Multimodel fuzzy rule based pattern mining technique for fetal heart rate detection using wavelet analysis and genetic algorithm

Abstract

Congenital heart defects are the most common disabilities and the leading cause of birth defect-related deaths. The morphology of cardiac electrical signals can be used to manifest cardiac defects. The non-invasive study of fetal cardiac signals can provide an effective means of monitoring the well-being of the fetal heart, and this may be used for the early detection of cardiac abnormalities. The electrocardiogram (ECG) signal is the graphical recording of the electrical potential generated in association with heart activity. It is one of the physiological signals commonly used in clinical aspects. As in adults, the well-being and the status of the fetus can be assessed from a fetal electrocardiogram (FECG) signal. newlineNon-invasive extraction of FECG has many technical problems. The FECG signal is corrupted by different sources of interferences such as maternal electrocardiogram (MECG), maternal electromyogram (MEMG), 50 Hz power line interference, and baseline wander. The low amplitude of the signals, the different types of noise, and overlapping frequencies of mother and fetal ECG make the extraction of FECG a problematic task. Extraction and analysis of the fetal ECG signal are the primary objectives of electronic fetal monitoring. In extracting the fetal ECG signal, digital signal processing techniques have played a significant role. The primary assumption is that the abdominal ECG signal (AECG) is a non-linear combination of the maternal ECG, fetal ECG signal, and other interference signals with several features. Wavelet Signal Analysis based feature extraction techniques has to be adopted to extract those features. After this, any abnormality detection problem can be solved by applying different data mining techniques. The classification can be performed with the help of different soft computing techniques newline