A Novel Classification and Synchronous Noise Removal During Fetal Heart Rate Monitoring

Diagnosis of fetal heart rate is very crucial during the prenatal phase of pregnancy as any delay in the early detection and prevention of anomalies in heart functioning may lead to devastating and life-threatening consequences to the child even after birth. Hence fetal electrocardiogram extraction is to be analyzed using either internal or external monitoring devices. One of the main problems is the intrusion of undesirable noise into the biomedical data, leading to misinterpretation of the diagnosis. Therefore, an effective way to identify and suppress such noise is to be formulated for extracting precise information. Several techniques have been excogitated over 200 samples collected from the dataset of MIT- BIH Arrhythmia, and on cross-validation, SVM Classifier with Trusted Ad – Hoc On Demand Distance Vector routing algorithm has been ascertained to have sensitivity to diverse noise at the rate of 88.4%. Adaptive multiband filtering technique eliminates almost all the noise within the bounded ranges that are already being medically defined. This filter offers high speed yet it occupies more area and glitches when the coefficients are increased by 15. Hence an energy-efficient filter is proposed and results are simulated using MATLAB 2013b, Xilinx ISE 9.1, ModelSim 10.0b, and Cadence Virtuoso under 90 nm technology for synthesis of area, power, and delay reports.