MULTIPLE LINEAR REGRESSION-ARTIFICIAL NEURON NETWORK MIXED MODEL FOR PREDICTING THE STANDARD STATE ENTHALPY OF FORMATION OF A PURE ORGANIC COMPOUND CAPABLE OF FORMING AN ANN OUTPUTTING THE STANDARD STATE ENTHALPY OF FORMATION BY USING A MOLECULE DESCRIPTOR INCLUDED IN AN MLRM

摘要

PURPOSE: An MLR(Multiple Linear Regression)-ANN(Artificial Neuron Network) mixed model for predicting the standard state enthalpy of formation of a pure organic compound is provided to form an ANN outputting the standard state enthalpy of formation by using a molecule descriptor included in an MLRM(Multiple Linear Regression Model), thereby improving prediction performance.;CONSTITUTION: Liquid hydrocarbon series experimental data is inputted. A molecule descriptor value about SEF(Standard State Enthalpy Of Formation) of a liquid hydrocarbon series organic compound is prepared from the experimental data. Experimental data is separated into a training set and a test set. An optimum MLRM(Multiple Linear Regression Model) for the training set is explored. 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 SEF prediction value, figured out by the MLRM and the ANNM, is greater than an over-suitability preventing standard value, the SEF prediction value by the MLRM is selected as a SEF value.;COPYRIGHT KIPO 2012