MULTIPLE LINEAR REGRESSION-ARTIFICIAL NEURAL NETWORK HYBRID MODEL PREDICTING CRITICAL TEMPERATURE OF PURE ORGANIC COMPOUND

摘要

PURPOSE: A multiple linear regression-artificial neural network(MLR-ANN) hybrid model for predicting the critical temperatures of organic compounds is provided to save costs and time required for experiments by predicting reliable critical temperatures of organic compounds with unknown experimental conditions. CONSTITUTION: Molecular descriptors for the critical temperatures 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 temperature difference based on the optimal MLRM and the optimal ANNM is more than an over-fitting preventive reference value, the predicted critical temperatures based on the MLRM is adopted as the critical temperatures.