Traffic Congestion Forecasting Based on Possibility Theory

详细信息    查看全文

• 作者：Zhanquan Sun ; Zhao Li ; Yanling Zhao
• 关键词：Traffic congestion ; Possibility theory ; Traffic flow forecasting ; SVM ; k ; means clustering
• 刊名：International Journal of Intelligent Transportation Systems Research
• 出版年：2016
• 出版时间：May 2016
• 年：2016
• 卷：14
• 期：2
• 页码：85-91
• 全文大小：381 KB
• 参考文献：1.Yang, Z.S.: Basis traffic information fusion technology and its application. China Railway Publish House, Beijing (2005)
  2.Persaud, B., Hall, F., Hall, L.: Congestion identification aspects of the McMaster detection algorithm. Transplant. Res. Rec. 1287, 167–175 (1990)
  3.Dudek, C., Messer, C., Nuckles, N.: Incident detection on urban freeways, pp. 12–24. Transportation Research Record, Washington (1974)
  4.Zadeh, L.A.: Fuzzy sets as a basis for a theory of possibility. Fuzzy Set. Syst. 1, 3–28 (1978)MathSciNet CrossRef MATH
  5.Dubois, D., Prade, H.: When upper probabilities are possibility measures. Fuzzy Set. Syst. 49, 65–74 (1992)MathSciNet CrossRef MATH
  6.Dubois, D., Prade, H.: Fundamentals of fuzzy sets. The Handbooks of Fuzzy Sets Series, Kluwer (2000). 343–438CrossRef MATH
  7.Dubois, D.: Possibility theory and statistical reasoning. Fuzzy Stat. Anal. 51(1), 47–69 (2006)MathSciNet MATH
  8.Dubois, D. Prade, H.: Possibility theory: an approach to computerized processing of uncertainty. Plenum Press (1988)
  9.Dubois, D., Nguyen, H.T., Prade, H.: Fuzzy sets and probability: misunderstanding, bridges and gaps, pp. 343–438. Fundamentals of Fuzzy Sets, Kluwer (2000)MATH
  10.Masson, M., Denoeux, T.: Inferring a possibility distribution from empirical data. Fuzzy Set. Syst. 157, 319–340 (2005)MathSciNet CrossRef MATH
  11.Dubois, D., Prade, H.: Possibility theory and its applications: A retrosptective and prospective view. The IEEE international conference on fuzzy systems 3–11 (2010)
  12.Ranjan, M., Peterson, A.D.,Ghosh, P.A.: A systematic evaluation of different methods for initializing the K-means clustering algorithm. IEEE transaction on knowledge and data engineering 522–537 (2010)
  13.Zhao, W.Z., Ma, H.F., He, Q.: Parallel K-means clustering based on MapReduce. Lect. Notes Comput. Sci. Vol. 5931, 674–679 (2009)CrossRef
  14.Cortes, C., Vapnik, V.: Support vector networks. Mach. Learn. 20, 273–297 (1995)MATH
  15.Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 27(2), 1–27 (2011)CrossRef
  16.Ekanayake, J., Li, H. et al.: Twister: A runtime for iterative MapReduce. The First International Workshop on MapReduce and its Applications of ACM HPDC, ACM press 810–818 (2010)
  
• 作者单位：Zhanquan Sun (1)
  Zhao Li (1) (2)
  Yanling Zhao (1)
  
  1. Shandong Computer Science Center (National Supercomputer Center in Jinan), Shandong Provincial Key Laboratory of Computer Networks, 19 Keyuan Road, Jinan, Shandong, 250014, China
  2. School of Software Engineering, Beijing Jiaotong University, Shang Yuan Cun, Hai Dian District, Beijing, 100044, China
  
• 刊物类别：Engineering
• 刊物主题：Electrical Engineering
  Civil Engineering
  Computer Imaging, Vision, Pattern Recognition and Graphics
  User Interfaces and Human Computer Interaction
  Automotive Engineering
  Robotics and Automation
  
• 出版者：Springer New York
• ISSN：1868-8659

文摘

Traffic congestion state identification is one of the most important tasks of ITS. Traffic flow is a nonlinear complicated system. Traffic congestion state is affected by many factors, such as road channelization, weather condition, drivers’ different driving behavior and so on. It is difficult to collect all necessary traffic information. Traffic congestion auto identification result based on incomplete traffic information exists uncertain. Little work has been done to analyze the uncertainty. Possibility theory introduced by Zadeh is an efficient means to present incomplete knowledge. Possibility distribution determination is an important task of possibility theory. In this paper, possibility theory is used to describe the uncertainty of traffic state. The possibility distribution of traffic state is determined according to the probability distribution of traffic flow parameters, such as volume, speed and occupancy and so on. The multi-variable distribution of traffic flow parameters is determined with large-scale traffic flow data. Large-scale traffic congestion samples are generated with parallel k-mean clustering method. Traffic congestion forecasting is based on the forecasting of traffic flow parameters with SVM (Support Vector Machines). At last, a practical example is analyzed with the proposed method.