Research and application of prediction model based on ensemble BP neural network

Huimin ZHAO; Jiangtao LUO; Junchao YANG; Zheng XU; Xiao LEI; Lin LUO

doi:10.3969/j.issn.1000-0801.2016.02.009

您当前的位置：

首页 >

文章列表页 >

Research and application of prediction model based on ensemble BP neural network

research and development | 更新时间：2024-06-05

- Research and application of prediction model based on ensemble BP neural network
- Telecommunication Science Vol. 32, Issue 2, Pages: 60-67(2016)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1000-0801.2016.02.009
  CLC： TP183
- Published Online：2016-02，
  
  Published：15 February 2016
- 稿件说明：
移动端阅览
Huimin ZHAO, Jiangtao LUO, Junchao YANG, et al. Research and application of prediction model based on ensemble BP neural network[J]. Telecommunication science, 2016, 32(2): 60-67.
DOI：

Huimin ZHAO, Jiangtao LUO, Junchao YANG, et al. Research and application of prediction model based on ensemble BP neural network[J]. Telecommunication science, 2016, 32(2): 60-67. DOI： 10.3969/j.issn.1000-0801.2016.02.009.

摘要

BP神经网络对逼近实数值提供了一种顽健有效的学习方法，适合对路口交通流量进行预测。针对BP神经网络存在易陷入局部最小值和收敛速度慢的问题，提出了一种集成BP预测模型。该模型集成多个具有不同初始权值和训练集的BP模型，并以加权平均值的方法作为结合方法。其中的每个BP模型是以一种改进的MapReduce方法实现的。将该模型运用到交通路口车辆分流流量大小的预测实例中，并依次与单机实现的单个BP模型和MapReduce实现的单个BP模型进行比较。结果表明，集成BP模型在路口车辆分流流量大小的预测中有较高的准确率和实时性。

Abstract

BP neural network provides a robust and effective learning method for approximating real values. It is fit for intersection traffic flow prediction. In order to resolve its slow convergence speed and easily falling into local minimum problem，an ensemble prediction model was proposed. This model integrated multiple BP neural networks which had different initial weights and training set and used weighted average as combination method. It had used an improved MapReduce method to implement every BP neural network of the ensemble prediction model. This ensemble prediction model took traffic shunt flow prediction at intersection as an example. At last，it was compared with simple single implementation BP model and MapReduce implementation BP model respectively. Finally，results prove that ensemble prediction model has a higher accuracy rate and real-time performance in traffic shunt flow prediction at intersection.

关键词

Keywords

references

SMITH B L ， DEMESKY M J . Traffic flow forecasting：comparison of modeling approaches [J ] . Journal of Transportation Engineering ， 1997 ， 123 （ 4 ）： 262 - 266 .

朱学明 . 基于神经网络的短时交通流预测方法的研究与应用 [D/OL ] . 兰州：兰州理工大学， 2013 [ 2013 - 10 - 30 ] . http://xueshu.baidu.com/s?wd=paperuri%3A%28cccf11993959c64f0b0fa9321a680311%29＆filter=sc_long_sign＆tn=SE_xueshusource_2kduw22v＆sc_vurl=http%3A%2F%2Fd.wanfangdata.com.cn%2FThesis%2FY2335877＆ie=utf-8 http://xueshu.baidu.com/s?wd=paperuri%3A%28cccf11993959c64f0b0fa9321a680311%29＆filter=sc_long_sign＆tn=SE_xueshusource_2kduw22v＆sc_vurl=http%3A%2F%2Fd.wanfangdata.com.cn%2FThesis%2FY2335877＆ie=utf-8 .

ZHU X M . Research and application on the short-term traffic flow prediction based on neural network [D/OL ] . Lanzhou：Lanzhou University of Technology ， 2013 [ 2013 - 10 - 30 ] . http://xueshu.baidu.com/s?wd=paperuri%3A%28cccf11993959c64f0b0fa9321a680311%29＆filter=sc_long_sign＆tn=SE_xueshusource_2kduw22v＆sc_vurl=http%3A%2F%2Fd.wanfangdata.com.cn%2FThesis%2FY2335877＆ie=utf-8 http://xueshu.baidu.com/s?wd=paperuri%3A%28cccf11993959c64f0b0fa9321a680311%29＆filter=sc_long_sign＆tn=SE_xueshusource_2kduw22v＆sc_vurl=http%3A%2F%2Fd.wanfangdata.com.cn%2FThesis%2FY2335877＆ie=utf-8 .

ZHAO J Y ， JIA L ， WANG X Q . The forecasting model of urban traffic flow based on parallel RBF neural network [C ] // The Interneational Conference on Intelligent Computing and Applications ， April 4 - 6 ， 2015 ， Wuhan，China . [ S.l.：s.n. ] ， 2005 ： 515 - 520 .

董春娇，邵春福，熊志华等 . 基于Elman神经网络的道路网短时交通流预测方法 [J ] . 交通运输系统工程与信息， 2010 ， 10 （ 1 ）： 145 - 151 .

DONG C J ， SHAO C F ， XIONG Z H ， et al . Short-term traffic flow forecasting of road network based on Elman beural network [J ] . Transportation Systems Engineering and Information Technology ， 2010 ， 10 （ 1 ）： 145 - 151 .

徐启华，杨瑞 . 支持向量机在交通流量实时预测中的应用 [J ] . 公路交通科技， 2005 ， 22 （ 12 ）： 131 - 134 .

XU Q H ， YANG R . Traffic flow prediction using support vector machine based method [J ] . Highway and Transportation Research and Development ， 2005 ， 22 （ 12 ）： 131 - 134 .

MITCHELL T M . 机器学习 [M ] . 北京：机械工业出版社， 2003 ： 60 - 90 .

MITCHELL T M . Machine Learing [M ] . Beijing ： China Machine Press ， 2003 ： 60 - 90 .

朱晨杰，杨永丽 . 基于MapReduce的BP神经网络算法研究 [J ] . 微型电脑应用， 2012 ， 28 （ 10 ）： 9 - 12 .

ZHU C J ， YANG Y LW . Research of MapReduce based on BP neural network algorithm [J ] . Microcomputer Applications ， 2012 ， 28 （ 10 ）： 9 - 12 .

BREIMAN L . Bagging predictors [J ] . Machine Learning ， 1996 ， 24 （ 2 ）： 123 - 140 .

CONNOLLY J F ， GTANGER E ， SABOURIN R . Dynamic multi-objective evolution of classifier ensembles for video face recognition [J ] . Applied Soft Computing ， 2013 ， 13 （ 6 ）： 3149 - 3166 .

SAUX B L ， SANFOURCHE M . Robust vehicle categorization from aerial images by 3d-template matching and multiple classifier system [C ] // The 7th International Symposium on Image＆Signal Processing ＆Analysis ， September 4 - 6 ， 2011 ， Dubrovnik，Croatia . New Jersey ： IEEE Press ， 2011 ： 466 - 470 .

KRAWCZYK B ， SCHAEFER G . Effective multiple classifier systems for breast thermogram analysis [C ] // The 21st Inte rnational Conference on Pattern Recognition（ICPR）， November 11 - 15 ， 2012 ， Tsukuba，Japan . New Jersey ： IEEE Press ， 2012 ： 3345 - 3348 .

尚宁，罩明贵，王亚琴，等 . 基于BP神经网络的路口短时交通流量预测方法 [J ] . 计算机应用与软件， 2006 ， 23 （ 2 ）： 32 - 33 .

SHANG N ， QIN M G ， WANG Y Q ， et al . A BP neural network method for short-term traffic flow forecasting on crossroads [J ] . Computer Applications and Software ， 2006 ， 23 （ 2 ）： 32 - 33 .

崔德光，吴淑宁，徐冰 . 空中交通流量预测的人工神经网络和回归组合方法 [J ] . 清华大学学报（自然科学版）， 2005 ， 45 （ 1 ）： 96 - 99 .

CUI D G ， WU S N ， XU B ， . Air traffic flow forecasts based on artificial neural networks combined with regression methods [J ] . Journal of Tsinghua University（Science and Technology Edition）， 2005 ， 45 （ 1 ）： 96 - 99 .

DIETTERICH T G . Ensemble Methods in Machine Learning [M ] . Berlin：Springer Berlin Heidelberg ， 2000 ： 1 - 15 .

CHU C T ， SANG K K ， LIN Y A et al . Map-reduce for machine learning on multicore [C ] // The Twentieth Annual Conference on Neural Information Processing Systems ， December 4 - 7 ， 2006 ， Vancouver，Canada . [ S.l.：s.n. ] ， 2006 ： 281 - 288 .

QUINLAN J R . Bagging，boosting，and C4.5 [EB/OL ] . （ 1996 - 08 - 04 ） [ 2015 - 03 - 11 ] . http://xueshu.baidu.com/s?wd=paperuri%3A%28c35bca131cc209561cc4f533a6cfd1a0%29＆filter=sc_long_sign＆sc_ks_para=q%3DBagging%2C%20boosting%2C%20and%20C4.S＆tn=SE_baiduxueshu_c1gjeupa＆ie=utf-8 http://xueshu.baidu.com/s?wd=paperuri%3A%28c35bca131cc209561cc4f533a6cfd1a0%29＆filter=sc_long_sign＆sc_ks_para=q%3DBagging%2C%20boosting%2C%20and%20C4.S＆tn=SE_baiduxueshu_c1gjeupa＆ie=utf-8 .

鞠训光，邵晓根，鲍蓉，等 . Hadoop下并行BP神经网络骆马湖水质分类 [J ] . 南京师大学报（自然科学版）， 2014 ， 37 （ 1 ）： 52 - 56 .

JU X G ， SHAO X G ， BAO R ， et al . Based on parallel BP neural network of classification on water quality of Luoma lake under hadoop [J ] . Journal of Nanjing Normal University（Natural Science Edition）， 2014 ， 37 （ 1 ）： 52 - 56 .

朱启敏 . 基于云计算平台的神经网络计算方法及其应用研究 [D/OL ] . 广州：华南理工大学， 2014 [ 2014 - 12 - 28 ] . http://xueshu.baidu.com/swd=paperuri%3A%28376cd6d6a7a74296f30ac11139993edc%29＆filter=sc_long_sign＆tn=SE_xueshusource_2kduw22v＆sc_vurl=http%3A%2F%2Fcdmd.cnki.com.cn%2FArticle%2FCDMD-10561-1014064144.htm＆ie=utf-8 http://xueshu.baidu.com/swd=paperuri%3A%28376cd6d6a7a74296f30ac11139993edc%29＆filter=sc_long_sign＆tn=SE_xueshusource_2kduw22v＆sc_vurl=http%3A%2F%2Fcdmd.cnki.com.cn%2FArticle%2FCDMD-10561-1014064144.htm＆ie=utf-8 .

ZHU Q M . Research on computation methods of neural networks and applications based on a cloud computing platform（master dessertation） . Guangzhou：South China University of Technology ， 2014 [ 2014 - 12 - 28 ] . http://xueshu.baidu.com/swd=paperuri%3A%28376cd6d6a7a74296f30ac11139993edc%29＆filter=sc_long_sign＆tn=SE_xueshusource_2kduw22v＆sc_vurl=http%3A%2F%2Fcdmd.cnki.com.cn%2FArticle%2FCDMD-10561-1014064144.htm＆ie=utf-8 http://xueshu.baidu.com/swd=paperuri%3A%28376cd6d6a7a74296f30ac11139993edc%29＆filter=sc_long_sign＆tn=SE_xueshusource_2kduw22v＆sc_vurl=http%3A%2F%2Fcdmd.cnki.com.cn%2FArticle%2FCDMD-10561-1014064144.htm＆ie=utf-8 .

南京交通RFID及车牌识别数据集（样例版） [EB/OL ] . （ 2015 - 04 - 20 ） [ 2015 - 05 - 21 ] . http://www.datatang.com/data/47187 http://www.datatang.com/data/47187 .

Views

1117

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on control strategy of bidirectional DC-DC converter based on improved genetic algorithm

Research on POI quality prediction based on KPCA-GA-BP neural network

A novel deep learning based time-varying channel prediction method

BP neural network based Doppler frequency offset estimation method for 5G high-speed mobile system

A distributed high efficiency similarity matrix computation method based on users’ mobile network access location

Related Author

ZHOU Hongxi

LIU Yang

CHEN Zhuaixia

GAO Feifan

LI Can

CHEN Can

LI Li

Dan YANG

Related Institution

State Grid Information & Telecommunication Co., Ltd.

Chongqing Branch of China Mobile Communications Group Design Institute Co., Ltd.

Yunnan Branch of China Mobile Communications Group Co., Ltd.

School of Electronics and Information,Wuhan University

Wuhan Ship Communication Research Institute

⁰