MULTIPLE LINEAR REGRESSION-ARTIFICIAL NEURON NETWORK MIXED MODEL, PREDICTING OF A STANDARD STATE ABSOLUTE ENTROPY OF A PURE ORGANIC COMPOUND, CAPABLE OF FORMING AN ANN OUTPUTTING THE STANDARD STATE ABSOLUTE ENTROPY BY RECEIVING A MOLECULAR DESCRIPTOR INCLUDED IN AN OPTIMUM MLRM

摘要

PURPOSE: A MLR(Multiple Linear Regression)-ANN(Artificial Neuron Network) mixed model, predicting a standard state absolute entropy of a pure organic compound, is provided to receive a molecular descriptor included in an optimum MLRM(Multiple Linear Regression Model) in order to form an ANN outputting the standard state absolute entropy, thereby improving prediction performance.;CONSTITUTION: Experimental data is separated into a training set and a test set. An optimum MLRM for the training set is explored. The predicted performance of the optimum MLRM is tested on the test set. After an optimum ANNM(Artificial Neural Network Model) divides every samples into three sets, it is explored. If the absolute value of the difference of a standard state absolute entropy prediction value, figured out by the MLRM and the ANNM, is greater than an over- suitability preventing standard value, the standard state absolute entropy prediction value by the ANNM is selected as a standard state absolute entropy value.;COPYRIGHT KIPO 2012