| 多环芳烃若干环化指标与分子几何参数的关系 |
| |
| 引用本文： | 陈念贻,陆文聪,刘旭,叶晨洲,李国正. 多环芳烃若干环化指标与分子几何参数的关系[J]. 计算机与应用化学, 2002, 19(6): 749-751 |
| |
| 作者姓名： | 陈念贻 陆文聪 刘旭 叶晨洲 李国正 |
| |
| 作者单位： | 1. 上海大学理学院化学系计算机化学研究室,上海,200436
2. 上海交通大学图象及模式识别研究所,上海,200030 |
| |
| 基金项目： | 国家自然科学基金委和美国福特公司联合资助(9716214) |
| |
| 摘 要： | 支持向量机（SVM）算法是特别适合于用有限已知样本训练建模，进而预报未知样本属性的模式识别新算法，本工作中应用支持向量回归算法和多环芳烃分子的环数，分子宽度，长度，体积，顶联接指数和边联接指数等几何参数作数据挖掘，总结了多环芳烃在空气－正辛醇分配比，多环芳烃在土壤中吸附参数，多环芳烃的生物浓度因子与分子几何参数关系的数学模型，用留一法证明，数学模型的预报可靠性较FLS算法建立的数学模型略优。
|
| 关 键 词： | 分子几何参数 多环芳烃 环化指标 支持向量回归 数学模型 统计学习理论 |
| 文章编号： | 1001-4160(2002)06-749-751 |
| 修稿时间： | 2002-09-16 |
On the relationships between geometrical parameters of polycyclic aromatic hydrocarbons and their environmental properties |
| |
| CHEN Nian-yi,LU Wen-cong,LIU Xu,YE Chen-zhou,LI Guo-zheng. On the relationships between geometrical parameters of polycyclic aromatic hydrocarbons and their environmental properties[J]. Computers and Applied Chemistry, 2002, 19(6): 749-751 |
| |
| Authors: | CHEN Nian-yi LU Wen-cong LIU Xu YE Chen-zhou LI Guo-zheng |
| |
| Abstract: | Support vector machine proposed by Vapnik is a newly developed technique for data mining. It is suitable for the data processing based on finite number of training samples, with special techm'que to restrict overfitting. In this work, support vector regression has been used for correlating and modeling the relationships between the geometrical parameters and environmental behaviors of polycyclic aromatic hydrocar-bons. The prediction ability of the mathematical models obtained is somewhat better than that obtained by PLS regression. |
| |
| Keywords: | polycyclic aromatic hydrocarbons environmental index support vector regression mathematical modei |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
