CLASSIFICATION OF FETAL STATUS BASED ON CARDIOTOCOGRAM DATA USING ALEXNET-SVM MODEL

Abstract

This paper proposes a method for classifying fetal status based on
cardiotocogram (CTG) data using a hybrid model combining AlexNet and SVM
(AlexNet-SVM). The CTG data includes parameters related to fetal heart rate
(FHR) and uterine contractions (UC) of pregnant mothers, classified into three
categories: normal, suspicious, and pathological. To improve accuracy in
classifying this complex data, the author employed the AlexNet convolutional
neural network (CNN) for feature extraction and support vector machine
(SVM) for classification. The results show that the AlexNet-SVM model
achieved an accuracy of 98.02%. This model has potential applications in
assisting doctors with early detection of fetal health issues, thereby reducing
risks and improving health outcomes for both mother and child.