Multiple Sub-Filter Adaptive Noise Canceller for Fetal ECG Extraction

Non-invasive monitoring of fetal cardiac signs through the signal processing of maternal abdominal signals has been emerging as a promising technique in the field of obstetrics and gynaecology. The underlying challenges in obtaining the Fetal Electrocardiogram (FECG) from maternal abdominal signals...

Full description

Saved in:
Bibliographic Details
Published in:Procedia computer science 2019, Vol.165, p.182-188
Main Authors: Krupa Abel, Jaba Deva, Samiappan, Dhanalakshmi, Kumar, R, Kumar, S Pravin
Format: Article
Language:English
Subjects:
Adaptive noise cancellers
Fetal Electrocardiogram
Multiple sub-filter
Single long filter
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Non-invasive monitoring of fetal cardiac signs through the signal processing of maternal abdominal signals has been emerging as a promising technique in the field of obstetrics and gynaecology. The underlying challenges in obtaining the Fetal Electrocardiogram (FECG) from maternal abdominal signals include elimination of dominant maternal ECG and other noises. The simple technique based on adaptive noise cancellers uses Single Long Filter (SLF) as adaptive filter for extracting the FECG. In this paper, we propose an algorithm for implementation of adaptive filter in adaptive noise canceller (ANC) as Multiple Sub-Filters (MSF). Each of the adaptive sub-filters are updated using the Least Mean Square (LMS) algorithm. The proposed MSF architecture is compared with traditional SLF ANC by testing using a real data from Daisy database. From the obtained results, it is observed that MSF-ANC performs better than SLF-ANC with 91.66% positive predictive value and 84.61% accuracy.
ISSN:1877-0509
1877-0509
DOI:10.1016/j.procs.2020.01.093