Fetal Heart Rate Extraction using NLMS Algorithm

Abstract

This project develops a fetal heart rate (FHR) extraction application to analyze the fetus activity in the mother uterus. Several methods are available that can be used to detect FHR such as using the fetal electrocardiogram (FECG) that generated by fetus’ heart. Extracting FECG signals is considered a major challenge while the fetus is inside the mother uterus. Normalized Least Mean Square (NLMS) algorithm is one of adaptive filters that is chosen as adaptive filter to get FECG. Pan Tompkins algorithm is used for tracking R-peaks of heartbeat pulses of FECG signal. After detecting the RR interval a formula is used to calculate the bpm (heartbeat per minute) of FECG. Abdominal and direct FECG (ADFECG) database will be used to evaluate the implemented techniques as it has reference signal. At the end of research, calculated FHR is varied from 125.4 bpm to 130.3 bpm. When comparison is done between abdominal ECG (AECG) and direct FECG (DFECG), the error of FHR is 0.1%. The accuracy of R-peaks extraction is 100% where all R-peaks are detected by implemented techniques. MATLAB is used for signal simulations. This system will have ability to interpret the non-invasive FECG (NIFECG) database and compute its FHR.