基于灰色理论及支持向量机的水质预测
详细信息 查看官网全文
- 论文作者：刘文 ; 王国胤 ; 宋应文 ; 傅剑宇 ; 利节
- 年：2013
- 作者机构：中国科学院重庆绿色智能技术研究院数据挖掘与认知中心;重庆邮电大学计算智能重庆市重点实验室;
- 论文关键词：水质预测 ; 小波变换 ; 灰色理论(GM) ; 支持向量机(SVM)
- 英文论文关键词：Water Quality Prediction ; Wavelet Transformation ; Grey Model(GM) ; Support Vector Machine(SVM)
- 会议召开时间：2013-12-26
- 会议录名称：2013年水资源生态保护与水污染控制研讨会论文集
- 语种：中文
- 分类号：X52;X824
- 学会代码：HJKP
- 会议名称：2013年水资源生态保护与水污染控制研讨会
- 会议地点：中国黑龙江哈尔滨
- 主办单位：中国环境科学学会、环境保护部环境规划院、哈尔滨工业大学、哈尔滨师范大学、中国科学院南京地理与湖泊研究所
- 学会名称：中国环境科学学会
- 页数：6
- 文件大小：1160k
- 原文格式：D
- 会议级别：全国
摘要
针对Db N小波变换分解后的子序列具有不同的特性,仅采用支持向量机建立所有子序列的预测模型,会导致大量输入的训练数据影响模型预测精度的问题,本文提出使用灰色理论(最少4个数据就能建立模型)和支持向量机分别对小波变换分解后的平稳尺度子序列和不断变化的细节子序列建立预测模型.将该预测模型应用于乌梁素海PH值时间序列预测,通过与传统的支持向量机模型和BP神经网络模型比较,结果表明:本文新的水质预测模型在个别监测点的预测效果存在不足,但是总体预测效果明显优于传统的预测模型,平均相对误差由0.88,降低到0.51.
As the sub-sequence decomposed by Db N having different properties, a large number of input training data will affect the prediction accuracy of the model if using SVM to build predictive models for all sub-sequences. This paper proposes using GM(at least four data can create models) and SVM to build predictive models of stationary scale sub-sequence and changing details sub-sequences, respectively. The new prediction model is applied to predict PH values of Wuliangsuhai, which is compared with the traditional models based on SVM and BP neural network. The results show that the accuracy of the new model is inadequate in the individual monitoring date, but its overall effect of prediction is better than the traditional models, the average relative error is reduced from 0.88 to 0.51.
As the sub-sequence decomposed by Db N having different properties, a large number of input training data will affect the prediction accuracy of the model if using SVM to build predictive models for all sub-sequences. This paper proposes using GM(at least four data can create models) and SVM to build predictive models of stationary scale sub-sequence and changing details sub-sequences, respectively. The new prediction model is applied to predict PH values of Wuliangsuhai, which is compared with the traditional models based on SVM and BP neural network. The results show that the accuracy of the new model is inadequate in the individual monitoring date, but its overall effect of prediction is better than the traditional models, the average relative error is reduced from 0.88 to 0.51.
引文
[1]孙国红,沈跃,徐应明,等.基于Box-Jenkins方法的黄河水质时间序列分析与预测[J].农业环境科学学报,2011,30(9):1888-1895.
[2]Chang K,Gao J L,Chen M L,etc.Urban Daily Water Demand Short-term Forecasts Based on the Chaos Theory[A].//Guo M Z.Fourth International Conference on Natural Computation.IEEE Computer Society,2008:696-699
[3]Kunwar P S,Ankita B,Amrita M,etc.Artificial neural network modeling of the river water quality—A case study[J].Ecological Modeling,2009,220:888-895
[4]李如忠.水质预测模式理论研究进展与趋势分析[J].合肥工业大学学报,2006,29(1):26-30.
[5]Xu L,Liu S.Study of short-term water quality prediction model based on wavelet neural network[J],Mathematical and Computer Modelling,2012,58:807-813
[6]何斯雯,谢正文,黄雅楠,等.基于指数平滑技术的水体污染灰色预测模型及应用[J].环境科学与管理,2009,34(8):169-172
[7]Thissen U,van Brakel R,de Weijer A P,etc.Using support vector machines for time series prediction[J].Chemometrics and Intelligent Laboratory Systems,2003,69:35-49
[8]Tan G.H,Yan J Z,Gao C,etc.Prediction Water Quality Times Series Data Based on Least Squares Support Vector[J].Proeedia Enihineering,2012,31:1194-1199
[9]Liu W,Wang G Y,Fu J Y,etc.Water Quality Prediction Based on Improved Wavelet Transformation and Support Vector Machine[A].//Zhao J.the 2013/2nd International Conference on Energy and Environmental Protection[C].Trans Tech Publications Inc,2013,726-731:3547-3553
[10]杨虞微,左洪福,陈果.支持向量机时间序列预测模型的参数影响分析与自适应优化[J].航空动力学报,2006,21(4):767-772.
[11]武国正,徐宗学,李畅游.支持向量回归机在水质预测中的应用与验证[J].中国农村水利水电,2012,1:25-29.
[12]荣海娜,张葛祥,金炜东.系统辨识中支持向量机核函数及其参数的研究[J].系统仿真学报,2006,18(11):3204-3208.
[13]雷英杰,张善文,李续武,等.MATLAB遗传算法工具箱及应用[M].西安:西安电子科技大学出版社,2005:34-36.
[14]Hsu C W,Chang C C,Lin C J.A practical guide to support vector classification[EB/OL].http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.
[15]MALLAT S G.A theory for multiresolution signal decomposition:the wavelet representation.IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(7),p.674-693
[16]周伟,桂林,周林,等.MATLAB小波分析高级技术[M].西安:西安电子科技大学出版社,2006:51-63.
[2]Chang K,Gao J L,Chen M L,etc.Urban Daily Water Demand Short-term Forecasts Based on the Chaos Theory[A].//Guo M Z.Fourth International Conference on Natural Computation.IEEE Computer Society,2008:696-699
[3]Kunwar P S,Ankita B,Amrita M,etc.Artificial neural network modeling of the river water quality—A case study[J].Ecological Modeling,2009,220:888-895
[4]李如忠.水质预测模式理论研究进展与趋势分析[J].合肥工业大学学报,2006,29(1):26-30.
[5]Xu L,Liu S.Study of short-term water quality prediction model based on wavelet neural network[J],Mathematical and Computer Modelling,2012,58:807-813
[6]何斯雯,谢正文,黄雅楠,等.基于指数平滑技术的水体污染灰色预测模型及应用[J].环境科学与管理,2009,34(8):169-172
[7]Thissen U,van Brakel R,de Weijer A P,etc.Using support vector machines for time series prediction[J].Chemometrics and Intelligent Laboratory Systems,2003,69:35-49
[8]Tan G.H,Yan J Z,Gao C,etc.Prediction Water Quality Times Series Data Based on Least Squares Support Vector[J].Proeedia Enihineering,2012,31:1194-1199
[9]Liu W,Wang G Y,Fu J Y,etc.Water Quality Prediction Based on Improved Wavelet Transformation and Support Vector Machine[A].//Zhao J.the 2013/2nd International Conference on Energy and Environmental Protection[C].Trans Tech Publications Inc,2013,726-731:3547-3553
[10]杨虞微,左洪福,陈果.支持向量机时间序列预测模型的参数影响分析与自适应优化[J].航空动力学报,2006,21(4):767-772.
[11]武国正,徐宗学,李畅游.支持向量回归机在水质预测中的应用与验证[J].中国农村水利水电,2012,1:25-29.
[12]荣海娜,张葛祥,金炜东.系统辨识中支持向量机核函数及其参数的研究[J].系统仿真学报,2006,18(11):3204-3208.
[13]雷英杰,张善文,李续武,等.MATLAB遗传算法工具箱及应用[M].西安:西安电子科技大学出版社,2005:34-36.
[14]Hsu C W,Chang C C,Lin C J.A practical guide to support vector classification[EB/OL].http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.
[15]MALLAT S G.A theory for multiresolution signal decomposition:the wavelet representation.IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(7),p.674-693
[16]周伟,桂林,周林,等.MATLAB小波分析高级技术[M].西安:西安电子科技大学出版社,2006:51-63.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |