期刊文献+

基于遗传算法的支持向量机预测含能材料密度的研究 被引量:4

Research on QSPR for energetic materials based on genetic algorithm support vector machine
原文传递
导出
摘要 基于遗传算法(genetic algorithm,GA)的变量筛选和支持向量机(support vector machine,SVM),提出了一种改进的定量结构-性质相关(quantitative structure detonation relationship,QSPR)建模方法——遗传-支持向量机(GA-SVM),并用其建立含能材料的定量结构-爆轰性能关系(QSDR)模型,此外还应用标准SVM方法建立了QSDR模型,并用这2种模型进行呋咱系含能化合物密度的预测,随机选取85%化合物作为训练集,用来建立模型,其余化合物作为测试集来测试模型的预测能力。预测结果的交互检验的相关系数平方分别为0.9887和0.9885,平均相对误差分别为1.16%和2.12%,表明了2种建模方法的有效性。通过对2种模型的预测能力进行比较,GA-SVM方法建立的QSDR模型能更好地预测呋咱系含能化合物的密度,更利于实际应用。 A modified method to develop quantitative structure property relationship (QSPR) models was proposed based on genetic al- gorithm (GA) and support vector machine (SVM) (GA-SVM). GA was used to perform the variable selection, and SVM was used to construct QSPR model. GA-SVM was applied to develop the quantitative structure detonation relationship model for energetic materials. The standard SVM was also utilized to construct QSDR prediction models, 85% of the whole date set were taken as training set to construct the model, the rest compounds were used to test the prediction ability of the model. The cross-validation correlation coefficient Rcv^2 is 0. 988 7 and 0. 988 5, and the mean relative error is 1.16% and 2. 12% , for the prediction results respectively. It demonstrates the validity of these two methods. By comparison the stability with prediction ability of the models, it was found that GA-SVM is the optimal method for developing QSDR model for predicting the density of furazan compounds.
出处 《计算机与应用化学》 CAS CSCD 北大核心 2009年第12期1529-1533,共5页 Computers and Applied Chemistry
基金 国防973资助项目(No.61374xx) 国家自然科学基金资助项目(No.20675063)
关键词 含能材料密度 支持向量机 遗传算法 定量结构-爆轰性能关系 energetic materialsOensity, support vector regression, genetic algorithm, quantitative structure detonation relationship
  • 相关文献

参考文献21

  • 1莫红军,赵凤起.纳米含能材料的概念与实践[J].火炸药学报,2005,28(3):79-82. 被引量:48
  • 2Ramaswamy A L and Kaste P. Nanoscale studies for environmentally benign explosives & propellant. Denmark, 2002, 176.
  • 3Pamela J and Kaste B. Novel energetic materials for the future force : the army pursues the next generation of propellants and explosives. The Amptiac Newsletter, 2004, 8 (4) :85 - 89.
  • 4Sergei Izrailev, Dimitris K. Agrafiotis. A method for quantifying and visualizing the diversity of QSAR models. J Mol Graphics Model, 2004, 22(4) :275 -284.
  • 5Sengupta C, Leonard J T and Roy K. Exploring QSAR of melatonin receptor ligand benzo furan derivatives using E-State index. Bioorgnaic & Medicinal Chemistry Letters, 2004, 14(13) : 3455 -3439.
  • 6Castro E A, Toropov A A and Nesterova A T, et al. QSAR Study of the Toxic action of aliphatic compounds to the bacteria vibrio fisheri based on correlation weighting of local graphy lnvariants. Journal of Molecular Structure (Theochem). 2003, 639 ( 3 ) : 129 - 135.
  • 7Vapnik V N. Estimation of Dependencies Based on Empirical Data. New York : Springer-Verlag, 1982.
  • 8张向东,毕韶丹,关宏宇.支持向量机方法预测有机物的亨利常数[J].分子科学学报,2006,22(3):185-189. 被引量:9
  • 9梅虎,梁桂兆,周原,李志良.支持向量机用于定量构效关系建模的研究[J].科学通报,2005,50(16):1703-1708. 被引量:28
  • 10Oldberg David E, Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley Publishing Company, 1989.

二级参考文献101

共引文献2379

同被引文献42

  • 1李侃,刘玉树.模糊核聚类的自适应算法[J].控制与决策,2004,19(5):595-597. 被引量:9
  • 2薛振框,李少远.MIMO非线性系统的多模型建模方法[J].电子学报,2005,33(1):52-56. 被引量:18
  • 3王国栋,刘玉存.神经网络在炸药晶体密度预测中的应用[J].火炸药学报,2007,30(1):57-59. 被引量:9
  • 4PAN Yong, JIANG Jun-cheng, WANG Rui. Prediction of auto-ignition temperatures of hydrocarbons by neural network based on atom-type electrotopological-state indices [J]. Journal of Hazardous Materials ,2008,157 (2 -3) :510 -517.
  • 5Katrizky A R, Maran U,Lobanov V S,et al. Structurally diverse quantitative structure-property relationship correlations of technologically relevant physical properties[J]. Journal of Chemical Information and Computer Sciences,2000,40(3):1 -18.
  • 6Taskinen J, Yliruusi J. Prediction of physicochemical properties based on neural network modeling[J]. Advanced Drug Delivery Reviews ,2003,55( 11 ) : 1 163 - 1 183.
  • 7Katrizky A R, Fara D. How chemical structure determines physical, chemical, and technological properties:An overview illustrating the potential of quantitative structure-property relationships for fuels science[J]. Energy & Fuels, 2005, 19(17) :922 - 935.
  • 8Katrizky A R, Lobanov V S, Karelson M. QSPR:The correlation and quantitative prediction of chemical and physical properties from structure[J]. Chemical Society Reviews,1995,24(4) :279-287.
  • 9Yaffe D L. A Neural Network Approach for Estimating Physicochemical Properties Using Quantitative Structure-property Relationships(QSPRs) [D]. Los Angeles : University of California,2001.
  • 10Mattioni B E. The Development of Quantitative Structure-activity Relationships Models for Physical Property and Biological Activity Prediction of Organic Compounds[D]. Pennsylvania State : The Pennsylvania State University,2003.

引证文献4

二级引证文献20

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部