基于指标规范值的海水水质评价的SVR模型  

Model of Seawater Quality Evaluation with Normalized Indices Values Based on Support Vector Regression

作　　者：梁晓龙[1] 李祚泳[1] 汪嘉杨[1] 

机构地区：[1]成都信息工程学院资源环境学院,四川成都610225

出　　处：《成都信息工程学院学报》2014年第2期208-212,共5页Journal of Chengdu University of Information Technology

基　　金：国家自然科学基金资助项目(51209024)

摘　　要：为了建立具有普适通用的海水水质评价的支持向量机模型,在设置各指标参照值和指标规范变换式,并对指标进行规范变换的基础上,应用免疫进化优化算法,建立基于指标规范值的海水水质评价的回归支持向量机模型。将优化好的模型用于珠江口海水水质的评价,其评价结果与BP神经网络的评价结果基本一致,从而表明基于指标规范值的支持向量机模型用于海水水质评价是可行的,且该模型较传统的支持向量机评价模型具有较好的普适性和通用性。The purpose of this study is to explore the universal and common assessment model of the seawater quality based on support vector regression.On the basis of the set of proper reference values and transformed formulae as well as the normalized transformation for indices,the model of the seawater quality assessment with normalized indices values based on support vector regression （SVR） was established using immune evolutionary algorithm.The SVR model optimized by immune evolutionary algorithm was applied to assess the seawater quality at the Zhujiang River estuary and the evaluation results of this model basically consistent with that of BP artificial neural networks.The results show that the SVR modal of seawater quality evaluation based on normalized index values is feasible; and the universality and versatility of the new model are better than that of the traditional SVM model.

关 键 词：环境科学 环境信息分析 规范变换 支持向量机 海水水质评价 普适性 

分 类 号：X823[环境科学与工程—环境工程]