MULTIPLE LINEAR REGRESSION-ARTIFICIAL NEURAL NETWORK HYBRID MODEL FOR PREDICTING THE CRITICAL PRESSURES OF ORGANIC COMPOUNDS CAPABLE OF FORMING AN ARTIFICIAL NEURAL NETWORK OUTPUTTING THE ACENTRIC FACTORS BASED ON THE VALUES OF MOLECULAR DESCRIPTORS CONTAINED IN A MULTIPLE LINEAR REGRESSION MODEL

摘要

PURPOSE: A multiple linear regression-artificial neural network(MLR-ANN) hybrid model for predicting the critical pressures of organic compounds is provided to improve the performance of prediction.;CONSTITUTION: Molecular descriptors for the critical pressures of hydrocarbon-based compounds are prepared. Experimental data is classified based on a training set and a testing set. The optimal MLR model(MLRM) for the training set is searched. Entire samples are divided into three sets, and the optimal ANN model(ANNM) is searched. If the absolute value of the predicted critical pressure difference based on the optimal MLRM and the optimal ANNM is more than an over-fitting preventive reference value, the predicted critical pressures based on the MLRM is adopted as the critical pressures.;COPYRIGHT KIPO 2012