A multisensor data fusion approach for improving the classification accuracy of uterine EMG signals

Advance Artificial Neural Network Classification Techniques Using EHG for Detecting Preterm Births

“…This suggests that it is easier to distinguish between pregnancies recorded at different stages of gestation than it is to distinguish between the time of delivery. Support Vector Machines (SVM) have also been successfully used to classify term and preterm deliveries [16]. This classifier classifies contractions as either labour or nonlabour, using different locations on the abdomen.…”

“…The support vector machine shows some promising results. For example, in [17], for a single SVM classifier, at one particular location on the abdomen, the result shows a 78.4% accuracy -the overall classification accuracy, for the combined SVM, was 88.4%. Finding the coefficients, for the decision boundary, occurs by solving a quadratic optimization problem.…”

Combining data fusion with multiresolution analysis for improving the classification accuracy of uterine EMG signals

“…It is important also to note that, due to the complexity of the analyzed data, a SVM classifier with a RBF kernel which is known to be a strong classifier should be used as the component classifier of the network. When tested on the same data, SVM classifier with a RBF kernel yielded better classification results than a neural network of the same kernel function [18,41]. On the other hand, the use of the multiresolution analysis and the LDB algorithm that selects a basis from a dictionary that illuminates the dissimilarities among the two classes presented an important preprocessing step for increasing the discriminatory powers of the extracted features.…”

“…As a result, when a decision fusion rule was applied, an improved accuracy of the classification decision compared to a decision based on any of the individual data sources alone was obtained. Furthermore, based on the fact that there was variability between the classification accuracies of the different channels, a decision fusion rule based on the WMV may be more convenient for combining the decisions than other rules such as the majority voting as concluded in [41]. It is important also to note that, due to the complexity of the analyzed data, a SVM classifier with a RBF kernel which is known to be a strong classifier should be used as the component classifier of the network.…”

“…The real uterine EMG signals used in this study were recorded on 32 women: 22 women were recorded during pregnancy (33 -41 week of gestation, WG), 7 during labor (37 -42 WG) and 3 during both pregnancy and labor (33)(34)(35)(36)(37)(38)(39)(40)(41)(42). The mean and standard deviations of the gestational ages for pregnancy and labor were 34.14 ± 3.94 and 39.6 ± 1.75 weeks, respectively.…”