基于Pearson关联度BP神经网络的时间序列预测

王可; 王慧琴; 殷颖; 毛力; 张毅

doi:10.3788/OPE.20182611.2805

您当前的位置：

首页 >

文章列表页 >

基于Pearson关联度BP神经网络的时间序列预测

信息科学 | 更新时间：2020-07-05

- 基于Pearson关联度BP神经网络的时间序列预测
- Time series prediction method based on Pearson correlation BP neural network
- 光学精密工程 2018年26卷第11期页码：2805-2813
- 作者机构：
  
  1.西安建筑科技大学信息与控制工程学院, 陕西西安 710055
  2.西安建筑科技大学管理学院, 陕西西安 710055
- 作者简介：
  
  [ "王可(1981-), 男, 山东荣成人, 讲师, 博士研究生, 2004年、2007年于西南交通大学分别获得学士、硕士学位, 主要从事数字图像处理及机器学习方面的研究。E-mail:wangke@xauat.edu.cn" ]
  [ "王慧琴(1970-), 女, 山西长治人, 教授, 博士生导师, 1992年、1997年于西安建筑科技大学分别获得学士、硕士学位, 2002年于西安交通大学获得博士学位, 主要从事数字图像处理及信息管理系统方面的研究。E-mail:hqwang@xauat.edu.cn" ]
- 基金信息：
  
  国家自然科学基金青年基金资助项目(61701388);住建部科学技术计划资助项目(2017-K2-014);陕西省科技厅国际合作资助项目(2017KW-036);陕西省自然科学基础研究计划资助项目(2018JM5127);陕西省自然科学基础研究计划资助项目(2018JM6080);西安市科技局软科学资助项目(2016043SF/RK06（3）);西安市碑林区科技计划资助项目(GX1606);西安建筑科技大学青年基金项目(QN1628)
- DOI：10.3788/OPE.20182611.2805
  中图分类号： TP183
- 收稿日期：2018-05-31，
  
  录用日期：2018-6-29，
  
  纸质出版日期：2018-11-25
- 稿件说明：
移动端阅览
王可, 王慧琴, 殷颖, 等. 基于Pearson关联度BP神经网络的时间序列预测[J]. 光学精密工程, 2018,26(11):2805-2813.

Ke WANG, Hui-qin WANG, Ying YIN, et al. Time series prediction method based on Pearson correlation BP neural network[J]. Optics and precision engineering, 2018, 26(11): 2805-2813.
王可, 王慧琴, 殷颖, 等. 基于Pearson关联度BP神经网络的时间序列预测[J]. 光学精密工程, 2018,26(11):2805-2813. DOI： 10.3788/OPE.20182611.2805.

Ke WANG, Hui-qin WANG, Ying YIN, et al. Time series prediction method based on Pearson correlation BP neural network[J]. Optics and precision engineering, 2018, 26(11): 2805-2813. DOI： 10.3788/OPE.20182611.2805.

摘要

针对BP神经网络存在的过拟合问题，提出了基于Pearson关联度的神经网络预测模型。将传统的基于误差反向传播的BP神经网络中的误差函数替换为Pearson关联度函数，利用梯度上升法对训练过程中神经网络的连接权重和阈值的调整量进行了推导，并为调整量添加了动量项用于提高神经网络收敛速度，然后建立了关联度反向传播预测模型，并对其权重进行了阈值限制以及增加学习率来防止过拟合。对通用数据集进行时间序列预测实验，通过与改进的RBF和BP神经网络对比，表明对于多因素时间序列的预测Pearson关联度BP神经网络的预测误差精度RMSE降低了4.02，收敛次数减少1 690代。实现了将关联分析与BP神经网络的结合，能够在保证效率的同时，解决过拟合问题，提高预测精度。

Abstract

In order to realize the over fitting problem existing in Back Propagation (BP) neural networks

a neural prediction model based on Pearson correlation was designed. It replaces the error function in a BP neural network based on error back propagation with the Pearson correlation function. By means of gradient ascent

the adjustment of connection weights and biases in training process is derived. Meanwhile

momentum is added to this adjustment to improve the convergence speed of the network. The Pearson correlation BP prediction model is built with weight threshold limiting and an increasing learning rate to prevent overfitting. Time series prediction experiments on a standard dataset were performed. The results demonstrate that compared with improved the radial basis function and BP neural networks

the Pearson correlation BP neural network reduces root-mean-square error

and time to convergence in multi-factor time series prediction. Therefore

the Pearson correlation BP neural network realizes the integration of correlation analysis with neural networks

is able to ensure efficiency

and can solve fitting problems in the same time as other methods with higher accuracy.

关键词

Keywords

references

LIU C X, SHU T, CHEN S. An improved grey neural network model for predicting transportation disruptions[J]. Expert Systems with Applications , 2016, 45:331-340.

TAN T, CHEN L, LIU F. Model of multiple seasonal autoregressive integrated moving average model and its application in prediction of the hand-foot-mouth disease incidence in Changsha[J]. Journal of Central South University , 2014, 39(11):1170-1176.

王民, 赵渊, 刘利, 等.基于量子粒子群优化广义回归神经网络的语音转换方法[J].液晶与显示, 2018, 33(2):165-173.

WANG M, ZHAO Y, LIU L, et al .. Voice conversion based on quantum particle swarm optimization of generalized regression neural network[J]. Chinese Journal of Liquid Crystals and Displays , 2018, 33(2):165-173.(in Chinese)

YU X L, GUO X L. Hourly photosynthetically active radiation estimation in midwestern united states from artificial neural networks and conventional regressions models[J]. Int J Biometeorol .2016, 60(8):1-13.

SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al .. Dropout:a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research , 2014, 15(1):1929-1958.

王林, 彭璐, 夏德, 等.自适应差分进化算法优化BP神经网络的时间序列预测[J].计算机工程与科学, 2015, 37(12):2270-2275.

WANG L, PENG L, XIA D, et al .. BP neural network incorporating self-adaptive differential evolution algorithm for time series forecasting[J]. Computer Engineering and Science , 2015, 37(12):2270-2275.(in Chinese)

雷雨, 蔡宏兵, 赵丹宁.利用灰色关联极限学习机预报日长变化[J].中国科学院大学学报, 2015, 32(5):588-593, 604.

LEI Y, CAI H B, ZHAO D N. Prediction of length-of-day variation using grey relational analysis and extreme learning machine[J]. Journal of University of Chinese Academy of Sciences , 2015, 32(5):588-593, 604.(in Chinese)

杜玉红, 魏坤鹏, 史屹君, 等.水质浊度红外光检测及聚类灰色融合预测模型[J].红外与激光工程, 2016, 45(10):264-270.

DU Y H, WEI K P, SHI Q J, et al .. Infrared detection and clustering grey fusion prediction model of water quality turbidity[J]. Infrared and Laser Engineering , 2016, 45(10):264-270.(in Chinese)

BAI J, PERRON P. Estimating and testing linear models with multiple structural changes[J]. Econometrics , 2007, 75(2):459-502.

SAAD Z, GLEN D G, BEAUCHAMP M, et al .. A new method for improving functional-to-structural MRI alignment using local Pearson correlation[J]. Neuroimaging , 2009, 44(3):839-848.

NIU W, CHENG J, WANG G. Applications of extension grey prediction model for power system forecasting[J]. Journal of Combinatorial Optimization , 2013, 26(3):555-567.

ARTHUR, MIRANDA, NETO. Pearson's correlation coefficient:a more realistic threshold for applications on autonomous Robotics[J]. Computer Technology and Application , 2014(2):69-72.

GOLUB G H, LOAN C F V. An analysis of the total least squares problem[J]. Siam Journal on Numerical Analysis , 1980, 17(6):883-893.

丁思敏, 吴军基.改进模糊神经网络在负荷预测中的应用研究[J].电力学报, 2009, 24(2):101-104.

DING S M, WU J J. Research on the use of improved fuzzy artificial neural network in load forecasting[J]. Journal of Electric Power , 2009, 24(2):101-104.(in Chinese)

KARHUMEN J. Applications of Machine Learning Group[EB/OL].(2015-10-21)[2018-01-15] . http://research.ics.aalto.fi/eiml/datasets.shtml http://research.ics.aalto.fi/eiml/datasets.shtml .

张小红, 王慧琴, 于洪磊, 等.基于灰色相关分析的GRFM倾斜量预测模型[J].西安建筑科技大学学报(自然科学版), 2016, 48(6):28-33.

ZHANG X H, WANG H Q, YU H L, et al .. GRFM forecasting model of inclination based on the grey relation analysis[J]. Xi'an Univ. of Arch. & Tech(Natural Science Edition) , 2016, 48(6):28-33.(in Chinese)

苗恩铭, 刘义, 董云飞, 等.数控机床热误差时间序列模型预测稳健性的提升[J].光学精密工程, 2016, 34(10):2480-2489.

MIAO E M, LIU Y, DONG Y F, et al .. Improvement of forecasting robustness of time series model for thermal error on CNC machine tool[J]. Opt. Precision Eng. , 2016, 34(10):2480-2489.(in Chinese)

郭文月, 余岸竹, 刘海砚, 等.正则化总体最小二乘用于光学线阵遥感影像定位[J].光学精密工程, 2017, 25(1):236-244.

GUO W Y, YU A ZH, LIU H Y, et al .. Regularized total least squares used in remote sensing image positioning of optical line array[J]. Opt. Precision Eng. , 2017, 25(1):236-244.(in Chinese)

王可, 王慧琴, 王展, 等.基于改进 R 矩阵方法的光谱反射率重建研究[J].液晶与显示, 2018, 33(4):78-86.

WANG K, WANG H Q, WANG ZH, et al .. Spectral reflectance reconstruction based on improved matrix R method[J]. Chinese Journal of Liquid Crystals and Displays , 2018, 33(4):78-86.(in Chinese).

浏览量

175

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

高频磁致伸缩换能器输出特性测试与优化控制

精密减速器检测仪测角误差补偿

BP神经网络在无人车避障中的应用

精密加工实验台热误差建模与补偿方法的对比分析

基于小波包和BP神经网络的周界入侵防御系统目标识别