MULTIPLE LINEAR REGRESSION-ARTIFICIAL NEURAL NETWORK HYBRID MODEL FOR PREDICTING THE PARACHOR OF PURE ORGANIC COMPOUNDS CAPABLE OF FORMING AN ARTIFICIAL NEURAL NETWORK OUTPUTTING THE PARACHOR BASED ON THE VALUES OF MOLECULAR DESCRIPTORS FOR A MULTIPLE LINEAR REGRESSION MODEL

摘要

PURPOSE: A multiple linear regression-artificial neural network(MLR-ANN) hybrid model for predicting the parachor of pure organic compounds is provided to improve the performance of prediction.;CONSTITUTION: Molecular descriptors for the parachor of sample organic 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 parachor difference based on the optimal MLRM and the optimal ANNM is more than an over-fitting preventive reference value, the predicted parachor based on the MLRM is adopted as the parachor.;COPYRIGHT KIPO 2012