基于支持向量机的高速公路交通量预测研究
|
摘要
交通量的预测是提高交通运输管理水平、降低运输成本的重要手段之一,同时也是进行交通状况评价、路网规划、线路改造以及工程建设项目可行性分析的基础。因此,研究高速公路交通量预测具有重要的意义。
本文在深入分析比较各种交通量预测方法的基础上,研究了利用支持向量机进行交通量预测方法并进行了实际应用。首先,对收费站出口数据进行了数据预处理,使之转化为预测分析数据集。然后,深入的研究了灰色理论预测方法和神经网络预测方法,并使用这些方法对现有数据集进行对比预测。重点研究了支持向量机预测模型的建模方法,包括数据归一化、核函数选择、模型参数选择等,建立了基于支持向量机的交通量预测模型,对西潼高速公路的渭南西与渭南东两站间的路段进行了交通量预测,平均误差率仅为2.5%。最后对基于支持向量机交通量预测软件进行了详细设计。
预测结果表明,支持向量机用于交通量的预测是可行及有效的。所研究的支持向量机预测模型在陕西省公路资源整合项目的“综合分析决策支持系统”中得到了应用。
Traffic prediction is one of the important means to improve the transportation management level and reduce the cost of transportation. Simultaneously, it is also the foundation of road network planning, traffic evaluation and feasibility analysis of construction projects.Therefore, the research on highway traffic prediction has important significance.
Based on the analysis and comparation of various traffic prediction methods, traffic prediction method using support vector machine (SVM) and conducted practical application are studied in this paper. First, the toll data of export is preprocessed into prediction analysis data sets.Then, the grey prediction methods and neural network prediction methods are researched, and these methods are used to conduct comparison of prediction about existing data sets in the paper. Support vector machine prediction model, including data normalization, selection of kernel function, selection of model parameter etc. are deeply studied. After that, the forecasting model of traffic based on support vector machine is established. The model is used to predict the road traffic between the station of Weinan Xi and Weinan Dong in Xitong highway, the average error is limited 2.5%.Finally, the paper gave the detailed design of support vector machine forecasting method based on support vector machine.
The prediction results show that the prediction of traffic using the support vector machine (SVM) is feasible and effective.The support vector machine prediction model has been applied in "comprehensive analysis and decision support system" for road resource integration project of Shaanxi province.
本文在深入分析比较各种交通量预测方法的基础上,研究了利用支持向量机进行交通量预测方法并进行了实际应用。首先,对收费站出口数据进行了数据预处理,使之转化为预测分析数据集。然后,深入的研究了灰色理论预测方法和神经网络预测方法,并使用这些方法对现有数据集进行对比预测。重点研究了支持向量机预测模型的建模方法,包括数据归一化、核函数选择、模型参数选择等,建立了基于支持向量机的交通量预测模型,对西潼高速公路的渭南西与渭南东两站间的路段进行了交通量预测,平均误差率仅为2.5%。最后对基于支持向量机交通量预测软件进行了详细设计。
预测结果表明,支持向量机用于交通量的预测是可行及有效的。所研究的支持向量机预测模型在陕西省公路资源整合项目的“综合分析决策支持系统”中得到了应用。
Traffic prediction is one of the important means to improve the transportation management level and reduce the cost of transportation. Simultaneously, it is also the foundation of road network planning, traffic evaluation and feasibility analysis of construction projects.Therefore, the research on highway traffic prediction has important significance.
Based on the analysis and comparation of various traffic prediction methods, traffic prediction method using support vector machine (SVM) and conducted practical application are studied in this paper. First, the toll data of export is preprocessed into prediction analysis data sets.Then, the grey prediction methods and neural network prediction methods are researched, and these methods are used to conduct comparison of prediction about existing data sets in the paper. Support vector machine prediction model, including data normalization, selection of kernel function, selection of model parameter etc. are deeply studied. After that, the forecasting model of traffic based on support vector machine is established. The model is used to predict the road traffic between the station of Weinan Xi and Weinan Dong in Xitong highway, the average error is limited 2.5%.Finally, the paper gave the detailed design of support vector machine forecasting method based on support vector machine.
The prediction results show that the prediction of traffic using the support vector machine (SVM) is feasible and effective.The support vector machine prediction model has been applied in "comprehensive analysis and decision support system" for road resource integration project of Shaanxi province.
引文
[1]李旭宏.城市交通分布预测模型研究——系统平衡模型及其应用.东南大学学报(自然科学版).1997,27(S1)：152-155
[2]刘娟娟,朱自强,范炳全.交通出行分布估计方法研究.上海理工大学学报.1999,21(1)：63-67
[3]段进宇,缪立新,江见鲸.由路段交通流量反估出行OD矩阵技术的应用.清华大学学报(自然科学版).2000,40(6)：123-126
[4]达庆东,张国伍,姜学峰.交通分布与熵.公路交通科技.1999,16(S1)：36-39
[5]李景,彭国雄,由路段交通量推算OD出行量方法研究——基于多路径概率分配模型的迭代反推法.交通运输工程学报.2001,1(2)：78-82
[6]曲昭伟,姚荣涵,王殿海.基于最大信息熵原理的居民出行分布模型.吉林大学学报(工学版).2003,33(2)：15-19
[7]Vapnik V.张学工译.统计学习理论的本质[M].北京：清华大学出版社.2000：1-211
[8]Vapnik V. Statistical Learning Theory[M].New York:John Wiley&Sons,1998.
[9]Osuna E, Freund R, Girosi F. An Improved Training Algorithm for Support VectorMachines[A].Principe J, Gile L, Morgan N. Proceedings of the 1997 IEEE Workshop on Neural Networks for Signal Processing[C].New York:IEEE,1997, 276-285.
[10]Joachims T. Making Large-Scale SVM Learning Practical[A].Scholkopf B,Burges C, Smola A. Advances in Kernel Method-Support Vector Learning[C].Cambrige,MA: MITPress,1999:169-184.
[11]Platt J. Fast training of support vector machines using sequential minimal optimization[A]. In:Scholkph B, Burges C, Smola A, editors. Advances in Kernel Method-Support Vector Learning[C].Cambridge, MA:MITPress,1998:185-208
[12]Keerthi S,Gilbert E. Convergence of a Generalized SMO Algorithm for SVM classifierdesign[J].Machine learning,2002,46(1):351-360
[13]董振海.精通MATLAB7编程与数据库应用[M].北京：电子工业出版社.2007：329-370
[14]罗芳琼,吴春梅.时间序列分析的理论与应用综述[J].柳州师专学报,2009,24(3)
[15]刘思峰,郭天榜,党耀国等著.灰色系统理论及其应用[M].北京：科学出版社,1999：134-174
[16]邓聚龙.灰色预测与决策[M].武昌：华中理工大学出版社,1986：108-134
[17]ISHAK SHERIF S.Application Of Artificial Neural Networks To Automatic Freeway Incident Detection[D].Orlando:University of Central Florida,1998:29-31
[18]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M].北京：电子工业出版社,2005：1-4,21-23
[19]阎平凡.人工神经网络与模拟进化计算[M].北京：清华大学出版社.2003
[20]Hecht-Nielsen, R. Theory of the Backpropagation Neural Network[A].Proc. International Joint Conference on Neural Network,IJCNN-89[C],1989:vol.1,593-605
[21]张德丰.MATLAB神经网络应用设计[M].北京：机械工业出版社.2009：92-182
[22]Powell M J D.Radial basis function for multivariable interpolation[A],In:Mason J C, Cox M G. Algorithms for Approximation of Functions and Data[C],New York, USA: Clarendon Press,1987:143-168
[23]Moody J, Darken C.Learning with Localized Receptive Fields[C].In:Touretzky D,56 Hinton D, Sejnowski T eds.Proceedings of Connectionist Models, Carnegie Mellon University, Morgan Kaufmann Publishers,1988:133-143
[24]Moody J, Darken C.Fast Learning in Networks of Locally-tuned Processing Units[J]. Neural Computation,1989,2(1):281-294
[25]王永骥,涂健.神经元网络控制[M].北京：机械工业出版社,1999：78-80
[26]S.Chen, C.F. N. Cowan and P. M. Grant. Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks[J].IEEE Trans.Neural Network,1991,2(2): 302-309
[27]周颖,郑德玲,裘之亮等.一种人工免疫与RBF神经网络结合的混合算法的应用[J].计算机工程与应用,2004,40(1)：39-40,46
[28]V. Vapnik. The Nature of Statistical learning[M].New York:Springer,1995
[29]李国正,支持向量机导论[M].北京：电子工业出版社,2003：1-110
[30]V. Vapnik, Levin E, Le Cun Y. Measuring the VC dimension of a learning machine[J]. Neural Computation,1994,6:851-876
[31]]李盼池,许少华.支持向量机在模式识别中的核函数特性分析[J].计算机工程与设计.2005,26(2)：28-30
[32]Steve Gunn, Support vector machines for classification and regression, ISIS. Southamp-ton University.1998
[33]A.Smola, Regression Estimation with Support Vector Learning Machines, Master's Thesis, Technische Universita Mu nchen, Germany,1996
[34]刘广利,杨志民.一种新的支持向晕回归预测模型[J].吉首大学学报(自然科学版),2002,23(3)：28-32
[35]Zonghai Sun, Youxin Sun. Fuzzy Support Vector Machine for Regression EstimationSystems[C],Man and Cybernetics,2003.IEEE International Conf.2003, 3(5-8):3336-3341
[36]Carozza, M. Rampone, S.Towards an incremental SVM for regression. Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Volume 6.24-27 July 2000:405-410
[37]Steve R Gunn. Support vector machines for classification and regression[R].England: University of Southampton,1998
[38]Suykens J. A. K, J.Vandewalle. Least squares support vectors machine classifiers[J]. Neural Processing Letters,1999,9(3):293-300
[39]李新军.基于支持向量机的建模预测研究(硕士学位论文).天津：天津大学.2004年
[40]相征,张太镒,孙建成.基于最小二乘支持向量机的非线性系统建模[J].系统仿真学报,2006,18(9)：2684-2688
[41]Zhao Dengfu, Wang Meng, Zhang Jiangshe. A Support Vector Machine Approach forShort-term Load Forecasting[J].Proceedings of the CSEE,2002,22(4):26-30
[2]刘娟娟,朱自强,范炳全.交通出行分布估计方法研究.上海理工大学学报.1999,21(1)：63-67
[3]段进宇,缪立新,江见鲸.由路段交通流量反估出行OD矩阵技术的应用.清华大学学报(自然科学版).2000,40(6)：123-126
[4]达庆东,张国伍,姜学峰.交通分布与熵.公路交通科技.1999,16(S1)：36-39
[5]李景,彭国雄,由路段交通量推算OD出行量方法研究——基于多路径概率分配模型的迭代反推法.交通运输工程学报.2001,1(2)：78-82
[6]曲昭伟,姚荣涵,王殿海.基于最大信息熵原理的居民出行分布模型.吉林大学学报(工学版).2003,33(2)：15-19
[7]Vapnik V.张学工译.统计学习理论的本质[M].北京：清华大学出版社.2000：1-211
[8]Vapnik V. Statistical Learning Theory[M].New York:John Wiley&Sons,1998.
[9]Osuna E, Freund R, Girosi F. An Improved Training Algorithm for Support VectorMachines[A].Principe J, Gile L, Morgan N. Proceedings of the 1997 IEEE Workshop on Neural Networks for Signal Processing[C].New York:IEEE,1997, 276-285.
[10]Joachims T. Making Large-Scale SVM Learning Practical[A].Scholkopf B,Burges C, Smola A. Advances in Kernel Method-Support Vector Learning[C].Cambrige,MA: MITPress,1999:169-184.
[11]Platt J. Fast training of support vector machines using sequential minimal optimization[A]. In:Scholkph B, Burges C, Smola A, editors. Advances in Kernel Method-Support Vector Learning[C].Cambridge, MA:MITPress,1998:185-208
[12]Keerthi S,Gilbert E. Convergence of a Generalized SMO Algorithm for SVM classifierdesign[J].Machine learning,2002,46(1):351-360
[13]董振海.精通MATLAB7编程与数据库应用[M].北京：电子工业出版社.2007：329-370
[14]罗芳琼,吴春梅.时间序列分析的理论与应用综述[J].柳州师专学报,2009,24(3)
[15]刘思峰,郭天榜,党耀国等著.灰色系统理论及其应用[M].北京：科学出版社,1999：134-174
[16]邓聚龙.灰色预测与决策[M].武昌：华中理工大学出版社,1986：108-134
[17]ISHAK SHERIF S.Application Of Artificial Neural Networks To Automatic Freeway Incident Detection[D].Orlando:University of Central Florida,1998:29-31
[18]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M].北京：电子工业出版社,2005：1-4,21-23
[19]阎平凡.人工神经网络与模拟进化计算[M].北京：清华大学出版社.2003
[20]Hecht-Nielsen, R. Theory of the Backpropagation Neural Network[A].Proc. International Joint Conference on Neural Network,IJCNN-89[C],1989:vol.1,593-605
[21]张德丰.MATLAB神经网络应用设计[M].北京：机械工业出版社.2009：92-182
[22]Powell M J D.Radial basis function for multivariable interpolation[A],In:Mason J C, Cox M G. Algorithms for Approximation of Functions and Data[C],New York, USA: Clarendon Press,1987:143-168
[23]Moody J, Darken C.Learning with Localized Receptive Fields[C].In:Touretzky D,56 Hinton D, Sejnowski T eds.Proceedings of Connectionist Models, Carnegie Mellon University, Morgan Kaufmann Publishers,1988:133-143
[24]Moody J, Darken C.Fast Learning in Networks of Locally-tuned Processing Units[J]. Neural Computation,1989,2(1):281-294
[25]王永骥,涂健.神经元网络控制[M].北京：机械工业出版社,1999：78-80
[26]S.Chen, C.F. N. Cowan and P. M. Grant. Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks[J].IEEE Trans.Neural Network,1991,2(2): 302-309
[27]周颖,郑德玲,裘之亮等.一种人工免疫与RBF神经网络结合的混合算法的应用[J].计算机工程与应用,2004,40(1)：39-40,46
[28]V. Vapnik. The Nature of Statistical learning[M].New York:Springer,1995
[29]李国正,支持向量机导论[M].北京：电子工业出版社,2003：1-110
[30]V. Vapnik, Levin E, Le Cun Y. Measuring the VC dimension of a learning machine[J]. Neural Computation,1994,6:851-876
[31]]李盼池,许少华.支持向量机在模式识别中的核函数特性分析[J].计算机工程与设计.2005,26(2)：28-30
[32]Steve Gunn, Support vector machines for classification and regression, ISIS. Southamp-ton University.1998
[33]A.Smola, Regression Estimation with Support Vector Learning Machines, Master's Thesis, Technische Universita Mu nchen, Germany,1996
[34]刘广利,杨志民.一种新的支持向晕回归预测模型[J].吉首大学学报(自然科学版),2002,23(3)：28-32
[35]Zonghai Sun, Youxin Sun. Fuzzy Support Vector Machine for Regression EstimationSystems[C],Man and Cybernetics,2003.IEEE International Conf.2003, 3(5-8):3336-3341
[36]Carozza, M. Rampone, S.Towards an incremental SVM for regression. Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Volume 6.24-27 July 2000:405-410
[37]Steve R Gunn. Support vector machines for classification and regression[R].England: University of Southampton,1998
[38]Suykens J. A. K, J.Vandewalle. Least squares support vectors machine classifiers[J]. Neural Processing Letters,1999,9(3):293-300
[39]李新军.基于支持向量机的建模预测研究(硕士学位论文).天津：天津大学.2004年
[40]相征,张太镒,孙建成.基于最小二乘支持向量机的非线性系统建模[J].系统仿真学报,2006,18(9)：2684-2688
[41]Zhao Dengfu, Wang Meng, Zhang Jiangshe. A Support Vector Machine Approach forShort-term Load Forecasting[J].Proceedings of the CSEE,2002,22(4):26-30
© 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 |