Comparison of Classification Methods for Fetal Heart Rate using Different Scale Dependent Features Selection
| Authors: | Georgoulas George, Laboratory for Automation and Robotics, University of Patras, Greece
Stylios Chrysostomos, Dept. of Communications, Informatics and Management, TEI of Epirus, Greece
Groumpos Peter, Laboratory for Automation and Robotics, University of Patras, Greece |
|---|
| Topic: | 8.2 Modelling & Control of Biomedical Systems |
|---|
| Session: | Biomedical Engineering / Biomedical Signal Processing II |
|---|
| Keywords: | Discrete Wavelet Transform, Support Vector Machines, Fetal Heart Rate |
|---|
Abstract
This research work compares the classification results of Fetal Heart Rate signal using three different feature sets. The Discrete Wavelet Transform is employed to extract three different sets consisted of scale and time-scale dependent features from the Fetal Heart Rate signal. The three sets of features are classified using the method of Support Vector Machines (SVM) with RBF kernels. The experimental data set are 40 intrapartum recordings and the extracted three different sets of features are entered to SVM to classify the FHR. The classification results for the three data sets are compared with respect to their ability to characterize fetal condition. The best classification performance achieved was 90%.
