Title: Fetal heart rate extraction from abdominal electrocardiograms through multivariate empirical mode decomposition

Biography:

Praveen Gupta received BE (Distinction) degree in Electronics Engineering from Sardar Vallabhbhai National Institute of Technology, Surat India in 1994. He completed his Master’s degree in VLSI from Malaviya National Institute of Technology, Jaipur, India in 2008. He started his professional career with the position of Lecturer (Electronics) in the Department of Technical Education (DTE), Rajasthan in 1995. Presently, he is a Lecturer (Selection Grade- stage-4) in DTE, Rajasthan. He has also worked as Technical Advisor in Government of Rajasthan from Dec.2014 to Feb.2016. His field of interest is Biomedical Signal Processing, specifically abdominal ECG signal processing, intracellular neuronal recordings, and algorithms. Apart from his engineering interests, he is greatly interested in policy issues in higher & technical education. He has a professional membership of IEEE.

Abstract

Assessment of fetal heart rate (FHR) and fetal heart rate variability (fHRV) reveals important information about fetal well-being, specifically in high-risk pregnancies. Abdominal electrocardiogram (abdECG) recording is a non-invasive method to capture fetal electrocardiograms. In this paper, we propose a methodology to extract FHR (fetal RR time series) from the abdECG recordings using the recently introduced multivariate empirical mode decomposition (MEMD) technique. MEMD breaks a signal into a finite set of intrinsic mode functions (IMFs). First, elimination of the noisier abdECG channels, based on the comparison of similar indexed IMFs that were obtained through the MEMD technique, is conducted. Thereafter, denoising of the remaining abdECG channels is performed by eliminating certain similar indexed IMFs. The unwanted mother QRS complexes are removed from these noise-free abdECG channels, and the candidate fetal R-peaks are detected through a wavelet-based approach. The proposed methodology is validated using an open source real-life clinical database. The proposed technique resulted in a high value (0.983) of cross-correlation between the detected and true FHR signals.