International Journal of
Physical Sciences

  • Abbreviation: Int. J. Phys. Sci.
  • Language: English
  • ISSN: 1992-1950
  • DOI: 10.5897/IJPS
  • Start Year: 2006
  • Published Articles: 2557

Full Length Research Paper

Separation of fetal electrocardiography (ECG) from composite ECG using adaptive linear neural network for fetal monitoring

M. S. Amin1*, Md. Mamun2, F. H. Hashim1 and H. Husain1          
1Department of Electrical, Electronic and Systems Engineering, Universiti Kebangsaan Malaysia 43600 Bangi, Selangor, Malaysia. 2Smart Engineering System Research Group, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia.
Email: [email protected]

  •  Accepted: 23 September 2011
  •  Published: 16 October 2011


The signal strength of the maternal ECG (MECG) is usually many times that of the fetal ECG (FECG). Separating FECG from abdominal ECG (AECG) is therefore always a challenge. Some multiple-lead algorithms use the thoracic MECG to cancel the MECG in the AECG to get FECG, though this is inconvenient for the patient during long-term monitoring. Hence, this paper describes an adaptive method to separate fetal ECG from composite electrocardiography (ECG) that consists of both maternal and fetal ECGs by using adaptive linear neural network (ADALINE) for easy fetal monitoring. The input signal is the maternal signal and the target signal is the composite signal. The network emulate maternal signal as closely as possible to abdominal signal, thus only predict the maternal ECG in the abdominal ECG. The network error equals abdominal ECG minus maternal ECG, which is the fetal ECG. The characteristic that enables fetal extraction is due to the correlation between maternal ECG signals and the abdominal ECG signal of pregnant woman. A graphic user interface (GUI) program is written in Matlab to detect the changes in extracted fetal ECG by different values of momentum, learning rate and initial weights used in the network. However, the learning rate, momentum and initial weights are adjusted until the results are reasonably well. It is found that filtering performs best by high learning rate, low momentum and small initial weights.


Key words: Neural network, fetal monitoring, fetal electrocardiography (ECG), QRS, maternal ECG, pregnancy.