车联网环境下交通信息采集与处理方法研究
|
摘要
依托国家高技术研究发展计划（863计划）课题《多源多维城市交通状态感知与交互处理》，本文对车联网环境下的交通信息采集与处理方法进行了深入研究。在对国内外研究现状和研究趋势进行分析的基础上，本文首先对车联网的系统架构和关键技术进行了分析。接下来在对车联网关键技术分析的基础上，得出路侧单元布设及优化方法是车联网环境下交通信息采集方法中的重要一环这一结论，并通过分析及实验，给出路侧单元的布设方法和调度优化方案。之后，在车联网环境下交通信息处理方法方面，根据车联网下对车辆定位技术的需求，提出了一个基于非参数动态模型的自适应数据融合框架结构以及一个适应信号强度和到达时间的自适应似然粒子滤波方法，实现基于已有的基础设施对车辆精确定位。最后，在行程时间预测技术方面，针对车联网下交通信息的特点，提出改进的人工神经网络（ANN）和改进的支持向量回归（SVR）方法，对行程时间进行预测，设计了一个仿真平台，并采用实际数据进行仿真，仿真结果表明提出的改进支持向量回归的行程时间预测模型具有良好的性能。
The rapid development of our country road traffic network transport and large-scalevehicle travel time and space characteristics of increasingly prominent, brings greatpressure of the road traffic safety, road transport efficiency, and sustainable urbandevelopment. It not only casues huge economic losses, but also causes the trafficaccidents, environment pollution, and other problems. The transportation system is acomplex giant system. Therefore it is difficult to undamentally solve the problemseparately from the vehicle angle or the road angle.
The internet of vehicles is that the internet of things extends to the intelligenttransportation system (ITS). It is based on the vehicle network, the international networkand the vehicle mobile internet as the foundation. And the internet of vehicles takes theInternet, wireless communication and information exchange with the contract standardcommunication protocol and data interaction, between car to car and car to internet, inorder to realize intelligent traffic management and control, intelligent control andintelligent vehicle dynamic integration of network information service. As thedevelopment direction of intelligent transportation, car networking radically changed thefuture of the construction and development of travel mode, greatly enhance the level ofroad traffic network transport efficiency, security, intelligence level and environmentallevel, to build a kind of adapt to the development of modern transportation road networkconstruction, operation and management model provides a breakthrough. At present,represented by American, European, Japanese, though developed countries have definedthe communication standard for car networking and a series of application scenarios, butthe core technology is still in the stage of laboratory research and test. But our countrystarts late, has not yet been defined standards, but also to related technical research.
Car traffic information is connected to the Internet the most core content in thesystem. To the center, traffic information application car networking system of eachfunction module. In traffic information collection technology at home and abroad havemore research, but mostly in isolation can be divided into fixed detector, vehicle-mountedmobile detector as well as the air detector. In networking environment, through thecar/vehicle road communications technology, will be an on-board system perceived information and roadside perceived information fusion, in order to obtain more accuratetraffic information, will people really-vehicle-road three combined. In addition, the carnetworking environment, traffic information multifarious variety were collectedinformation on how to use these different categories, require different processingmethods.
To solve the problems, this article relying on the national high technology researchand development program (863program)“the multi-source and multi-dimension urbantraffic state perception and interaction processing”, studies the traffic informationcollection and processing methods in internet of vehicles. The main research resultsinclude the following aspects:
1. The internet of vehicles’ system framework is put forward. In car networkingenvironment based on the analysis of information demand, car networking systemarchitecture is put forward, analysis the key technology of vehicle network, includingcar/vehicle road communication technology, intelligent vehicle technology and intelligentroadside systems technology.
2. The traffic information collection methods in internert of vehicles. Onintelligent technology based on the analysis of the lateral files system, expounds theimportance of roadside unit Settings. Several factors affecting the roadside unit layout areanalyzed, and the roadside units deploy test, roadside unit layout Suggestions are putforward. Based on the starting point of saving energy and reducing consumption, andproposes a roadside unit scheduling optimization scheme, the assurance systemconnectivity at the same time reduce the roadside unit energy consumption of the system.
3. The vehicle positioning methods in internert of vehicles. Based on vehicle toinfrastructure communication, the location of the on-board unit to unit based on sideoutline is the transmission and reception of radio frequency signal range measurements toestimate. But in complex urban environments, wireless channel characteristic ofvariability and unpredictability of multipath and impact on the location of the direct waveconditions. Put forward a dynamic model based on the parameters of the adaptive datafusion frame structure and an adaptive signal intensity and arrival time of the improvedbayesian method, which can use existing infrastructure to position the vehicle.
4. The travel time prediction methods in internert of vehicles. In the internert ofvehicles, vehicle and infrastructure can be determined through information interactionbetween flow and density. Using artificial intelligence, such as artificial neural network(ANN) and support vector regression (SVR) in the existing travel time and determine theflow and density on the basis of travel time forecast. Development and evaluation of thecar under the network environment based on artificial neural network and support vectorregression of travel time prediction model, a simulation platform was designed, the actual data is used for simulation.
The rapid development of our country road traffic network transport and large-scalevehicle travel time and space characteristics of increasingly prominent, brings greatpressure of the road traffic safety, road transport efficiency, and sustainable urbandevelopment. It not only casues huge economic losses, but also causes the trafficaccidents, environment pollution, and other problems. The transportation system is acomplex giant system. Therefore it is difficult to undamentally solve the problemseparately from the vehicle angle or the road angle.
The internet of vehicles is that the internet of things extends to the intelligenttransportation system (ITS). It is based on the vehicle network, the international networkand the vehicle mobile internet as the foundation. And the internet of vehicles takes theInternet, wireless communication and information exchange with the contract standardcommunication protocol and data interaction, between car to car and car to internet, inorder to realize intelligent traffic management and control, intelligent control andintelligent vehicle dynamic integration of network information service. As thedevelopment direction of intelligent transportation, car networking radically changed thefuture of the construction and development of travel mode, greatly enhance the level ofroad traffic network transport efficiency, security, intelligence level and environmentallevel, to build a kind of adapt to the development of modern transportation road networkconstruction, operation and management model provides a breakthrough. At present,represented by American, European, Japanese, though developed countries have definedthe communication standard for car networking and a series of application scenarios, butthe core technology is still in the stage of laboratory research and test. But our countrystarts late, has not yet been defined standards, but also to related technical research.
Car traffic information is connected to the Internet the most core content in thesystem. To the center, traffic information application car networking system of eachfunction module. In traffic information collection technology at home and abroad havemore research, but mostly in isolation can be divided into fixed detector, vehicle-mountedmobile detector as well as the air detector. In networking environment, through thecar/vehicle road communications technology, will be an on-board system perceived information and roadside perceived information fusion, in order to obtain more accuratetraffic information, will people really-vehicle-road three combined. In addition, the carnetworking environment, traffic information multifarious variety were collectedinformation on how to use these different categories, require different processingmethods.
To solve the problems, this article relying on the national high technology researchand development program (863program)“the multi-source and multi-dimension urbantraffic state perception and interaction processing”, studies the traffic informationcollection and processing methods in internet of vehicles. The main research resultsinclude the following aspects:
1. The internet of vehicles’ system framework is put forward. In car networkingenvironment based on the analysis of information demand, car networking systemarchitecture is put forward, analysis the key technology of vehicle network, includingcar/vehicle road communication technology, intelligent vehicle technology and intelligentroadside systems technology.
2. The traffic information collection methods in internert of vehicles. Onintelligent technology based on the analysis of the lateral files system, expounds theimportance of roadside unit Settings. Several factors affecting the roadside unit layout areanalyzed, and the roadside units deploy test, roadside unit layout Suggestions are putforward. Based on the starting point of saving energy and reducing consumption, andproposes a roadside unit scheduling optimization scheme, the assurance systemconnectivity at the same time reduce the roadside unit energy consumption of the system.
3. The vehicle positioning methods in internert of vehicles. Based on vehicle toinfrastructure communication, the location of the on-board unit to unit based on sideoutline is the transmission and reception of radio frequency signal range measurements toestimate. But in complex urban environments, wireless channel characteristic ofvariability and unpredictability of multipath and impact on the location of the direct waveconditions. Put forward a dynamic model based on the parameters of the adaptive datafusion frame structure and an adaptive signal intensity and arrival time of the improvedbayesian method, which can use existing infrastructure to position the vehicle.
4. The travel time prediction methods in internert of vehicles. In the internert ofvehicles, vehicle and infrastructure can be determined through information interactionbetween flow and density. Using artificial intelligence, such as artificial neural network(ANN) and support vector regression (SVR) in the existing travel time and determine theflow and density on the basis of travel time forecast. Development and evaluation of thecar under the network environment based on artificial neural network and support vectorregression of travel time prediction model, a simulation platform was designed, the actual data is used for simulation.
引文
[1]中国交通技术网.智能交通未来的发展方向[EB/OL].(2011-04-01)[2012-11-01]. http://www.itschina.org
[2]王云鹏.车联网与车路协同[EB/OL].(2011-11-01)[2012-11-12].http://labs.chinamobile.com/report/view_60705
[3] RFID世界网.车载物联网应用案例[EB/OL].(2011-11-30)[2012-10-1]http://success.rfidworld.com.cn/2011_11/a70d26e31496e6ec.html
[4]熊炜,李清泉,李宇光．智能道路系统的发展现状与趋势[J]．研究报告,2007,9(2):83-88.
[5] Vehicle Infrastructure Integration (VII) Version1.2.1[R]. Washington, DC: ITSJoint Program Office US Department of Transportation, April,2008.
[6]太平洋汽车网. Telematics产业化的发展动向[EB/OL].(2007-09-02)[2012-11-01]. http://www.pcauto.com.cn/qcyp/rmlm/hycw/0708/504910.html
[7] MIT CarTel[EB/OL].[2004-10-27]. http://cartel.csail.mit.edu/doku.php
[8]欧洲智能交通信息服务平台.[EB/OL](2008-03011)[2012-11-01].http://www.ertico.com/about-ertico-mission,2010
[9]陈超,吕植勇.国内外车路协同系统发展现状综述[J].交通信息与安全,2011,29(1):102-109.
[10]FleetNet [EB/OL].(2004-10-27)[2012-11-01]
[11]CarTalk [EB/OL].(2004-01-13)[2012-11-02]. http://www.cartalk2000.net/.
[12]淘治中.智慧型运输系统（ITS）整体发展趋势之比较与评析[J].中华技术,2009,7(1):112-123.
[13]马杨.车路协同，还有多远？[J].中国交通信息化,2011,(9):30-31.
[14]刘昕.基于IPv6的智能交通信息采集与处理方法[D].长春:吉林大学交通学院,2011.
[15]于悦.重大灾害条件下城市应急交通诱导系统关键技术研究[D].长春:吉林大学交通学院,2010.
[16]胡永利,孙艳丰,尹宝才.物联网信息感知与交互技术[J].计算机学报,2012,35(6):1147-1163.
[17]王贵槐,万剑.汽车安全辅助驾驶支持系统信息感知技术综述[J].交通与计算机,2008(3):50-54.
[18]魏李琦.面向802.11p标准的车载网络MAC和广播协议的设计与优化[D].长沙:国防科技大学,2011.
[19]邹凤,仲娇菲,伍伟丽等.解决高度分割的车载自组网络连通性问题的路侧单元最优化调度方案[J].计算机工程与科学,2012,34(1):1-10.
[20]B. Gallagher et al. Wireless Communications for Vehicle Saftey: Radio LinkPerformance and Wirelss Connectivity Methods[J]. IEEE Vehic. Tech. Mag.,vol.1(4), Dec.2006:4-24.
[21]A. Paier, et al. Average Downstream Performance of Measured IEEE802.11pInfrastructure-to-Vehicle Links[C]. Proc. IEEE ICC, Cape Town, South Africa,May2010, pp1-5.
[22]C.F. Mecklenbrauker et al. Vehicluar Channel Characterization and ItsImplications for Wireless System Design and Performance[C]. Proc. IEEE,vol.99(7), July2011, pp1189-1212.
[23]S.R. Dickey et al. Field Measurements of Vehicle to Roadside CommunicationPerformance[C]. IEEE VTC-Fall, Baltimore(USA), Oct2007, pp2179-2183.
[24]R. Meireles, et al. Experimental Study on the Impact of Vehicluar Obstructions inVANETs[C]. Proc. IEEE Vehic. NET. Conf.(VNC), New Jersey(USA), Dec.2010,pp338-345.
[25]A.Bohm, et al. Evaluating CALM M5-based Vehicle-to-Vehicle Communicationin Various Road Settings through Field Trials[C]. Proc.IEEE Conf. LocalComputer Networks(LCN), Denver, CO, Oct2010, pp613-620.
[26]F.Bai et al. Reliability Anaysis of DSRC Wireless Communications for VehicleSafty Applications[C]. Proc. IEEE Conf. Intelligent Transporation Systems(ITSC),Toronto (Canada), Sept.2006, pp355-362.
[27]Broch J, Maltz D A, Johnson D B, et al. A Performance Comparison ofMulti-Hop Wirelss Ad Hoc Network Routing Protocols[C]. Proc of the4thAnnual ACM/IEEE International Conference on Mobile Conputing andNetworking,1998:85-97.
[28]Johnson D B, Maltz D A. Dynamic Source Routing in Ad Hoc WirelessNetworks[J]. Mobile Computing,1996:153-181.
[29]Royer E M, Perkins C E. Multicast Operation of the Ad-Hoc On-DemandDistance Vector Routing Protocol[C]. Proc of the5th Annual ACM/IEEEInternational Conference on Mobile Computing and Networking,1999:207-218.
[30]Das S R, Perkins C E, Royer E E. Performance Comparison of Two On-DemandRouting Protocols for Ad Hoc Networks[C]. Proc of INFOCOM’00,2000:3-12.
[31]Naumov V, Baumann R, Gross T. An Evaluation of Inter-Vehicle Ad HocNetworks Based on Realistic Vehicular Traces[C]. Proc of the7th ACMInternational Symposium on Mobile Ad Hoc Networking and Computing,2006:108-119.
[32]Saha A K, Johnson D B. Modeling Mobility for Vehicular Ad-Hoc Networks[C].Proc of the1st ACM International Workshop on Vehicular Ad Hoc Networks,2004:91-92.
[33]Robins G, Zelikovsky A. Improved Steiner Tree Approximation in Graphs[C].Proc of the Eleventh Annual ACM-SI-AM Symposium on Discrete Algorithms,2000:770-779.
[34]Patari, N. Hero III A.O., Perkins M., Correal N.S., O’Dea J. Relative LocationEstimation in Wireless Sensor Networks[J]. IEEE Transaction on SignalProcessing (2003).,51(8),2137-2148.
[35]Shen, Y,&Win, M.Z. Fundamental Limeits of Wideband Localization0Part I: AGeneral Framework[J]. IEEE Transactions on Information Theory (2010).,56(10),4956-4890.
[36]Gustafsson, F, Gunnarsson, F, Bergman, N, Forssell, U, Jansson, J, Karlsson, R,&Nordlund, P.J. Particle Filters for Positioning, Navigation, and Tracking[J].IEEE Transactions on Signal Processing (2002).,50(2),425-437.
[37]Bar-shalom, Y. Rong Li X., Kirubarajan T. Estimation with Applications toTracking and Navigation[J]. New York: John Wiley&Sons;(2004).
[38]Qi, Y. Wireless Geolocation in a non-Line-of-Sight Environment[D]. PhD thesis.Princeton University;(2003).
[39]Mazuelas, S, Lago, F.A, Blas, J, Bahillo, A, Fernandez, P, Lorenzo, R.M,&Abril,E. J. Priot NLOS Measurement Correction for Positioning in Cellular WirelessNetworks[J]. IEEE Transactions on Vehicular Technology (2009).,58(5),2585-2591.
[40]Prieto, J, Bahillo, A, Mazuelas, S, Lorenzo, R. M, Fenandezm, P,&Abril, E. J.Characterization and Mitigation of Range Estimation Errors for and RTT-BasedIEEE802.11Indoor Location System[J]. Progress in Electromagnetics ResearchPIERB (2009).,15-217.
[41]Chen, P.C. Mobile Position Location Estimation in Cellular Systems[D]. PhDthesis. The State University of New Jersey.
[42]Wylie, M. P,,&Holtzman, J. The non-Line of Sight Problem in Mobile LocationEstimation[C]. In: Proceedings of the19965th IEEE International Conference onUniversal Personal Communications Record,29September–2October1996,Cambridge, MA, USA:(1996).
[43]Nicoli, M, Morelli, C,&Rampa, V. A Jump Markov Particle Filter forLocalization of Moving Terminals in Multipath Indoor Scenarios[J]. IEEETransactions on Signal Processing (2008).,56(8),3801-3809.
[44]Chen, L,&Wu, L. Mobile Positioning in Mixed LOS/NLOS Conditions underModified EKF Banks and Data Fusion[J]. IEICE Transactions onCommunications (2009). EB(4)1318-1325.,92.
[45]Hatami, A,&Pahlavan, L. QRPp1-5: Hybrid TOA-RSS Based LocalizationUsing Neural Networks[C]. In: Proceedings of the IEEE GlobalTelecommunications Conference, GLOBECOM’06,27November–1December2006, San Francisco, CA, USA;(2006).
[46]Catovi, A,&Shinoglu, Z. The Cramer-Rao Bounds of Hybrid TOA/RSS andTDOA/RSS Location Estimation Schemes[J]. IEEE Communications Letters(2004).,8(10),626-628.
[47]Mcguire, M, Plataniotis, K. N,&Venetsanopoulos, A. N. Data Fusion of Powerand Time Measurements for Mobile Terminal Location[J]. IEEE Transactions onMobile Computing (2005).,4(2),142-153.
[48]Song, Y,&Yu, H. A New Hybrid TOA/RSS Location Tracking Algorithm forWireless Sensor Network[C]. In: Proceedings of the9th International Conferenceon Signal Processing, ICSP(2008). October2008, Beijing, China;2008.,2008,26-29.
[49]Chen, B. S, Yang, Y, Liao, F.K,&Liao, J. F. Mobile Location Estimator in aRough Wirelss Environment Using Extended Kalman-Based IMM and DataFusion[J]. IEEE Transactions on Vehicular Technology (2009).,58(3),1157-1169.
[50]Risitc, B, Arulampalam, S,&Gordon, N. Beyond the Kalman Filter, ParticleFilters for Tracking Applications[J]. Boston: Artech House;(2004).
[51]Bar-shalom, Y. Rong Li X., Kirubarajan T. Estimation with Applications toTracking and Navigation[J]. New York: John Wiley&Sons;(2001).
[52]Bahillo, A, Fernandez, P, Prieto, J, Mazuelas, S, Lorenzo, R. M,&Abril, E. J.Distance Estimation Based on802.11RTS/CTS Mechanism for IndoorLocalization[J]. In: Almeida M.(ed.) Advances in Vehicular NetworkingTechnologies. Rijeka: In-Tech;(2011).,217-236.
[53]Mazuelas, S, Bahillo, A, Lorenzo, R. M, Fernandez, P, Lago, F. A, Garcia, E, Blas,J,&Abril, E. J. Robust Indoor Positioning Provided by Real-Time RSSI Valuesin Unmodified WLAN Networks[J]. IEEE Journal of Selected Topics in SignalProcessing (2009).,3(5),821-831.
[54]Hashmi, H. The Indoor Radio Propagation Channel[C]. Proceedings of the IEEE(1993).,81(7),943-968.
[55]Titterington, D, Smith, A,&Makov, U. Statistical Analysis of Finite MixtureDistributions[J]. Chichester: John Wiley&Sons;(1985).
[56]Mclachlan, G. J,&Krishman, T. The EM Algorithm and Extensions[J]. Hoboken:John Wiley&Sons;(2008).
[57]Neapolitan, R. E. Learning Bayesian Networks[M]. Upper Saddle River: PrenticeHall;(2003).
[58]Prieto, J, Bahillo, A, Mazuelas, S, Lorenzo, R, Blas, J,&Fernandez, P. NLOSMitigation Based on Range Estimation Error Characterization in An RTT-basedIEEE802.11Indoor Location System[C]. In: Proceedings of the IEEEInterational Symposium on Intelligent Signal Processing, WISP2009. August2009, Budapest, Hungary;(2009).,26-28.
[59]Jourdan, D, Daradari, D,&Win, M. Z. Position Error Bound for UWBLocalization in Dense Cluttered Environments[J]. IEEE Transactions onAerospace and Electronic Systems(2008).,44(2),613-628.
[60]Hwang, J, lays&Lippman, A. Nonparametric Multivariate Density Estimation: AComparative Study[J]. IEEE Transactions on Signal Processing (1994).,42(10),2795-2810.
[61]Doucet, A, Godsill, S,&Andrieu, C. On Sequential Monte Carlo SamplingMethods for Bayesian Filtering[J]. Statistics and Computing (2000).,10(3),197-208.
[62]Van Trees, H. L. Detection, Estimation, and Modulation Theory: Part I[J]. NewYork: John Wiley&Sons.(1968).
[63]Bergman, N. Recursive Bayesian Estimation, Navigation and TrackingApplications[D]. PhD thesis. Link ping University, Sweden.(1999).
[64]Tichavsky, P, Muravchik, C. H,&Nehorai, A. Posterior Cramér-Rao Bounds forDiscrete-Time Nonlinear Filtering[J]. IEEE Transactions on Signal Processing(1998).,46(5),1386-1396.
[65]Daum, F,&Huan, J. Curse of Dimensionality and Particle Filters[C]. In:Proceedings of IEEE Conference on Aerospace. March1993, Big Sky, MT, USA;(1993).,1-8.
[66]Williams, J. L. Gaussian Mixture Reduction for Tracking Multiple ManeuveringTargets in Clutter[D]. PhD thesis. Air Force Institute of Technology;(2003).
[67]Huber, M,&Hanebeck, U. Progressive Gaussian Mixture Reduction[C]. In:Proceedings of the11th International Conference on Information Fusion,FUSION’08.30June-3July2008, Cologne, Germany;(2008).
[68]Schieferdecker, D,&Huber, M. Gaussian Mixture Reduction via Clustering[C].In: Proceedings of the12th International Conference on Information Fusion,FUSION’09. July2009, Seattle, WA, USA;(2009).,6-9.
[69]杨兆升.城市交通流诱导系统[M].北京:中国铁道出版社,2004:274.
[70]M. Ben-Akiva, M. Bierlaire, D. Burton, H. N. Koutsopoulos, and R. Mishalani.Network state estimation and prediction for real-time transportation managementapplications[C]. In Proc.81st Annu. Meeting Transp. Res. Board, Washington,DC,2002,[CD-ROM].
[71]X. Fei, S. Eisenman, H. Mahmassani, and S. Zhou, Application ofDYNASMART-X to the Maryland CHART network for real-time trafficmanagement center decision support[C]. In Proc.12th World Congr. Intell.Transp. Syst., San Francisco, CA,2005,[CD-ROM].
[72]J. Rice and E. Van Zwet. A simple and effective method for predicting traveltimes on freeways[C]. In Proc. IEEE Conf. Intell. Transp. Syst., Oakland, CA,2001, pp.227–232。
[73]X. Zhang and J. A. Rice. Short-term travel time prediction[J]. Transp. Res. C,Emergency Technol., vol.11, no.3/4, pp.187–210, Jun./Aug.2003.
[74]S. I. Bajwa, E. Chung, andM. Kuwahara. A travel time predictionmethod basedon pattern matching technique[C] In Proc.21st ARRB Conf., Cairns, Australia,2003,[CD-ROM].
[75]朱中，杨兆升.实时交通流量人工神经网络预测模型[J].中国公路学报,1998,11(4):89-92
[76]G. Huisken and E. C. Van Berkum. A comparative analysis of short-range traveltime predictionmethods[C]. In Proc.82nd Annu. Meeting Transp. Res. Board,Washington, DC,2003,[CD-ROM].
[77]J. W. C. Van Lint. Reliable real-time framework for short-term freeway traveltime prediction[J]. Transp. Eng., vol.132, no.12, pp.921–932, Dec.2006.
[78]Vythoulkas P C. Alternative approaches to short term traffic forecasting for use indriver information[C]. University of Oxford12th International Symposium on theTheory of Traffic Flow and Transportation: Transportation and Traffic theory.Amsterdam: Elsevier Science,1993:485-506.
[79]D. Park, L. Rilett, and G. Han. Spectral basis neural networks for realtime traveltime forecasting[J]. Transp. Eng., vol.125, no.6, pp.515–523, Nov./Dec.1999.
[80]C.-H. Wu, J.-M. Ho, and D.-T. Lee. Travel-time prediction with support vectorregression[J] IEEE Trans. Intell. Transp. Syst., vol.5, no.4, pp.276–281, Dec.2004.
[81]W.-C. Lin. A case study on support vectormachine versus artificial neuralnetworks[D]. M.S. thesis, Univ. Pittsburgh, Pittsburgh, PA,2004.
[82]L. Vanajakshi and L. Rilett. A comparison of the performance of artificial neuralnetworks and support vector machines for the prediction of traffic speed[C]. InProc. IEEE Intell. Veh. Symp., Parma, Italy,2004, pp.194–199.
[83]Vapnik V N. Statistical Learning Theory[M].北京：电子工业出版社，2004.
[84]Chen S, Cowan C F N, Grant P M. Orthogonal least squares learing algorithmsfor radial basis function network[J]. IEEE Trans. Neural Networks,1991,2(2)：302-309.
[85]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.
[86]杨兆升，等.基于支持向量机方法的短时交通流量预测方法[J].吉林大学学报，2006.36（6）：881-884.
[87]姚智胜，邵春福，高永亮.基于支持向量回归机的交通状态短时预测方法研究[J].北京交通大学学报，2006，30（3）：19-22.
[88]Y. Gardes, A. D. May, J. Dahlgren, and A. Skabardonis. Freeway calibration andapplication of the PARAMICS model[C]. In Proc.82th Annu. Meeting Transp.Res. Board, Washington, DC,2002,[CD-ROM].
[89]J. Hourdakis, P. G. Michalopoulos, and J. Kottommannil. A practical procedurefor calibrating microscopic traffic simulation models[J]. Transp. Res. Record, no.1852, pp.130–139,2003.
[90]C.-W. Hsu, C.-C. Chang, and C.-J. Lin. A Practical Guide to Support VectorClassification[J].2007.[Online].
[91]C.-C. Chang and C.-J. Lin. LIBSVM: A Library for Support Vector Machines[J].2005.[Online].
[92]B. Vanschoenwinkel, F. Liu, and B. Manderick. Context-sensitive kernelfunctions: A distance function viewpoint[C]. In Proc. ICMLC, Berlin, Germany,2006, vol.3930, pp.861–870.
[93]T.Wang, J. G. Proakis, E. Masry, and J. R. Zeidler. Performance degradation ofOFDM systems due to Doppler spreading[J]. IEEE Trans. Wireless Commun., vol.5, no.6, pp.1422–1432, Jun.2006
[94]B. S. Gukhool and S. Cherkaoui. IEEE802.11p modeling in ns-2[C]. In Proc.33rd IEEE Conf. Local Comput. Netw., Montreal, PQ, Canada,2008, pp.622–626.
[95]Yang Zhaosheng，Zhou Huxing，Gao Peng，Chen Hong，Zhang Nan. TheTopological Analysis of Urban Transit System as a Small-World Network[J].International Journal of Computational Intelligence Systems,2011,4(6):1216-1223.
[96]Yang Zhaosheng，Zhou Huxing，Gao Xueying，Liu Songnan. MultiobjectiveModel for Emergency Resources Allocation[J]. Mathematical Problems inEngineering,2013.
[97]Zhou Huxing，Yang Zhaosheng，Gao Peng. A Hierarchical Control Model forRegional Traffic Signal Coordination[C]. Proceedings of the1st InternationalConference on Transportation Information and Safety,2011:964-970.
[2]王云鹏.车联网与车路协同[EB/OL].(2011-11-01)[2012-11-12].http://labs.chinamobile.com/report/view_60705
[3] RFID世界网.车载物联网应用案例[EB/OL].(2011-11-30)[2012-10-1]http://success.rfidworld.com.cn/2011_11/a70d26e31496e6ec.html
[4]熊炜,李清泉,李宇光．智能道路系统的发展现状与趋势[J]．研究报告,2007,9(2):83-88.
[5] Vehicle Infrastructure Integration (VII) Version1.2.1[R]. Washington, DC: ITSJoint Program Office US Department of Transportation, April,2008.
[6]太平洋汽车网. Telematics产业化的发展动向[EB/OL].(2007-09-02)[2012-11-01]. http://www.pcauto.com.cn/qcyp/rmlm/hycw/0708/504910.html
[7] MIT CarTel[EB/OL].[2004-10-27]. http://cartel.csail.mit.edu/doku.php
[8]欧洲智能交通信息服务平台.[EB/OL](2008-03011)[2012-11-01].http://www.ertico.com/about-ertico-mission,2010
[9]陈超,吕植勇.国内外车路协同系统发展现状综述[J].交通信息与安全,2011,29(1):102-109.
[10]FleetNet [EB/OL].(2004-10-27)[2012-11-01]
[11]CarTalk [EB/OL].(2004-01-13)[2012-11-02]. http://www.cartalk2000.net/.
[12]淘治中.智慧型运输系统（ITS）整体发展趋势之比较与评析[J].中华技术,2009,7(1):112-123.
[13]马杨.车路协同，还有多远？[J].中国交通信息化,2011,(9):30-31.
[14]刘昕.基于IPv6的智能交通信息采集与处理方法[D].长春:吉林大学交通学院,2011.
[15]于悦.重大灾害条件下城市应急交通诱导系统关键技术研究[D].长春:吉林大学交通学院,2010.
[16]胡永利,孙艳丰,尹宝才.物联网信息感知与交互技术[J].计算机学报,2012,35(6):1147-1163.
[17]王贵槐,万剑.汽车安全辅助驾驶支持系统信息感知技术综述[J].交通与计算机,2008(3):50-54.
[18]魏李琦.面向802.11p标准的车载网络MAC和广播协议的设计与优化[D].长沙:国防科技大学,2011.
[19]邹凤,仲娇菲,伍伟丽等.解决高度分割的车载自组网络连通性问题的路侧单元最优化调度方案[J].计算机工程与科学,2012,34(1):1-10.
[20]B. Gallagher et al. Wireless Communications for Vehicle Saftey: Radio LinkPerformance and Wirelss Connectivity Methods[J]. IEEE Vehic. Tech. Mag.,vol.1(4), Dec.2006:4-24.
[21]A. Paier, et al. Average Downstream Performance of Measured IEEE802.11pInfrastructure-to-Vehicle Links[C]. Proc. IEEE ICC, Cape Town, South Africa,May2010, pp1-5.
[22]C.F. Mecklenbrauker et al. Vehicluar Channel Characterization and ItsImplications for Wireless System Design and Performance[C]. Proc. IEEE,vol.99(7), July2011, pp1189-1212.
[23]S.R. Dickey et al. Field Measurements of Vehicle to Roadside CommunicationPerformance[C]. IEEE VTC-Fall, Baltimore(USA), Oct2007, pp2179-2183.
[24]R. Meireles, et al. Experimental Study on the Impact of Vehicluar Obstructions inVANETs[C]. Proc. IEEE Vehic. NET. Conf.(VNC), New Jersey(USA), Dec.2010,pp338-345.
[25]A.Bohm, et al. Evaluating CALM M5-based Vehicle-to-Vehicle Communicationin Various Road Settings through Field Trials[C]. Proc.IEEE Conf. LocalComputer Networks(LCN), Denver, CO, Oct2010, pp613-620.
[26]F.Bai et al. Reliability Anaysis of DSRC Wireless Communications for VehicleSafty Applications[C]. Proc. IEEE Conf. Intelligent Transporation Systems(ITSC),Toronto (Canada), Sept.2006, pp355-362.
[27]Broch J, Maltz D A, Johnson D B, et al. A Performance Comparison ofMulti-Hop Wirelss Ad Hoc Network Routing Protocols[C]. Proc of the4thAnnual ACM/IEEE International Conference on Mobile Conputing andNetworking,1998:85-97.
[28]Johnson D B, Maltz D A. Dynamic Source Routing in Ad Hoc WirelessNetworks[J]. Mobile Computing,1996:153-181.
[29]Royer E M, Perkins C E. Multicast Operation of the Ad-Hoc On-DemandDistance Vector Routing Protocol[C]. Proc of the5th Annual ACM/IEEEInternational Conference on Mobile Computing and Networking,1999:207-218.
[30]Das S R, Perkins C E, Royer E E. Performance Comparison of Two On-DemandRouting Protocols for Ad Hoc Networks[C]. Proc of INFOCOM’00,2000:3-12.
[31]Naumov V, Baumann R, Gross T. An Evaluation of Inter-Vehicle Ad HocNetworks Based on Realistic Vehicular Traces[C]. Proc of the7th ACMInternational Symposium on Mobile Ad Hoc Networking and Computing,2006:108-119.
[32]Saha A K, Johnson D B. Modeling Mobility for Vehicular Ad-Hoc Networks[C].Proc of the1st ACM International Workshop on Vehicular Ad Hoc Networks,2004:91-92.
[33]Robins G, Zelikovsky A. Improved Steiner Tree Approximation in Graphs[C].Proc of the Eleventh Annual ACM-SI-AM Symposium on Discrete Algorithms,2000:770-779.
[34]Patari, N. Hero III A.O., Perkins M., Correal N.S., O’Dea J. Relative LocationEstimation in Wireless Sensor Networks[J]. IEEE Transaction on SignalProcessing (2003).,51(8),2137-2148.
[35]Shen, Y,&Win, M.Z. Fundamental Limeits of Wideband Localization0Part I: AGeneral Framework[J]. IEEE Transactions on Information Theory (2010).,56(10),4956-4890.
[36]Gustafsson, F, Gunnarsson, F, Bergman, N, Forssell, U, Jansson, J, Karlsson, R,&Nordlund, P.J. Particle Filters for Positioning, Navigation, and Tracking[J].IEEE Transactions on Signal Processing (2002).,50(2),425-437.
[37]Bar-shalom, Y. Rong Li X., Kirubarajan T. Estimation with Applications toTracking and Navigation[J]. New York: John Wiley&Sons;(2004).
[38]Qi, Y. Wireless Geolocation in a non-Line-of-Sight Environment[D]. PhD thesis.Princeton University;(2003).
[39]Mazuelas, S, Lago, F.A, Blas, J, Bahillo, A, Fernandez, P, Lorenzo, R.M,&Abril,E. J. Priot NLOS Measurement Correction for Positioning in Cellular WirelessNetworks[J]. IEEE Transactions on Vehicular Technology (2009).,58(5),2585-2591.
[40]Prieto, J, Bahillo, A, Mazuelas, S, Lorenzo, R. M, Fenandezm, P,&Abril, E. J.Characterization and Mitigation of Range Estimation Errors for and RTT-BasedIEEE802.11Indoor Location System[J]. Progress in Electromagnetics ResearchPIERB (2009).,15-217.
[41]Chen, P.C. Mobile Position Location Estimation in Cellular Systems[D]. PhDthesis. The State University of New Jersey.
[42]Wylie, M. P,,&Holtzman, J. The non-Line of Sight Problem in Mobile LocationEstimation[C]. In: Proceedings of the19965th IEEE International Conference onUniversal Personal Communications Record,29September–2October1996,Cambridge, MA, USA:(1996).
[43]Nicoli, M, Morelli, C,&Rampa, V. A Jump Markov Particle Filter forLocalization of Moving Terminals in Multipath Indoor Scenarios[J]. IEEETransactions on Signal Processing (2008).,56(8),3801-3809.
[44]Chen, L,&Wu, L. Mobile Positioning in Mixed LOS/NLOS Conditions underModified EKF Banks and Data Fusion[J]. IEICE Transactions onCommunications (2009). EB(4)1318-1325.,92.
[45]Hatami, A,&Pahlavan, L. QRPp1-5: Hybrid TOA-RSS Based LocalizationUsing Neural Networks[C]. In: Proceedings of the IEEE GlobalTelecommunications Conference, GLOBECOM’06,27November–1December2006, San Francisco, CA, USA;(2006).
[46]Catovi, A,&Shinoglu, Z. The Cramer-Rao Bounds of Hybrid TOA/RSS andTDOA/RSS Location Estimation Schemes[J]. IEEE Communications Letters(2004).,8(10),626-628.
[47]Mcguire, M, Plataniotis, K. N,&Venetsanopoulos, A. N. Data Fusion of Powerand Time Measurements for Mobile Terminal Location[J]. IEEE Transactions onMobile Computing (2005).,4(2),142-153.
[48]Song, Y,&Yu, H. A New Hybrid TOA/RSS Location Tracking Algorithm forWireless Sensor Network[C]. In: Proceedings of the9th International Conferenceon Signal Processing, ICSP(2008). October2008, Beijing, China;2008.,2008,26-29.
[49]Chen, B. S, Yang, Y, Liao, F.K,&Liao, J. F. Mobile Location Estimator in aRough Wirelss Environment Using Extended Kalman-Based IMM and DataFusion[J]. IEEE Transactions on Vehicular Technology (2009).,58(3),1157-1169.
[50]Risitc, B, Arulampalam, S,&Gordon, N. Beyond the Kalman Filter, ParticleFilters for Tracking Applications[J]. Boston: Artech House;(2004).
[51]Bar-shalom, Y. Rong Li X., Kirubarajan T. Estimation with Applications toTracking and Navigation[J]. New York: John Wiley&Sons;(2001).
[52]Bahillo, A, Fernandez, P, Prieto, J, Mazuelas, S, Lorenzo, R. M,&Abril, E. J.Distance Estimation Based on802.11RTS/CTS Mechanism for IndoorLocalization[J]. In: Almeida M.(ed.) Advances in Vehicular NetworkingTechnologies. Rijeka: In-Tech;(2011).,217-236.
[53]Mazuelas, S, Bahillo, A, Lorenzo, R. M, Fernandez, P, Lago, F. A, Garcia, E, Blas,J,&Abril, E. J. Robust Indoor Positioning Provided by Real-Time RSSI Valuesin Unmodified WLAN Networks[J]. IEEE Journal of Selected Topics in SignalProcessing (2009).,3(5),821-831.
[54]Hashmi, H. The Indoor Radio Propagation Channel[C]. Proceedings of the IEEE(1993).,81(7),943-968.
[55]Titterington, D, Smith, A,&Makov, U. Statistical Analysis of Finite MixtureDistributions[J]. Chichester: John Wiley&Sons;(1985).
[56]Mclachlan, G. J,&Krishman, T. The EM Algorithm and Extensions[J]. Hoboken:John Wiley&Sons;(2008).
[57]Neapolitan, R. E. Learning Bayesian Networks[M]. Upper Saddle River: PrenticeHall;(2003).
[58]Prieto, J, Bahillo, A, Mazuelas, S, Lorenzo, R, Blas, J,&Fernandez, P. NLOSMitigation Based on Range Estimation Error Characterization in An RTT-basedIEEE802.11Indoor Location System[C]. In: Proceedings of the IEEEInterational Symposium on Intelligent Signal Processing, WISP2009. August2009, Budapest, Hungary;(2009).,26-28.
[59]Jourdan, D, Daradari, D,&Win, M. Z. Position Error Bound for UWBLocalization in Dense Cluttered Environments[J]. IEEE Transactions onAerospace and Electronic Systems(2008).,44(2),613-628.
[60]Hwang, J, lays&Lippman, A. Nonparametric Multivariate Density Estimation: AComparative Study[J]. IEEE Transactions on Signal Processing (1994).,42(10),2795-2810.
[61]Doucet, A, Godsill, S,&Andrieu, C. On Sequential Monte Carlo SamplingMethods for Bayesian Filtering[J]. Statistics and Computing (2000).,10(3),197-208.
[62]Van Trees, H. L. Detection, Estimation, and Modulation Theory: Part I[J]. NewYork: John Wiley&Sons.(1968).
[63]Bergman, N. Recursive Bayesian Estimation, Navigation and TrackingApplications[D]. PhD thesis. Link ping University, Sweden.(1999).
[64]Tichavsky, P, Muravchik, C. H,&Nehorai, A. Posterior Cramér-Rao Bounds forDiscrete-Time Nonlinear Filtering[J]. IEEE Transactions on Signal Processing(1998).,46(5),1386-1396.
[65]Daum, F,&Huan, J. Curse of Dimensionality and Particle Filters[C]. In:Proceedings of IEEE Conference on Aerospace. March1993, Big Sky, MT, USA;(1993).,1-8.
[66]Williams, J. L. Gaussian Mixture Reduction for Tracking Multiple ManeuveringTargets in Clutter[D]. PhD thesis. Air Force Institute of Technology;(2003).
[67]Huber, M,&Hanebeck, U. Progressive Gaussian Mixture Reduction[C]. In:Proceedings of the11th International Conference on Information Fusion,FUSION’08.30June-3July2008, Cologne, Germany;(2008).
[68]Schieferdecker, D,&Huber, M. Gaussian Mixture Reduction via Clustering[C].In: Proceedings of the12th International Conference on Information Fusion,FUSION’09. July2009, Seattle, WA, USA;(2009).,6-9.
[69]杨兆升.城市交通流诱导系统[M].北京:中国铁道出版社,2004:274.
[70]M. Ben-Akiva, M. Bierlaire, D. Burton, H. N. Koutsopoulos, and R. Mishalani.Network state estimation and prediction for real-time transportation managementapplications[C]. In Proc.81st Annu. Meeting Transp. Res. Board, Washington,DC,2002,[CD-ROM].
[71]X. Fei, S. Eisenman, H. Mahmassani, and S. Zhou, Application ofDYNASMART-X to the Maryland CHART network for real-time trafficmanagement center decision support[C]. In Proc.12th World Congr. Intell.Transp. Syst., San Francisco, CA,2005,[CD-ROM].
[72]J. Rice and E. Van Zwet. A simple and effective method for predicting traveltimes on freeways[C]. In Proc. IEEE Conf. Intell. Transp. Syst., Oakland, CA,2001, pp.227–232。
[73]X. Zhang and J. A. Rice. Short-term travel time prediction[J]. Transp. Res. C,Emergency Technol., vol.11, no.3/4, pp.187–210, Jun./Aug.2003.
[74]S. I. Bajwa, E. Chung, andM. Kuwahara. A travel time predictionmethod basedon pattern matching technique[C] In Proc.21st ARRB Conf., Cairns, Australia,2003,[CD-ROM].
[75]朱中，杨兆升.实时交通流量人工神经网络预测模型[J].中国公路学报,1998,11(4):89-92
[76]G. Huisken and E. C. Van Berkum. A comparative analysis of short-range traveltime predictionmethods[C]. In Proc.82nd Annu. Meeting Transp. Res. Board,Washington, DC,2003,[CD-ROM].
[77]J. W. C. Van Lint. Reliable real-time framework for short-term freeway traveltime prediction[J]. Transp. Eng., vol.132, no.12, pp.921–932, Dec.2006.
[78]Vythoulkas P C. Alternative approaches to short term traffic forecasting for use indriver information[C]. University of Oxford12th International Symposium on theTheory of Traffic Flow and Transportation: Transportation and Traffic theory.Amsterdam: Elsevier Science,1993:485-506.
[79]D. Park, L. Rilett, and G. Han. Spectral basis neural networks for realtime traveltime forecasting[J]. Transp. Eng., vol.125, no.6, pp.515–523, Nov./Dec.1999.
[80]C.-H. Wu, J.-M. Ho, and D.-T. Lee. Travel-time prediction with support vectorregression[J] IEEE Trans. Intell. Transp. Syst., vol.5, no.4, pp.276–281, Dec.2004.
[81]W.-C. Lin. A case study on support vectormachine versus artificial neuralnetworks[D]. M.S. thesis, Univ. Pittsburgh, Pittsburgh, PA,2004.
[82]L. Vanajakshi and L. Rilett. A comparison of the performance of artificial neuralnetworks and support vector machines for the prediction of traffic speed[C]. InProc. IEEE Intell. Veh. Symp., Parma, Italy,2004, pp.194–199.
[83]Vapnik V N. Statistical Learning Theory[M].北京：电子工业出版社，2004.
[84]Chen S, Cowan C F N, Grant P M. Orthogonal least squares learing algorithmsfor radial basis function network[J]. IEEE Trans. Neural Networks,1991,2(2)：302-309.
[85]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.
[86]杨兆升，等.基于支持向量机方法的短时交通流量预测方法[J].吉林大学学报，2006.36（6）：881-884.
[87]姚智胜，邵春福，高永亮.基于支持向量回归机的交通状态短时预测方法研究[J].北京交通大学学报，2006，30（3）：19-22.
[88]Y. Gardes, A. D. May, J. Dahlgren, and A. Skabardonis. Freeway calibration andapplication of the PARAMICS model[C]. In Proc.82th Annu. Meeting Transp.Res. Board, Washington, DC,2002,[CD-ROM].
[89]J. Hourdakis, P. G. Michalopoulos, and J. Kottommannil. A practical procedurefor calibrating microscopic traffic simulation models[J]. Transp. Res. Record, no.1852, pp.130–139,2003.
[90]C.-W. Hsu, C.-C. Chang, and C.-J. Lin. A Practical Guide to Support VectorClassification[J].2007.[Online].
[91]C.-C. Chang and C.-J. Lin. LIBSVM: A Library for Support Vector Machines[J].2005.[Online].
[92]B. Vanschoenwinkel, F. Liu, and B. Manderick. Context-sensitive kernelfunctions: A distance function viewpoint[C]. In Proc. ICMLC, Berlin, Germany,2006, vol.3930, pp.861–870.
[93]T.Wang, J. G. Proakis, E. Masry, and J. R. Zeidler. Performance degradation ofOFDM systems due to Doppler spreading[J]. IEEE Trans. Wireless Commun., vol.5, no.6, pp.1422–1432, Jun.2006
[94]B. S. Gukhool and S. Cherkaoui. IEEE802.11p modeling in ns-2[C]. In Proc.33rd IEEE Conf. Local Comput. Netw., Montreal, PQ, Canada,2008, pp.622–626.
[95]Yang Zhaosheng，Zhou Huxing，Gao Peng，Chen Hong，Zhang Nan. TheTopological Analysis of Urban Transit System as a Small-World Network[J].International Journal of Computational Intelligence Systems,2011,4(6):1216-1223.
[96]Yang Zhaosheng，Zhou Huxing，Gao Xueying，Liu Songnan. MultiobjectiveModel for Emergency Resources Allocation[J]. Mathematical Problems inEngineering,2013.
[97]Zhou Huxing，Yang Zhaosheng，Gao Peng. A Hierarchical Control Model forRegional Traffic Signal Coordination[C]. Proceedings of the1st InternationalConference on Transportation Information and Safety,2011:964-970.