MULTIPLE LINEAR REGRESSION-ARTIFICIAL NEURON NETWORK MODEL, PREDICTING AN IDEAL GAS ABSOLUTE ENTROPY OF A STANDARD STATE OF A PURE ORGANIC COMPOUND, CAPABLE OF REDUCING TIME AND COST FOR AN EXPERIMENT

摘要

PURPOSE: A MLR(Multiple Linear Regression)-ANN(Artificial Neuron Network) model, predicting an ideal gas absolute entropy of a standard state of a pure organic compound, is provided to reduce time and cost for an experiment and enable a value to be guessed when the experiment cannot be conducted, thereby vitalizing research and development of a related industry.;CONSTITUTION: Experimental data of sample organic compounds is separated into a training set and a test set. 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 of the difference of an ideal gas absolute entropy prediction value of a standard state, figured out by the MLRM and the ANNM, is greater than an over- suitability preventing standard value, the ideal gas absolute entropy prediction value of the standard state by the MLRM is selected as an ideal gas absolute entropy value of the standard state.;COPYRIGHT KIPO 2012