Multiple Linear Regression-Artificial Neural Network Hybrid Model Predicting Acentric Factor of Pure Organic Compound

摘要

invention is hydrogen (H), carbon (C), nitrogen (N), oxygen (O) , sulfur (S) consists of elements, such as less than 5 kinds and provides a mathematical model to predict with high accuracy the number of atoms other than hydrogen consisting of 25 molecules or less pure eccentricity factor of the organic compound (acentric factor). The model is for a number of organic compounds which satisfy the condition of the eccentric experimental factors are known, any of a variety of molecules presenter (molecular descriptor) as independent variables, many of the multi-factor as the dependent variable eccentric linear regression model (multiple linear regression model) are among the best that the genetic algorithm (genetic algorithm) was determined after using this model to include molecular presenter of the value of the input receives the output of eccentricity factor ANN (artificial neural network) was further improved by configuring multiple linear regression forecasting performance - as a hybrid artificial neural network model (hybrid model) QSPR (quantitative and structure-property relationship) example of a model, if you know the specific values of the molecules presenters included in the model that for any molecule, allows to estimate the eccentricity factor of pure compound made by the 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 unknown number of reliable experimental eccentricity factor of the condition for the organic compound, the research and development of related industries lays the effect of such readily. ;