Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Application of Intelligent Support Vector Machines to Predict the Properties/Toxicity of Polycyclic Aromatic Hydrocarbons

A technology of support vector machines and polycyclic aromatic hydrocarbons, which is applied in the direction of chemical property prediction, special data processing applications, computer parts, etc., can solve the problem of failure to consider the selection of support vector machine parameters and the decline of parameter generalization ability and other issues to achieve good prediction results, ensure the best accuracy rate, and avoid the effect of local optimization

Active Publication Date: 2018-04-13
HARBIN UNIV OF SCI & TECH
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Application of Intelligent Support Vector Machines to Predict the Properties/Toxicity of Polycyclic Aromatic Hydrocarbons
  • Application of Intelligent Support Vector Machines to Predict the Properties/Toxicity of Polycyclic Aromatic Hydrocarbons
  • Application of Intelligent Support Vector Machines to Predict the Properties/Toxicity of Polycyclic Aromatic Hydrocarbons

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] The following is to predict the PAH air-n-octanol partition coefficient K OA The quantitative structure-activity model of is used as an example to further explain the present invention.

[0033] According to the experimental results, the known air-n-octanol partition coefficient K was obtained OA According to the ChemDraw chemical software, the molecular structure is constructed and optimized, and the corresponding molecular descriptors are calculated by Dragon software, which are molecular weight (W), molecular volume (V), molecular length (L), and molecular width. (B). 11 data are extracted from it as the training set to establish the prediction model, and the remaining 4 data are used as the test set for verification.

[0034] Use the libsvm toolbox to add to the MATLAB software and compile the file. Convert the data obtained in step (1) into a format and compile it into a file PAH S _svr_scale.mat, this file mainly contains four matrix data files: train_x is a 1...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a method for predicting the properties / toxicity of polycyclic aromatic hydrocarbons by using an intelligent support vector machine. According to the measured molecular structure of polycyclic aromatic hydrocarbons, the method uses quantitative structure-activity relationship technology to establish a polycyclic aromatic hydrocarbon cyclization index prediction model and multiple The carcinogenicity prediction model of cycloaromatic hydrocarbons, using the support vector machine algorithm, realizes the processing of small sample, nonlinear and high-dimensional problems. The grid search method, genetic algorithm, and particle swarm optimization algorithm are used to optimize the model, which avoids the influence of parameters and further increases the accuracy of the model. The invention can quickly predict the properties and toxicity of unknown polycyclic aromatic hydrocarbons by using the intelligent optimization support vector machine, improves the test efficiency compared with the traditional toxicological test experiment, and improves the generalization ability compared with the traditional statistical prediction method. Compared with the normal algorithm, the influence of parameters is avoided. It realizes programming and can provide a reference decision-making basis for the environmental assessment 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 ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F19/00G06K9/62
CPCG16C20/30G06F18/2411
Inventor 周真杨旭牛訦琛陈鑫
Owner HARBIN UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com