Network-wide traffic state estimation using a mixture Gaussian graphical model and graphical lasso

被引:28
|
作者
Hara, Yusuke [1 ]
Suzuki, Junpei [2 ]
Kuwahara, Masao [3 ]
机构
[1] Univ Tokyo, Dept Civil Engn, Bunkyo Ku, 7-3-1 Hongo, Tokyo, Japan
[2] East Japan Railway Co, Shibuya Ku, 2-2-2 Yoyogi, Tokyo, Japan
[3] Tohoku Univ, Grad Sch Informat Sci, Aoba Ku, 6-6-06 Aoba, Sendai, Miyagi, Japan
关键词
Traffic state estimation; Probe vehicle; Gaussian graphical model; Mixture model; NONPARAMETRIC PROBLEMS; MAXIMUM-LIKELIHOOD; FLOW;
D O I
10.1016/j.trc.2017.12.007
中图分类号
U [交通运输];
学科分类号
08 ; 0823 ;
摘要
This study proposes a model that estimates unobserved highway link speeds by a machine learning technique using historical probe vehicle data. For highway traffic monitoring, probe vehicle data is one of the most promising data source. However, since such data do not always cover an entire study area, we cannot measure traffic speeds on all links in a time-dependent manner; quite a few links are unobserved. To continuously monitor speeds on all links, it is necessary to develop a technique that estimates speeds on unobserved links from historical observed link speeds. For this purpose, we extend the current Gaussian graphical model so as to use two or more multivariate normal distributions to accurately estimate unobserved link speeds. In general, since the number of unknown model parameters (mean parameters and covariance matrices) is enormous and also unobserved links always exist, the EM algorithm and the graphical lasso technique are employed to determine the model parameters. Our proposed model was applied to the Bangkok city center in Thailand as well as to the Fujisawa city in Japan. We confirmed that the model can estimate the unobserved link speeds quite reasonably.
引用
收藏
页码:622 / 638
页数:17
相关论文
共 50 条
  • [1] Network-wide traffic state estimation using a mixture Gaussian graphical model and graphical lasso
    Hara, Yusuke
    Suzuki, Junpei
    Kuwahara, Masao
    [J]. Transportation Research Part C: Emerging Technologies, 2018, 86 : 622 - 638
  • [2] The cluster graphical lasso for improved estimation of Gaussian graphical models
    Tan, Kean Ming
    Witten, Daniela
    Shojaie, Ali
    [J]. COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2015, 85 : 23 - 36
  • [3] LEARNING GAUSSIAN GRAPHICAL MODELS USING DISCRIMINATED HUB GRAPHICAL LASSO
    Li, Zhen
    Bai, Jingtian
    Zhou, Weilian
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 2471 - 2475
  • [4] A note on the Lasso for Gaussian graphical model selection
    Meinshausen, Nicolai
    [J]. STATISTICS & PROBABILITY LETTERS, 2008, 78 (07) : 880 - 884
  • [5] GRAPHICAL LASSO FOR HIGH-DIMENSIONAL COMPLEX GAUSSIAN GRAPHICAL MODEL SELECTION
    Tugnait, Jitendra K.
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 2952 - 2956
  • [6] Regularized Estimation of Piecewise Constant Gaussian Graphical Models: The Group-Fused Graphical Lasso
    Gibberd, Alexander J.
    Nelson, James D. B.
    [J]. JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 2017, 26 (03) : 623 - 634
  • [7] Gaussian Mixture Graphical Lasso with Application to Edge Detection in Brain Networks
    Yin, Hang
    Liu, Xinyue
    Kong, Xiangnan
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2020, : 1430 - 1435
  • [8] Partial Gaussian Graphical Model Estimation
    Yuan, Xiao-Tong
    Zhang, Tong
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2014, 60 (03) : 1673 - 1687
  • [9] Finding Genetic network using Graphical Gaussian Model
    Bag, Abhishek
    Barman, Bandana
    Saha, Goutam
    [J]. IEEE REGION 10 COLLOQUIUM AND THIRD INTERNATIONAL CONFERENCE ON INDUSTRIAL AND INFORMATION SYSTEMS, VOLS 1 AND 2, 2008, : 185 - +
  • [10] Network-Scale Traffic Modeling and Forecasting with Graphical Lasso
    Gao, Ya
    Sun, Shiliang
    Shi, Dongyu
    [J]. ADVANCES IN NEURAL NETWORKS - ISNN 2011, PT II, 2011, 6676 : 151 - 158