Deep learning and optimization-based feature selection for fetal health classification using CTG data

Abstract

This study introduces a DL and metaheuristic optimization-based framework for fetal health assessment using cardiotocography (CTG) signals to mitigate maternal and neonatal mortality. One-dimensional CTG signals were transformed into 2D representations, and deep feature extraction was performed using AlexNet. Feature vectors FC6, FC7, and their combination were subjected to optimization via Whale Optimization Algorithm (WOA + DL) and War Strategy Optimization (WSO + DL), utilizing updated fitness functions tailored for feature selection. Experimental results with SVM classifiers demonstrated superior performance with FC6 (89.98 %) and WSO + DL (90.17 %). FC6 exhibited strong discriminative capacity, while FC7 contained semantically richer features. The concatenated FC6 + FC7 vector increased feature diversity. WSO + DL achieved optimal balance across classification accuracy, feature subset size, convergence rate, and overall performance metrics. The integration of DL and metaheuristic algorithms effectively isolated informative feature subsets, improving training efficiency, minimizing redundant/noisy data, reducing overfitting risk, and enhancing classification accuracy. Optimization method selection proved critical to overall model performance.