Novel Approach for Reinforcement the Extraction of ECG Signal for Twin Fetuses Based on Modified BSS

Abstract

One of the most used traditional method to measure heart conductivity of fetal is the fetal Electrocardiography (FECG). Many indicators related to the health of fetal can be determined depending on FECG since fetal heart rate (FHR) is obtained from the components of FECG signal. Recording fetal ECG in a clinic forms a problem due to the interferences of other signals which corrupt the ECG signal. Another problem happen as a result to the location of the used electrodes for recording ECG since these electrodes are placed on the mother abdomen. The obtained abdominal ECG signal also contain different types of interferences. The maternal ECG represents the first big interference source with the FECG signal. Breathing, the activity of mother's muscle, electrode contact with the mother's skin, power line interference and thermal noise, all of them represent a possible noise source. In case of extraction ECG signal for twin gestation, clear FECG for every single fetal would be more difficult because in addition to the all mentioned source of interferences and noise, both fetuses may share the same morphology and FHR. Close monitoring to the heart of twin is required for early diagnose of congenial problems which infect heart. In this study a novel approach has been made by combining conventional Stone BSS and particle swarm optimization (PSO) to produce (MSBSS). The obtained results are compared with other two BSS algorithms (EFICA and JADE) in addition to the obtained results using conventional Stone BSS. MSBSS method has revealed better performance comparing with the other BSS techniques including original Stone BSS.