An Optimized Single Layer Perceptron-based Approach for Cardiotocography Data Classification

Uterine Contractions (UC) and Fetal Heart Rate (FHR) are the most common techniques for evaluating fetal maternal assessment during pregnancy detecting changes in oxygenation occurred throughout labor. By monitoring Cardiotocography (CTG) patterns, doctors can measure fetus state, accelerations, heart rate, uterine contractions. Several computational machine learning (ML) methods have been done on CTG recordings to improve effectiveness of analysis aid understand variations their interpretation. However, getting an optimal solution best accuracy remains important concern. Among various ML approaches, artificial neural network (ANN)-based approach has achieved a high performance several applications. In this paper, optimized Single Layer Perceptron (SLP)-based is proposed classify data accurately predict state. The able exploit advantages SLP model optimize rate using grid search method which we arrive at converge local minima. evaluated dataset University California, Irvine (UCI). trained tested 10-fold cross-validation technique patterns as normal, suspect or pathologic. experimental results show that 99.20% compared with state-of-the-art models.