机动车综合排气性能的支持向量分类和预报方法  

The classification and prediction of integrative performance of automobile exhaust

作　　者：刘亮 杨柳 双菊荣 陈旸 陆文聪 

机构地区：[1]上海大学理学院化学系计算机化学研究室,上海200436 [2]广州市环境监测中心站,广州513300

出　　处：《计算机与应用化学》2002年第6期737-740,共4页Computers and Applied Chemistry

基　　金：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。由于它根据严格的数学理论,同时考虑了拟合精度和对过拟合的抑制,故能基于小样本集作较可靠的计算机预报。本工作用这一算法研究了11类排量为125cc的四冲程摩托车的综合排气性能的分类和预报方法,并用留一法比较了SVM算法与Fisher法和KNN法的预报准确率。结果表明:SVM算法所建立的数学模型的预报正确率比Fisher法和KNN法高,因此,SVM算法可望应用于环保领域。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 technique to restrict overfitting. In this work, the support vector classification tech-nique is used for the classification and prediction of the integrative performance of automobile exhaust. The leaving-one method has been used to compare the rate of correctness predicted by using the SVM, Fisher and KNN methods. The results indicate that the rate of correctness of prediction by the SVM method is higher than other two methods. Therefore, the SVM method is an effective tool for classification and prediction of integrative performance of automobile exhaust. It is expected that the SVM method would be further applied to the field of environmental pro-tection.

关 键 词：综合排气性能 支持向量分类 预报方法 过拟合 机动车 过拟合 数学模型 SVM算法 环境污染 排气污染 统计学习理论 

分 类 号：X701[环境科学与工程—环境工程] TP181[自动化与计算机技术—控制理论与控制工程]