Multiple Linear Regression-Artificial Neural Network Hybrid Model Predicting Enthalpy of Fusion at Melting Point of Pure Organic Compound

摘要

invention is hydrogen (H), carbon (C), nitrogen (N), oxygen (O) , sulfur (S), such as the five pure organic compound composed of the elements and the number of atoms other than hydrogen consisting of not more than 25 within the molecule of the heat of fusion (enthalpy of fusion at melting point) to provide a mathematical model to predict with a high degree of accuracy, The. The model is, for a number of organic compounds which satisfy the condition that the experimental value of the heat of fusion are known, any of a variety of molecules presenter (molecular descriptor) as independent variables, the heat of fusion to number of multiple linear regression as the dependent variable 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 the heat of fusion ANN (artificial neural network) to constructed by predicting the performance was further improved multiple linear regression - is an example of a hybrid artificial neural network model (hybrid model) as a QSPR model, if you know the specific values of the molecules presenters included in the model that whatever molecules, purely as a molecule allows to predict the heat of fusion of the compound made. 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 heat of fusion and reliable for the number of the organic compound of the experimental conditions is unknown, facilitate the research and development of related industries lays effects such as that. ;