Multiple Linear Regression-Artificial Neural Network Hybrid Model Predicting Standard State Absolute Entropy of Pure Organic Compound

摘要

The present invention is hydrogen (H), carbon (C), nitrogen (N), oxygen (O) , sulfur (S) consists of elements, such as less than 5 kinds and provides mathematical models for predicting the number of hydrogen atoms except the standard state entropy of absolute pure organic compound consisting of not more than 25 molecules with high accuracy. The model is for a number of organic compounds which satisfy the condition that the experimental value of the standard state entropy never known, any of a variety of molecules presenter as an independent variable, the absolute number multiple of the standard state entropy as the dependent variable linear regression model (multiple linear regression model) back to the best obtained using genetic algorithms (genetic algorithm) of, receives the value of the molecules presenters included with this model of artificial neural network which outputs the absolute standard state entropy ( artificial neural network) configuration was further enhanced by the multiple linear regression to predict the performance - and ANN hybrid model (hybrid model) as an example of a QSPR model, if you know the specific values of the molecules presenters included in the model that for any molecule, allows to predict the absolute standard state entropy of pure compound made by this molecule. As such, the present invention can maintain the cost and time savings by giving the experiment to provide a way to predict the value of the trusted standard state entropy for the absolute number of the organic compound of the experimental conditions is unknown, research and development of related industries lays effects such as to facilitate the work. ;