[1]余 洋,万定生.基于 WNN-SVM 的水文时间序列预测方法研究[J].计算机技术与发展,2019,29(09):13-17.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 003]
　YU Yang,WAN Ding-sheng.Research on Hydrological Time Series Prediction Method Based on WNN-SVM[J].,2019,29(09):13-17.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 003]
点击复制

基于 WNN-SVM 的水文时间序列预测方法研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年09期
页码:
13-17
栏目:
智能、算法、系统工程
出版日期:
2019-09-10

文章信息/Info

Title:
Research on Hydrological Time Series Prediction Method Based on WNN-SVM
文章编号:
1673-629X(2019)09-0013-05
作者:
余 洋; 万定生
河海大学 计算机与信息学院,江苏 南京 211100
Author(s):
YU Yang; WAN Ding-sheng
School of Computer and Information,Hohai University,Nanjing 211100,China
关键词:
均值归一化; 组合模型; 时间序列预测; 小波神经网络; 支持向量机
Keywords:
mean normalization; combined model; time series prediction; WNN; SVM
分类号:
TP39
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 09. 003
摘要:
在面对具有随机性、突变性的复杂时间序列数据(如流量等水文时间序列数据)时,传统单一的模型的预测精度不尽人意,对单一模型的优化不能完全克服其局限性。 因此,文中提出一种基于 WNN-SVM 组合的水文时间序列预测模型。首先对水文时间序列数据作均值归一化处理,然后对预处理后的水文时间序列进行小波分解,将分解后的子序列通过相空间重构的方法使其从低维时间序列向高维转换;根据其分解后的特点,对尺度变换序列采用支持向量机(SVM)进行建模预测,小波变换序列采用小波神经网络(WNN)进行建模预测,再将两者的预测结果进行小波重构,得到原始序列预测值。 随后采用屯溪流域 1980 年至 2007 年 43 996 个小时流量数据进行实验验证,结果表明该模型的预测精度高于单一模型,证明了该模型的有效性。
Abstract:
When faced with hydrological time series data with randomness and inconsistency,such as flow,etc. ,the prediction accuracy of traditional single model is not satisfactory,and the optimization of single model cannot completely overcome its limitations. Therefore,we present a hydrological time series prediction model based on WNN-SVM combination. First of all,the hydrological time series data are normalized by means,and then the wavelet decomposition is performed on the pretreatment hydrological time series and the low-dimensional time series is transformed to high - dimensional by phase space reconstruction. According to the characteristics of decomposition,the scaling sequence is modeled and predicted by support vector machine (SVM),and the wavelet transform sequence is modeled and predicted by wavelet neural network (WNN),and the predicted value of the original sequence is obtained after the wavelet reconstruction of the predicted result. The experiment of 43 996 data of hourly flow in Tunxi basin from 1980 to 2007 indicates that the rediction accuracy of the model is higher than that of a single model,which proves the validity of the model.

相似文献/References:

[1]周燕 姜浩.面向动态工作流的Web服务组合模型研究[J].计算机技术与发展,2008,(01):63.
　ZHOU Yan,JIANG Hao.Study on Dynamic- Workflow Oriented Web Service Composition Model[J].,2008,(09):63.
[2]成云,成孝刚,谈苗苗,等. 基于ARIMA和小波神经网络组合模型的交通流预测[J].计算机技术与发展,2017,27(01):169.
　CHENG Yun,CHENG Xiao-gang,TAN Miao-miao,et al. Traffic Flow Prediction Based on Hybrid Model of ARIMA and WNN[J].,2017,27(09):169.
[3]王荣波,王亚杰,黄孝喜,等.基于多算法融合的移动通信客户流失预测模型[J].计算机技术与发展,2018,28(08):152.[doi:10.3969/ j. issn.1673-629X.2018.08.032]
　WANG Rong-bo,WANG Ya-jie,HUANG Xiao-xi,et al.Customer Churn Prediction Model of Mobile Communication Based on Multi-algorithm Fusion[J].,2018,28(09):152.[doi:10.3969/ j. issn.1673-629X.2018.08.032]

更新日期/Last Update: 2019-09-10