| 支持向量机用于多溴联苯醚蒸汽压的QSPR研究 |
| |
| 引用本文： | 罗元锋,黄俊,余刚.支持向量机用于多溴联苯醚蒸汽压的QSPR研究[J].计算机与应用化学,2009,26(6). |
| |
| 作者姓名： | 罗元锋 黄俊 余刚 |
| |
| 作者单位： | 清华大学环境科学与工程系POPs研究中心,北京,100084 |
| |
| 基金项目： | "十一五"国家科技支撑计划课题"执行持久性有机污染物公约的支撑技术研究与示范" |
| |
| 摘 要： | 应用ChemOffice 8.0中的MOPAC-PM3算法计算得到多溴联苯醚(PBDEs)的6个量子化学参数,采用基于多项式核,径向基核及Sigmoid核的支持向量机(SVM)方法建立了23种PBDEs蒸汽压的QSPR模型.三类核函数对训练集拟合的相关系数R2分别为0.994,0.996,0.994.,均方误差MSE分别为0.0102,0.0081,0.0095;留一法交叉验证(LOO)的相关系数分别为0.992,0.991,0.991.对测试集进行同归的相关系数分别为0.994,0.986,0.991,均方误差MSE分别为0.0225,0.0458,0.0247.结果表明SVM回归算法在PBDEs蒸汽压的QSPR建模上表现出色,核函数的选择对SVM模犁性能影响不显著.文章还从模型拟合效果、预测能力及稳定性三方面比较了三类核函数的整体性能,并比较了支持向量数目对核函数预测能力的影响.结果表明多项式核与Sigmoid核性能相当,优于径向基核.
|
| 关 键 词： | 定量结构性质相关(QSPR) 支持向量机(SVM) 核函数 多溴联苯醚(PBDEs) 蒸汽压 |
QSPR study of vapor pressure of PBDEs by SVM method |
| |
| Luo Yuanfeng,Huang Jun,Yu Gang.QSPR study of vapor pressure of PBDEs by SVM method[J].Computers and Applied Chemistry,2009,26(6). |
| |
| Authors: | Luo Yuanfeng Huang Jun Yu Gang |
| |
| Affiliation: | POPs Research Center;Department of Environmental Science and Engineering;Tsinghua University;Beijing;100084;China |
| |
| Abstract: | With MOPAC-PM3 method in the ChemOffice 8.0 software,6 quantum chemistry parameters for 23 kinds of PBDEs were calculated.Using support vector machine(SVM) method based on polynomial kernel,radial basis kernel,sigmoid kernel,a QSPR model has been set up for vapor pressure of 23 kinds of PBDEs.For the training set,the correlation coefficient R~2 of the three types of kernel function is 0.994,0.996 and 0.994,the mean square error(MSE) is 0.0102,0.0081 and 0.0095,respectively.The correlation coefficient R~2 of... |
| |
| Keywords: | QSPR support vector machine (SVM) kernel function PBDEs vapor pressure |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
