| 摘要 |
PURPOSE: A multiple linear regression-artificial neural network(MLR-ANN) hybrid model for predicting the critical volume of pure organic compounds is provided to improve the performance of prediction. CONSTITUTION: Experimental data for hydrocarbon-based compounds is input. Molecular descriptors for the critical volume of the hydrocarbon-based compounds are prepared. The 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 volume difference based on the optimal MLRM and the optimal ANNM is more than an over-fitting preventive reference value, the predicted critical volume based on the MLRM is adopted as the critical volume. |
