Optimizing the Algorithm of FECG Separation from MECG Based on ICA Rationale

Abstract:

The study presents a method to separate the fetal electrocardiograph (FECG) from concomitant maternal electrocardiograph (MECG) by using Fast Independent component analysis (ICA) algorithm of Blind Signal Separation. Current methods of extracting fetal ECG have defects and drawbacks. Traditional ICA method has a persistent problem that the signal of FECG extracted from MECG was always mixed with the signal of MECG in diverse levels, and the order of MECG and FECG is uncertain, resulting in the decrease of its rate of convergence. To improve the rate of convergence, this research adopts Fast ICA algorithm. Experimental results indicate that this method is useful for extracting the fetal signal of ECG. And a satisfactory signal to noise ratio (SNR) is obtained.

• Periodical: Advanced Materials Research (Volumes 846-847)
• Pages: 1257-1261
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.846-847.1257
• Online since: November 2013
• Authors: Heng Yan Zhou, Yu Cong Xu, Yu Xi Luo*, Yu Bao Gao
• Keywords: Fast ICA Algorithm, Fetal ECG Signal, ICA Algorithm

References

[1] Zhou ligao, Liang Yuhou, Ye Datian, qinghua university The development of fetal ECG monitor using match filtering [J]. Chinese Journal Of Biomedical Engineering 1989, 13(5): 253-257.

[2] Li Shen, Zhou ligao, Yang Fusheng. Application of adaptive noise cancellation system for fetal ECG signal processing to achieve fetal monitoring [J]. Chinese Journal Of Biomedical Engineering, 1985, 4(4): 220-229.

[3] Li Zhangyong, Xie Zhengxiang, Niu Yonghong. The visual simulation method of extracting FECS by adaptive interference cancellation technique [J]. Shanghai Journal Of Biomedical Engineering, 2001, 22 (4): 13-17.

[4] Vicente Zarzoso, NandiAK. Noninvasive fetal electrocardiogram extraction: blind separation versus adaptive noise cancellation [J]. IEEE Transactions on Biomedical Engineering, 2001, 48(1): 12-18.

DOI: 10.1109/10.900244

[5] P.P. Kanjilal, S. Palit, G. Saha. Fetal ECG Extraction from Single-channel Maternal ECG Using Singular Value Decomposition [J]. IEEE Trans Biomed Eng, 1997, 44(1): 51-59.

DOI: 10.1109/10.553712

[6] Xu Jin. Fetal ECG Extraction Method Analysis[J]. ElectronicL Engineer. 2006, 32(6): 77-80.

[7] Ali Khamene. A New Method for the Extraction of Fetal ECG from the Composite Abdominal Signal [J]. IEEE Transactions on biomedical engineering, 2000, 47(4): 507-515.

DOI: 10.1109/10.828150

[8] F. Mochimaru, Y. Fujimoto, and Y. Ishikawa. Detecting the fetal electrocardiogram by wavelet theory-based methods [J]. Prog. Biomed. Res., 2002, 7(3): 185-193.

[9] G. Camps-Valls, M. Martínez-Sober, E. Soria-Olivas, R. Magdalena Benedito, J. Calpe- Maravilla, and J. Guerrero-Martínez. Fetal ECG recovery using dynamic neural networks [J]. Artif. Intell. Med., 2004, 31(3): 197-209.

DOI: 10.1016/j.artmed.2004.03.005

[10] Pu Xiujuan , Zeng XiaoPing, Chen Yuejun. Fetal electrocardiogram extraction based on radial basis function neural networks[J]. Journal of Chongqing University, 2009, 32(1): 114-115.

[11] Moor D.B. Database for the Identification of Systems (DaISy).

[12] Jasper Raj Immanuel. Ja, Prabhu. Va, Jane Christopheraj. Va, Sugumar. Da, Dr. Vanathi P.T. b, a* Separation Of Maternal And Fetal ECG Signals From The Mixed Source Signal Using FASTICA Procedia Engineering 30 (2012) 356.

DOI: 10.1016/j.proeng.2012.01.872