A polycyclic aromatic hydrocarbon property/toxicity prediction method using an intelligent support vector machine

Abstract

The invention relates to a polycyclic aromatic hydrocarbon property / toxicity prediction method using an intelligent support vector machine. The method, based on measured polycyclic aromatic hydrocarbon molecule structures and the quantitative structure-activity relationship technology, establishes a polycyclic aromatic hydrocarbon environmental index prediction module and a polycyclic aromatic hydrocarbon carcinogenicity prediction module and employs the support vector machine algorithm, thereby realizing handing of problems of small samples, nonlinearity and high dimension. The method also optimizes the models by using the grid search method, the genetic algorithm, and the particle swarm algorithm, thereby preventing parameter influence and further improving the accuracy of the models. The method can predict the property and toxicity of unknown polycyclic aromatic hydrocarbons rapidly by using intelligent optimized support vector machine; compared with conventional toxic test experiments, the method increases the test efficiency; compared with the conventional statistical prediction method, the method improves the generalization; compared with normal algorithms, the method prevents parameter influence, realizes programming and can provide referable decisional proof for environmental evaluation of polycyclic aromatic hydrocarbons.

Description

technical field [0001] The present invention relates to a molecular quantitative structure-property / activity correlation research method, especially the application and comparison of an intelligent optimization method, that is, a method for predicting the property / toxicity quantitative structure-activity of polycyclic aromatic hydrocarbons by applying an intelligent optimization support vector machine . Background technique [0002] With the acceleration of the global development process, the degree of air pollution has further intensified. Atmospheric suspended particulate matter is one of the important air pollutants that affect the quality of the air environment and endanger human health. Atmospheric particulate matter is highly correlated with environmental problems such as ozone layer depletion, global warming, and acid rain, and is closely related to severe air pollution such as sandstorms and photochemical smog. Epidemiological surveys and studies have shown that as ...

AI Technical Summary

Problems solved by technology

However, in the application of the support vector machine method, it is only a comparative study with other methods, and the selection of the support vector machine parameters is not well considered, which leads to the introduction of inaccurate parameters and leads to the decline of generalization ability.

Images