Fetal Electrocardiogram Extraction Using Adaptive Neuro-fuzzy Inference Systems and Undecimated Wavelet Transform

Abstract

The Fetal electrocardiogram (FECG) signal reflects the electrical activity of the fetal heart. Fetal heart monitoring yields vital information about the fetus health and can support medical decision making in critical situations. In this paper, FECG is extracted from the maternal electrocardiogram using adaptive neuro-fuzzy inference systems and undecimated wavelet transform (UWT) is proposed. The performance of the proposed system is compared with the standard discrete wavelet transform (DWT). For numerical evaluation, the mean square error (MSE) between de-noised FECG signal and original FECG signal is used. Experimental results show that the UWT produce better results than DWT, as the MSE of DWT is higher than the UWT.

Keywords:

• ANFIS
• Discrete wavelet transform
• Electrocardiogram and thresholding
• Undecimated wavelet transform.

Additional information

Notes on contributors

S. Hema Jothi

S. Hema Jothi received her B.E., degree in Electronics and Communication Engineering from Mepco Schlenk Engineering College, Sivakasi in 1993 and M.E., degree in Medical Electronics from Anna University, Chennai in 2007. Presently, she is working as an Associate Professor in RMD Engineering college, Chennai. Her area of interest includes Bio-Signal processing, Soft computing, Neural Network, Fuzzy Logic and Medical image processing. She is having more than 18 years of teaching and research experiences. She is the Life Member of IETE and ISTE. E-mail: [email protected]

K. Helen Prabha

K. Helen Prabha received her B.E degree in Electronics and Communication Engineering from Government Institute of Technology, Coimbatore in 1989, M.E., degree in Applied Electronics from Coimbatore Institute of Technology, Coimbatore in 1994 and Ph.D degree from Anna University, Chennai in 2007. She is presently working as a Professor and Head of the ECE department at RMD Engineering College, Chennai. She has more than 50 research papers in her credit in National and International Conferences and Journals. Her area of interest includes Bio-Signal Processing, Neural Network, Fuzzy Logic and Soft Computing. She is having more than 20 years of teaching and research experiences. She is the Fellow Life Member of IETE and Life Member of ISTE. E-mail: [email protected]