MULTIPLE LINEAR REGRESSION-ARTIFICIAL NEURON NETWORK MIXED MODEL, PREDICTING IONIZATION ENERGY OF A PURE ORGANIC COMPOUND, CAPABLE OF CONSIDERING VRIOUS MOLECULAR DESCRIPTORS

摘要

PURPOSE: A MLR(Multiple Linear Regression)-ANN(Artificial Neuron Network) mixed model, predicting ionization energy of a pure organic compound, is provided to build a MLR-ANN mixed model considering various molecular descriptors, thereby building a QSPR(Quantitative Structure-Property Relationship) model about the ionization energy of a pure organic compound.;CONSTITUTION: An optimum MLRM(Multiple Linear Regression Model) 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 the difference of an ionization energy prediction value, figured out by the MLRM and the ANNM, is greater than an over- suitability preventing standard value, the ionization energy prediction value by the MLRM is selected as an ionization energy value.;COPYRIGHT KIPO 2012