基于AdaBoost-LMBP的高速公路交通事件检测算法研究
|
摘要
高速公路的建设与发展,给人们的生活出行带来了方便和快捷,同时它所引发的安全问题也引起了人们的重视。高速公路上发生交通拥挤、交通事故等各类交通事件,不仅降低了高速公路的运输效率和运营效益,还给人们的生命和财产安全带来严重的损失。如何快速检测并及时处理交通事件,有效降低交通事件的危害成了人们高度关注的问题。交通事件检测技术的核心就是检测算法,检测算法的好坏直接影响事件的检测效率。因此,对检测算法研究有着十分重要的意义。
大多数交通事件检测算法都是通过分析交通流数据找到交通事件和交通流参数的对应关系。因此,本文首先分析交通事件和交通流参数的特性；接着学习研究BP(Back Propagation)神经网络和其学习算法,仿真分析各种优化BP学习算法后选择LM(Levenberg Marquard)算法作为本文的BP神经网络学习算法,并给出N·W(N guyen-Widrow)离散度选取法优化LMBP[4260]神经网络初始权值。在此基础上,设计基于优化后的LMBP神经网络的交通事件检测算法,算法建模过程中就LMBP神经网络结构和参数设置进行详细的设计,然后利用构建好的算法模型检测交通事件。最后,根据弱分类器差异越大集成效果越好的原则,利用交通流参数的不同组合形式构成不同网络结构的LMBP弱分类器,用AdaBoost方法集成得到LMBP模型集成系统,并建模检测交通事件。
本文采用I-880交通流数据,运用MATLAB7.10工具进行仿真,通过仿真结果分析得知,利用N-W离散度选取法优化网络初始权值提高了LMBP神经网络的收敛速度,缩短了LMBP模型检测交通事件的时间,结合AdaBoost方法又进一步提高了检测精度,获得了良好的综合检测性能。
The construction and development of the freeway has brought much convenience and efficiency to people, however, at the same time we need pay attention to the security issues caused due to it. Traffic congestion, traffic accidents and other types of traffic incidents occur on the freeway, not only reduce the transport efficiency and operational effectiveness of the freeway, and also cause plenty of serious losses of people's lives and properties. How to quickly detect and deal with traffic incidents, effectively reduce the traffic incident hazards has become a highly topical issue. The detection algorithm is the core of the traffic incident detection technology which directly impact on the performance of traffic incident detection. Therefore, the research of the detection algorithm is of great significance.
Most of the detection algorithms find the corresponding relationship of traffic incidents and traffic flow parameters by analyzing traffic flow data. Therefore, in this paper we firstly analyze the traffic incidents and traffic flow parameters'characteristics, then study the BP neural network and its learning algorithm. Finally we choose the LM algorithm in my paper after analysis and comparison of various BP algorithms and use the N-W dispersion select method to optimize LMBP neural network's initial weights. Based on those, we design traffic incident detection algorithm due to the improved LMBP neural network, and make detailed designation of LMBP network structure and parameters in the model building process, then use the built algorithm model to detect traffic incident. At last, according to the principle of "the more the difference of weak classifiers, the better the integration result", we use different combinations of traffic flow parameters to constitute LMBP weak classifiers in different network structures, and put in use of the AdaBoost method to integrate improved LMBP model, and build model to detect traffic incident.
This paper use1-880data in simulation, the result show that the use of this N-W dispersion select method optimization LMBP's initial weights greatly raise the convergence speed of the detection algorithm, further improve the detection precision in combination with the AdaBoost method and obtain a good detection performance in the end.
大多数交通事件检测算法都是通过分析交通流数据找到交通事件和交通流参数的对应关系。因此,本文首先分析交通事件和交通流参数的特性；接着学习研究BP(Back Propagation)神经网络和其学习算法,仿真分析各种优化BP学习算法后选择LM(Levenberg Marquard)算法作为本文的BP神经网络学习算法,并给出N·W(N guyen-Widrow)离散度选取法优化LMBP[4260]神经网络初始权值。在此基础上,设计基于优化后的LMBP神经网络的交通事件检测算法,算法建模过程中就LMBP神经网络结构和参数设置进行详细的设计,然后利用构建好的算法模型检测交通事件。最后,根据弱分类器差异越大集成效果越好的原则,利用交通流参数的不同组合形式构成不同网络结构的LMBP弱分类器,用AdaBoost方法集成得到LMBP模型集成系统,并建模检测交通事件。
本文采用I-880交通流数据,运用MATLAB7.10工具进行仿真,通过仿真结果分析得知,利用N-W离散度选取法优化网络初始权值提高了LMBP神经网络的收敛速度,缩短了LMBP模型检测交通事件的时间,结合AdaBoost方法又进一步提高了检测精度,获得了良好的综合检测性能。
The construction and development of the freeway has brought much convenience and efficiency to people, however, at the same time we need pay attention to the security issues caused due to it. Traffic congestion, traffic accidents and other types of traffic incidents occur on the freeway, not only reduce the transport efficiency and operational effectiveness of the freeway, and also cause plenty of serious losses of people's lives and properties. How to quickly detect and deal with traffic incidents, effectively reduce the traffic incident hazards has become a highly topical issue. The detection algorithm is the core of the traffic incident detection technology which directly impact on the performance of traffic incident detection. Therefore, the research of the detection algorithm is of great significance.
Most of the detection algorithms find the corresponding relationship of traffic incidents and traffic flow parameters by analyzing traffic flow data. Therefore, in this paper we firstly analyze the traffic incidents and traffic flow parameters'characteristics, then study the BP neural network and its learning algorithm. Finally we choose the LM algorithm in my paper after analysis and comparison of various BP algorithms and use the N-W dispersion select method to optimize LMBP neural network's initial weights. Based on those, we design traffic incident detection algorithm due to the improved LMBP neural network, and make detailed designation of LMBP network structure and parameters in the model building process, then use the built algorithm model to detect traffic incident. At last, according to the principle of "the more the difference of weak classifiers, the better the integration result", we use different combinations of traffic flow parameters to constitute LMBP weak classifiers in different network structures, and put in use of the AdaBoost method to integrate improved LMBP model, and build model to detect traffic incident.
This paper use1-880data in simulation, the result show that the use of this N-W dispersion select method optimization LMBP's initial weights greatly raise the convergence speed of the detection algorithm, further improve the detection precision in combination with the AdaBoost method and obtain a good detection performance in the end.
引文
[1]刘伟铭.高速公路系统控制方法.人民交通出版社,1998
[2]赵祥模,靳引利,张洋.高速公路监控系统理论及应用.电子工业出版社,2003：30-39
[3]陈祥梅GA-SVM在高速公路交通事件检测中的应用研究.西南交通大学.2009：3-49
[4]Persaud B. N, Hall F. L. Catastrophe theory and patterns in 30 second freeway traffic data implications for incident detection. Transportation research. Part A:general, 1989,23(2):103-113
[5]张敬磊,王晓原.交通事件检测算法研究进展.武汉理工大学学报：交通科学与工程版.2005,29(002)：215-218
[6]C.L.Dudek, C.J.Messer, N.B.Nuckles. Incident Detection on Urban Freeway. TRB.Transportation Research Record. Washington D C,1974:12-24
[7]Levin M, Krause G. M. Incident detection:A Bayesian approach. 1978
[8]Ahmed M, Cook A. Analysis of Freeway Traffic Time Series Data by Using Box-Jenkins Techniques. Transportation Research Board. 1987,722:1-9
[9]Willsky.S. Dynamic Model-based Techniques for the Detection of Incident on Freeway.IEEE Trans.Autom.Control.1980, No.25:347-360
[10]Chew.R.L and Ritchie.S.G. Automatic Detection of Lane-blocking Freeway Indents Using Artificial Neural Network. Transportation Research Part C.1995,3(6): 371-388
[11]Hsiao C. H, Lin C. Application of Fuzzy Logic and Neural Networks to Automatically Detect Freeway Traffic Incident. Journal of Transportation Engineering. 1993
[12]Chang E. C, Wang S. H. Improved Freeway Incident Detection using Fuzzy Set Theory. Transportation Research Board.1994,21(7):75-82
[13]Abdulhai B., Ritchie S. G Enhancing the universality and transferability of freeway incident detection using a Bayesian-based neural network. Transportation Research Part C.1999,7(5):261-280
[14]M.R.Berthold and J.Diamond. Constructive training of probabilistic neural n etworks. Neurocomputing. PP,1998:167-183
[15]邓卫,李峻利.高速公路常发性与偶发性交通挤的判别.东南大学学报：自然科学版.1994,24(002)：60-65
[16]李文江,荆便顺,杨光王.基于小波分析的事件检测算法.西安公路交通大学学报.1997,17(2B)：134-138
[17]姜紫峰,刘小坤.基于神经网络的交通事件检测算法.西安公路交通大学学报.2001
[18]姜桂艳,温慧敏,杨兆升.高速公路交通事件自动检测系统与算法设计.交通运输工程学报.2001,1(001)：77-81
[19]吕琪,王慧.基于动态神经网络模型的交通事件检测算法.公路交通科技.2003,20(6)：105-108
[20]樊小红,荆便顺.基于遗传算法的交通事件检测.长安大学学报(自然科学版).2005,25(4)：70-72
[21]梁新荣,刘智勇.基于支持向量机的高速公路事件检测.计算机工程与应用.2006,1(16)：213-218
[22]Chen S, Wang W, Van Zuylen H. Construct support vector machine ensemble to detect traffic incident. Expert Systems with Applications, 2009
[23]朱红斌.基于Bagging算法和遗传神经网络的交通事件检测.计算机应用与软件.2010,1(27)：234-236
[24]张良春,夏利民.基于Adaboost方法的高速公路事件检测.计算机工程与应用.2007,43(28)：230-232
[25]党长青,张景辉,沈志远.基于Boosting算法和RBF神经网络的交通事件检测.计算机应用.2007,27(12)：3105-3107
[26]张凯.高速公路交通事件检测与仿真研究.长安大学.2009
[27]孟建军.基于动态交通模型和多信息融合的高速公路交通事件检测算法.河海大学.2007
[28]张洋.高速公路交通事件检测与管理系统研究.北京航空航天大学.2002
[29]覃频频.基于信息融合的高速公路事件检测建模与仿真.西南交通大学.2007
[30]Teng H, Qi Y. Detection-delay-based freeway incident detection algorithms. Transportation Research Part C, 2003,11(3-4):265-287
[31]史新宏,蔡伯根.高速公路自动事件检测算法.交通运输系统工程与信息.2001,1(004)：306-310
[32]温慧敏,杨兆升.交通事件检测技术的进展研究.交通运输系统工程与信启、.2005,5(001)：25-28
[33]陈斌.高速公路交通意外事件管理关键技术.西南交通大学出版社,2007
[34]Karl Petty, the Analyss Software for the FSP Project[OL], http://ipa.eecs.berkeley.edu/-pettyk/FSP/.2005-01-01
[35]龚炯.基于SVM的高速公路交通事件检测研究.西南交通大学.2010：10-47
[36]汪坦岳.基于LM-BP神经网络入侵检测系统的研究与实现.湖南大学.2007
[37]Rumelhart D E, Mcclelland J L. Paranllel Distributed Processing. The MIT Press, Cambridge, 1986
[38]李驰新.基于神经网络的交通事件检测系统研究.兰州理工大学.2006
[39]陈强.高速公路交通流特征参数被动声学检测技术研究.吉林大学.2005
[40]周永进.BP网络的改进及其应用.南京信息工程大学.2007
[41]Martin T.Hagan, Howard B.emuth, Mark H.Beale神经网络设计,机械出版社,2002
[42]于庆明LMBP算法的改进及其在远程故障诊断系统中的应用.山东科技大学.2008
[43]孙娓娓.BP神经网络算法改进及应用研究.重庆大学.2009：23-28
[44]李敏生,刘斌.BP学习算法的改进与应用.北京理工大学学报.1999,19(6)：721-724
[45]左志强,陈永进,慈春令.基于MATLAB下的改进BP算法.燕山大学学报.2001,25(12)：101-104
[46]R.A.Jacobs. Increased Rates of Convergence through Learning Rate Adaptation.Neural Networks.1988,1(4):295-307
[47]阎平凡,张长水.人工神经网络与模拟进化计算.清华大学出版社,2005
[48]肖伟,周东辉,孙建风.初始权值优化技术在机器人学习中的应用.电子学报.2005,33(9)：1720-1722
[49]Derrick Nguyen,Bernard Widrow,Improving the Learning Speed of 2-layer Neural Networks by Choosing Initial Values of the Adaptive Weights, IEEE Trans.1990,2:21-26
[50]姜绍飞.人工神经网络用于建筑工程领域的数据处理方法.哈尔滨建筑大学学报.1999,1(5)：24-32
[51]王钰,周志华,周傲英.机器学习及其应用.清华大学出版社,2006
[52]Freund Y., Schapire R. A desicion-theoretic generalization of on-line learning and an application to boosting, 1997[C]. Springer.
[53]Schapire R. E. The strength of weak learnability. Machine learning. 1990, 5(2):197-227
[54]陈斌.高速公路意外事件影响下的车辆行为模型与事件检测研究.西南交通大学.2005
[55]王丽丽.集成学习算法研究.广西大学.2006：21-30
[56]Zhou Z-H,Wu J,Tang W.Ensembling neural networks:many could be better than all.Artificial Intelligence.2002,137(1-2):239-263
[57]Sandhya Samarasinghe著,史晓霞等译.神经网络在应用科学和工程中的应用：从基本原理到复杂的模式识别.机械工业出版社,2010
[58]Petty K. F., Noeimi H., Sanwal K.. The freeway service patrol evaluation project: Database support programs, and accessibility. Transportation Research Part C: Emerging Technologies.1996,4(2):71-85
[59]Fang Yuan, Ruey Long Cheu. Incident detection using support vector machines.Transportation Research.2003, Part(11):309-328
[60]陈军.改进的LMBP算法在组合式非周期缺陷接地结构建模中的应用.天津大学.2007：21-43
[61]何忠华.城市需水量的预测研究.安徽理工大学.2009：10-16
[62]王成福.视频扫描表头识别系统的研究与实现.华北电力大学.2008：21-23
[63]刘超.免疫前馈神经网络在传感器故障诊断中的应用.苏州大学.2008：26-28
[64]席宁.基于数据挖掘的企业库存管理系统研究.天津大学.2008：9-10
[65]马冉冉.集成学习算法研究.山东科技大学.2010：8-25
[66]钮冰.基于集成学习算法的若干生物信息学问题研究.上海大学.2008：13-17
[2]赵祥模,靳引利,张洋.高速公路监控系统理论及应用.电子工业出版社,2003：30-39
[3]陈祥梅GA-SVM在高速公路交通事件检测中的应用研究.西南交通大学.2009：3-49
[4]Persaud B. N, Hall F. L. Catastrophe theory and patterns in 30 second freeway traffic data implications for incident detection. Transportation research. Part A:general, 1989,23(2):103-113
[5]张敬磊,王晓原.交通事件检测算法研究进展.武汉理工大学学报：交通科学与工程版.2005,29(002)：215-218
[6]C.L.Dudek, C.J.Messer, N.B.Nuckles. Incident Detection on Urban Freeway. TRB.Transportation Research Record. Washington D C,1974:12-24
[7]Levin M, Krause G. M. Incident detection:A Bayesian approach. 1978
[8]Ahmed M, Cook A. Analysis of Freeway Traffic Time Series Data by Using Box-Jenkins Techniques. Transportation Research Board. 1987,722:1-9
[9]Willsky.S. Dynamic Model-based Techniques for the Detection of Incident on Freeway.IEEE Trans.Autom.Control.1980, No.25:347-360
[10]Chew.R.L and Ritchie.S.G. Automatic Detection of Lane-blocking Freeway Indents Using Artificial Neural Network. Transportation Research Part C.1995,3(6): 371-388
[11]Hsiao C. H, Lin C. Application of Fuzzy Logic and Neural Networks to Automatically Detect Freeway Traffic Incident. Journal of Transportation Engineering. 1993
[12]Chang E. C, Wang S. H. Improved Freeway Incident Detection using Fuzzy Set Theory. Transportation Research Board.1994,21(7):75-82
[13]Abdulhai B., Ritchie S. G Enhancing the universality and transferability of freeway incident detection using a Bayesian-based neural network. Transportation Research Part C.1999,7(5):261-280
[14]M.R.Berthold and J.Diamond. Constructive training of probabilistic neural n etworks. Neurocomputing. PP,1998:167-183
[15]邓卫,李峻利.高速公路常发性与偶发性交通挤的判别.东南大学学报：自然科学版.1994,24(002)：60-65
[16]李文江,荆便顺,杨光王.基于小波分析的事件检测算法.西安公路交通大学学报.1997,17(2B)：134-138
[17]姜紫峰,刘小坤.基于神经网络的交通事件检测算法.西安公路交通大学学报.2001
[18]姜桂艳,温慧敏,杨兆升.高速公路交通事件自动检测系统与算法设计.交通运输工程学报.2001,1(001)：77-81
[19]吕琪,王慧.基于动态神经网络模型的交通事件检测算法.公路交通科技.2003,20(6)：105-108
[20]樊小红,荆便顺.基于遗传算法的交通事件检测.长安大学学报(自然科学版).2005,25(4)：70-72
[21]梁新荣,刘智勇.基于支持向量机的高速公路事件检测.计算机工程与应用.2006,1(16)：213-218
[22]Chen S, Wang W, Van Zuylen H. Construct support vector machine ensemble to detect traffic incident. Expert Systems with Applications, 2009
[23]朱红斌.基于Bagging算法和遗传神经网络的交通事件检测.计算机应用与软件.2010,1(27)：234-236
[24]张良春,夏利民.基于Adaboost方法的高速公路事件检测.计算机工程与应用.2007,43(28)：230-232
[25]党长青,张景辉,沈志远.基于Boosting算法和RBF神经网络的交通事件检测.计算机应用.2007,27(12)：3105-3107
[26]张凯.高速公路交通事件检测与仿真研究.长安大学.2009
[27]孟建军.基于动态交通模型和多信息融合的高速公路交通事件检测算法.河海大学.2007
[28]张洋.高速公路交通事件检测与管理系统研究.北京航空航天大学.2002
[29]覃频频.基于信息融合的高速公路事件检测建模与仿真.西南交通大学.2007
[30]Teng H, Qi Y. Detection-delay-based freeway incident detection algorithms. Transportation Research Part C, 2003,11(3-4):265-287
[31]史新宏,蔡伯根.高速公路自动事件检测算法.交通运输系统工程与信息.2001,1(004)：306-310
[32]温慧敏,杨兆升.交通事件检测技术的进展研究.交通运输系统工程与信启、.2005,5(001)：25-28
[33]陈斌.高速公路交通意外事件管理关键技术.西南交通大学出版社,2007
[34]Karl Petty, the Analyss Software for the FSP Project[OL], http://ipa.eecs.berkeley.edu/-pettyk/FSP/.2005-01-01
[35]龚炯.基于SVM的高速公路交通事件检测研究.西南交通大学.2010：10-47
[36]汪坦岳.基于LM-BP神经网络入侵检测系统的研究与实现.湖南大学.2007
[37]Rumelhart D E, Mcclelland J L. Paranllel Distributed Processing. The MIT Press, Cambridge, 1986
[38]李驰新.基于神经网络的交通事件检测系统研究.兰州理工大学.2006
[39]陈强.高速公路交通流特征参数被动声学检测技术研究.吉林大学.2005
[40]周永进.BP网络的改进及其应用.南京信息工程大学.2007
[41]Martin T.Hagan, Howard B.emuth, Mark H.Beale神经网络设计,机械出版社,2002
[42]于庆明LMBP算法的改进及其在远程故障诊断系统中的应用.山东科技大学.2008
[43]孙娓娓.BP神经网络算法改进及应用研究.重庆大学.2009：23-28
[44]李敏生,刘斌.BP学习算法的改进与应用.北京理工大学学报.1999,19(6)：721-724
[45]左志强,陈永进,慈春令.基于MATLAB下的改进BP算法.燕山大学学报.2001,25(12)：101-104
[46]R.A.Jacobs. Increased Rates of Convergence through Learning Rate Adaptation.Neural Networks.1988,1(4):295-307
[47]阎平凡,张长水.人工神经网络与模拟进化计算.清华大学出版社,2005
[48]肖伟,周东辉,孙建风.初始权值优化技术在机器人学习中的应用.电子学报.2005,33(9)：1720-1722
[49]Derrick Nguyen,Bernard Widrow,Improving the Learning Speed of 2-layer Neural Networks by Choosing Initial Values of the Adaptive Weights, IEEE Trans.1990,2:21-26
[50]姜绍飞.人工神经网络用于建筑工程领域的数据处理方法.哈尔滨建筑大学学报.1999,1(5)：24-32
[51]王钰,周志华,周傲英.机器学习及其应用.清华大学出版社,2006
[52]Freund Y., Schapire R. A desicion-theoretic generalization of on-line learning and an application to boosting, 1997[C]. Springer.
[53]Schapire R. E. The strength of weak learnability. Machine learning. 1990, 5(2):197-227
[54]陈斌.高速公路意外事件影响下的车辆行为模型与事件检测研究.西南交通大学.2005
[55]王丽丽.集成学习算法研究.广西大学.2006：21-30
[56]Zhou Z-H,Wu J,Tang W.Ensembling neural networks:many could be better than all.Artificial Intelligence.2002,137(1-2):239-263
[57]Sandhya Samarasinghe著,史晓霞等译.神经网络在应用科学和工程中的应用：从基本原理到复杂的模式识别.机械工业出版社,2010
[58]Petty K. F., Noeimi H., Sanwal K.. The freeway service patrol evaluation project: Database support programs, and accessibility. Transportation Research Part C: Emerging Technologies.1996,4(2):71-85
[59]Fang Yuan, Ruey Long Cheu. Incident detection using support vector machines.Transportation Research.2003, Part(11):309-328
[60]陈军.改进的LMBP算法在组合式非周期缺陷接地结构建模中的应用.天津大学.2007：21-43
[61]何忠华.城市需水量的预测研究.安徽理工大学.2009：10-16
[62]王成福.视频扫描表头识别系统的研究与实现.华北电力大学.2008：21-23
[63]刘超.免疫前馈神经网络在传感器故障诊断中的应用.苏州大学.2008：26-28
[64]席宁.基于数据挖掘的企业库存管理系统研究.天津大学.2008：9-10
[65]马冉冉.集成学习算法研究.山东科技大学.2010：8-25
[66]钮冰.基于集成学习算法的若干生物信息学问题研究.上海大学.2008：13-17