SELEKSI FITUR ALGORITMA NEURAL NETWORK MENGGUNAKAN PARTICLE SWARM OPTIMIZATION UNTUK MEMPREDIKSI KELAHIRAN PREMATUR Kresna Ramanda, Irmawati Carolina

Abstract

Premature birth, defined as delivery in pregnant women with gestation age 20 - 36 weeks. Research related to preterm birth has been done by the researchers by using the neural network method. However such research only showcase about the results of the sensitivity and specificity. The results of research using the method of neural network in predicting preterm birth has a value of the resulting accuracy is still less accurate and only limited to presenting the results of the sensitivity and specificity. In this study produced a model of the neural network algorithm and model of neural network algorithm based on particle swarm optimization to get the architecture in predicting preterm birth and gives a more accurate value for accuracy on a data set of RSUPN Cipto Mangunkusumo , RS Sumber Waras and in its entirety. After you are done testing with two models of neural network algorithms and neural network algorithm based on particle swarm optimization and the results obtained are the neural network algorithm generates value accuracy of 94,60%, 96,40%, 91,33%, and AUC values of 0,973, 0,982, 0,953, however, after the addition of the neural network algorithm based on particle swarm optimization value accuracy of 95,20%, 96,80%, 92,40% and AUC values of 0,979 , 0,987, 0,965. So both of these methods has the distinction of accuracy which amounted to 0.60%, 0.40%, 1.07% and AUC value difference of 0.006, 0.005, 0.012.