Haar wavelet transform and principal component analysis for fetal QRS classification from abdominal maternal ECG recordings

Fetal heart rate monitoring plays an essential role in helping to decrease the perinatal mortality rate associated with abnormalities in the cardiovascular system of the fetus. In this sense, a new approach to detect fetal QRS (fQRS) complexes from abdominal maternal ECG signals is proposed in this paper. First, signals were segmented into contiguous frames of 250 ms duration and then labeled in four classes. Principal component analysis was applied on Haar-Wavelet transform for dimensionality reduction and feature extraction, and interquartile ranges and sampling without replacement were employed to deal with outliers and imbalanced class problems, respectively. K-nearest neighborhood (KNN), support vector machine (SVM) and Bayesian network (BN) were trained and tested on the ECG signals of four electrodes of the PhysioNet/CinC challenge 2013 dataset, using 10-fold stratified cross-validation. Results show that KNN and SVM got better average accuracies over BN, that reach to 89.59% and 89.19%, respectively. Although KNN yielded better results, SVM was less time-consuming in prediction. In addition, the fourth electrode signals are less noisy and contain more representative data that helps SVM reaches an accuracy about 80% for fQRS estimation.