Blind Separation of Abdominal Electrocardiogram Sources through Dynamic Neural Network

Cardiovascular system of the fetus is biological critical infrastructure. Fetal electrocardiogram and its characteristics such as heart ratio, waveform and dynamic behavior overall include vital information about health state, development and possible deviations from normal fetation. Thus fetal heart ratio monitoring is mandatory during pregnancy. Widespread Doppler ultrasound diagnostics can guarantee obtaining accurate results but is not suitable for long-term monitoring. Non-invasive fetal electrocardiography proposes to extract fetal signal from maternal abdominal electrocardiogram. This approach is applicable for long-term monitoring, but because of amplitude of maternal R-peaks is significantly larger than fetal it is a challenge to extract fetal signal. In this paper we propose using dynamic neural networks for extracting fetal components and demonstrate its advantages compared to blind source separation though independent component analysis. The training algorithm is a combination of backpropagation through time and resilient propagation. The proposed approach accuracy of R-peak detection is 97%. Statistical analysis proved that developed algorithm can process even non-stationary signals with loss of accuracy and no additional training is required. Keywords—dynamic neural network; vanishing gradient; blind source separation; fetal electrocardiogram; resilient propagation

[1]  Robert A. Pretlow,et al.  Fetal heart rate estimation via adaptive least mean square linear prediction methods , 1990, IEEE Proceedings on Southeastcon.

[2]  Janusz Jezewski,et al.  Spatio-temporal Filtering for Fetal QRS Enhancement , 2009 .

[3]  Danilo P. Mandic,et al.  Recurrent Neural Networks for Prediction: Learning Algorithms, Architectures and Stability , 2001 .

[4]  V. Medina,et al.  Fetal QRS extraction based on wavelet analysis and pattern matching , 1996, Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[5]  B. Widrow,et al.  Adaptive noise cancelling: Principles and applications , 1975 .

[6]  Danko Brezak,et al.  A comparison of feed-forward and recurrent neural networks in time series forecasting , 2012, 2012 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr).

[7]  F. Mochimaru,et al.  Detecting the Fetal Electrocardiogram by Wavelet Theory-Based Methods , 2022 .

[8]  Ryan McCaughey.  22. Deep Learning and Neural Networks used for Chinese Handwritten Optical Character Recognition , 2016 .

[9]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[10]  T. Fuchs,et al.  Signal loss during fetal heart rate monitoring using maternal abdominal surface electrodes between 28 and 42 weeks of pregnancy. , 2014, Advances in clinical and experimental medicine : official organ Wroclaw Medical University.

[11]  MA Hasan,et al.  Detection and Processing Techniques of FECG Signal for Fetal Monitoring , 2009, Biological Procedures Online.

[12]  Yalan Ye,et al.  A Non-Invasive Fetal Electrocardiogram Extraction Algorithm Based on ICA Neural Network , 2007, 2007 1st International Conference on Bioinformatics and Biomedical Engineering.

[13]  G. Clifford,et al.  A Review of Fetal ECG Signal Processing; Issues and Promising Directions. , 2010, The open pacing, electrophysiology & therapy journal.

[14]  Solange Akselrod,et al.  Fetal heart rate detection by a special transform method , 1989, [1989] Proceedings. Computers in Cardiology.

[15]  Arnon Cohen,et al.  Detection of fetal ECG with IIR adaptive filtering and genetic algorithms , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[16]  Chunlan Yang,et al.  Fetal ECG extraction based on adaptive linear neural network , 2010, 2010 3rd International Conference on Biomedical Engineering and Informatics.

[17]  Sumit Saroha,et al.  Multi step ahead forecasting of wind power by different class of neural networks , 2014, 2014 Recent Advances in Engineering and Computational Sciences (RAECS).

[18]  H. Sasa,et al.  Measurement characteristics of the ultrasound heart rate monitor , 1994, Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[19]  Jinwei Sun,et al.  Fetal ECG extraction using adaptive functional link artificial neural network , 2014, Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific.