[1] Pan Yiyong, Sun Lu, Characterizing heterogeneity in vehicular traffic speedusing two-step cluster analysis [J]. Journal of Southeast University (English Edition), 2012, 28 (4): 480-484. [doi:10.3969/j.issn.1003-7985.2012.04.019]

Copy

Characterizing heterogeneity in vehicular traffic speedusing two-step cluster analysis()

基于两步聚类法的交通流速度不均匀性分析

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

28

Issue:

2012 4

Page:

480-484

Research Field:

Traffic and Transportation Engineering

Publishing date:

2012-12-30

Info

Title:

Characterizing heterogeneity in vehicular traffic speedusing two-step cluster analysis

基于两步聚类法的交通流速度不均匀性分析

Author(s):

Pan Yiyong¹;  Sun Lu¹;  2

¹School of Transportation, Southeast University, Nanjing 210096
²Department of Civil Engineering, The Catholic University of America, Washington DC 20064, USA

潘义勇¹;  孙璐¹;  2

¹东南大学交通学院, 南京 210096; ²Department of Civil Engineering, The Catholic University of America, Washington DC 20064, USA

Keywords:

speed distribution;  heterogeneity;  mixture model;  cluster analysis

速度分布;  不均匀性;  混合模型;  聚类分析

PACS:

U491

DOI:

10.3969/j.issn.1003-7985.2012.04.019

Abstract:

In order to analyze the heterogeneity in vehicular traffic speed, a new method that integrates cluster analysis and probability distribution function fitting is presented. First, for identifying the optimal number of clusters, the two-step cluster method is applied to analyze actual speed data, which suggests that dividing speed data into two clusters can best reflect the intrinsic patterns of traffic flows. Such information is then taken as guidance in probability distribution function fitting. The normal, skew-normal and skew-t distribution functions are used to fit the probability distribution of each cluster respectively, which suggests that the skew-t distribution has the highest fitting accuracy; the second is skew-normal distribution; the worst is normal distribution. Model analysis results demonstrate that the proposed mixture model has a better fitting and generalization capability than the conventional single model. In addition, the new method is more flexible in terms of data fitting and can provide a more accurate model of speed distribution.

为了分析交通流的速度不均匀性, 提出了一种将聚类分析和概率分布函数拟合相结合的新方法.首先, 为了确定最优的子类数, 采用两步聚类法对实际的速度数据进行聚类分析, 分析表明将速度数据分为2类最能反映交通流的固有类型.然后, 将此信息用于指导概率分布函数拟合, 采用正态分布、偏正态分布和偏-T分布函数分别拟合各子类数据的概率分布, 发现偏-T分布函数拟合精度最高, 偏正态分布次之, 正态分布最差.模型分析结果表明, 所提出的混合分布模型比传统单个分布模型具有更好的拟合能力和通用性.此外, 新方法在数据拟合方面更加灵活, 且能提供更精确的速度分布模型曲线.

References:

[1] May A D. Traffic flow fundamentals [M]. New Jersey: Prentice-Hall, 1990.
[2] Katti B K, Raghavachari S. Modeling of mixed traffic speed data as inputs for the traffic simulation models [M]//Highway Research Bulletin. New Delhi, India: Indian Roads Congress, 1986, 28: 35-48.
[3] Leong H J. The distribution and trend of free speeds on two-lane two-way rural highways in New South Wales [C]//Proceedings of the 4th Australian Road Research Board Conference. Melbourne, Australia, 1968: 791-808.
[4] McLean J R. Observed speed distributions and rural road traffic operations [C]//Proceedings of the 9th Australian Road Research Board Conference. Brisbane, Australia, 1978: 235-244.
[5] Haight F A, Mosher W W. A practical method for improving the accuracy of vehicular speed distribution measurements [R]. Washington DC, USA: Highway Research Board, 1962: 92-116.
[6] Dey P P, Chandra C, Gangopadhaya S. Speed distribution curves under mixed traffic conditions [J]. Journal of Transportation Engineering, 2006, 132(6): 475-481.
[7] Ko J, Guensler R L. Characterization of congestion based on speed distribution: a statistical approach using Gaussian mixture model [C/D]//Transportation Research Board 2005 Annual Meeting. Washington DC, USA: TRB, 2005.
[8] Park B, Zhang Y, Lord D. Bayesian mixture modeling approach to account for heterogeneity in speed data [J]. Transportation Research Part B, 2010, 44(5): 662-673.
[9] Jun J. Understanding the variability of speed distributions under mixed traffic conditions caused by holiday traffic [J]. Transportation Research Part C, 2010, 18(4): 599-610.
[10] Zou Y J, Zhang Y L. Use of skew-normal and skew-t distributions for mixture modeling of freeway speed data [J]. Transportation Research Record, 2011, 2260: 67-75.
[11] SPSS Inc. Two-step cluster analysis [EB/OL].(2004)[2012-06-20]. http://support.spss.com/tech/stat/Algorithms/12.0/Two-step_cluster.pdf.
[12] Texas Department of Transportation. Roadway network of San Antonio in TransGuide program [EB/OL].(2006-12-31)[2012-06-20].

Memo

Memo:

Biographies: Pan Yiyong(1980—), male, graduate; Sun Lu(corresponding author), male, doctor, professor, sunl@cua.edu.
Foundation items: The National Science Foundation by Changjiang Scholarship of Ministry of Education of China(No.BCS-0527508), the Joint Research Fund for Overseas Natural Science of China(No.51250110075), the Natural Science Foundation of Jiangsu Province(No.BK200910046), the Postdoctoral Science Foundation of Jiangsu Province(No.0901005C).
Citation: Pan Yiyong, Sun Lu. Characterizing heterogeneity in vehicular traffic speed using two-step cluster analysis[J].Journal of Southeast University(English Edition), 2012, 28(4):480-484.[doi:10.3969/j.issn.1003-7985.2012.04.019]

Common functions