011) Fetal electrocardiogram extraction and R-peak detection for fetal heart rate monitoring using artificial neural network and correlation. In: International Joint Conference on Neural Network (IJCNN 2011), 31 July - 5 August 2011, San Jose, California.

PDF - Published Version Restricted to Repository staff only Download (390kB) | Request a copy

Abstract

Conventional techniques are often unable to achieve the Fetal Electrocardiogram FECG extraction and Rpeak detection in FECG from the abdominal ECG (AECG) in satisfactorily level for Fetal Heart Rate (FHR) monitoring. A new methodology by combining the Artificial Neural Network (ANN) and Correlation approach has been proposed in this paper. Artificial Neural Network is chosen primarily since it is adaptive to the nonlinear and time-varying features of the ECG signal. The supervised multilayer perception (MLP) network has been used because it requires a desired output in order to learn. Similarly, the Correlation method has been chosen as the correlation factor can be used to scale the MECG when subtracting it from the AECG, in order to get the FECG. By combining these two approaches the proposed methodology gives better and efficient result in terms of accuracy for FECG extraction and R-peak detection in the AECG signal due to its above characteristics. The proposed approach involves the FECG extraction from the AECG signal with the accuracy of 100% and R-peak detection performance is 93.75%, even though the overlapping situation of MECG and FECG signal in the AECG signal. Therefore the physician and clinician can make the correct decision for the well-being status of the fetus and mother during the pregnancy period.

Item Type:	Conference or Workshop Item (Full Paper)
Additional Information:	4637/6473 ISSN: 2161-4393 Print ISBN: 978-1-4244-9635-8 Digital Object Identifier: 10.1109/IJCNN.2011.6033193
Uncontrolled Keywords:	AECG signal , FECG signal , MECG signal , R-peak detection , abdominal ECG signal , artificial neural network , correlation method , fetal electrocardiogram FECG extraction , fetal heart rate monitoring , nonlinear feature , pregnancy period , supervised multilayer perception network , time-varying feature
Subjects:	T Technology > T Technology (General)
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering > Department of Electrical and Computer Engineering
Depositing User:	Dr Muhammad Ibrahimy
Date Deposited:	07 Dec 2011 23:02
Last Modified:	07 Dec 2011 23:02
URI:	http://irep.iium.edu.my/id/eprint/6473

Actions (login required)

View Item