An adaptive cluster-based sparse autoregressive model for large-scale multi-step traffic forecasting

被引:8
作者
Salamanis, Athanasios I. [1 ]
Lipitakis, Anastasia-Dimitra [2 ]
Gravvanis, George A. [1 ]
Kotsiantis, Sotiris [3 ]
Anagnostopoulos, Dimosthenis [2 ]
机构
[1] Democritus Univ Thrace, Sch Engn, Dept Elect & Comp Engn, Univ Campus, Xanthi 67100, Greece
[2] Harokopio Univ Athens, Dept Informat & Telemat, 9 Omirou Str, Athens 17778, Greece
[3] Univ Patras, Dept Math, Rion 26504, Greece
关键词
Multi-step traffic forecasting; Autoregressive model; Sparse least squares; Efficiency; Hyperparameter optimization; ARTIFICIAL NEURAL-NETWORK; TRAVEL-TIME; FLOW; PREDICTION;
D O I
10.1016/j.eswa.2021.115093
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Traffic forecasting has been extensively studied due to its importance for the design and development of Intelligent Transportation Systems (ITS). Most of the existing relevant literature focuses, almost exclusively, on the effectiveness of the traffic forecasting models, while neglecting the importance of computational efficiency. However, the need for faster models becomes increasingly urgent as the volume of available traffic data increases. In this paper, an effective and efficient model for large-scale multi-step traffic forecasting is presented. In particular, the classic autoregressive model is reformulated based on the idea that not all past traffic values are important for predicting future traffic values, and thus only some of them should be taken into account in the forecasting process. The selection of the appropriate past values is performed by the application of an eligibility criterion, controlled by a respective hyperparameter and its value is optimized using an efficient cluster-based method. The overall modelling approach leads to a sparse least squares problem, which is efficiently solved using a novel explicit preconditioned iterative method based on generic approximate sparse pseudoinverse. Large scale evaluation experiments were conducted using two real-world traffic datasets, and the experimental results indicate that the proposed model can achieve better balance between forecasting accuracy and computational efficiency compared to benchmark models.
引用
收藏
页数:13
相关论文
共 57 条
  • [1] Traffic Flow Prediction for Road Transportation Networks With Limited Traffic Data
    Abadi, Afshin
    Rajabioun, Tooraj
    Ioannou, Petros A.
    [J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2015, 16 (02) : 653 - 662
  • [2] Alghamdi T, 2019, INT WIREL COMMUN, P1227, DOI 10.1109/IWCMC.2019.8766698
  • [3] Anagnostopoulos D., 2020, 7 ANN C COMP SCI COM
  • [4] Bjorck A., 1996, NUMERICAL METHODS LE, DOI DOI 10.1137/1.9781611971484
  • [5] A graph CNN-LSTM neural network for short and long-term traffic forecasting based on trajectory data
    Bogaerts, Toon
    Masegosa, Antonio D.
    Angarita-Zapata, Juan S.
    Onieva, Enrique
    Hellinckx, Peter
    [J]. TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2020, 112 : 62 - 77
  • [6] Ranking learning algorithms: Using IBL and meta-learning on accuracy and time results
    Brazdil, PB
    Soares, C
    Da Costa, JP
    [J]. MACHINE LEARNING, 2003, 50 (03) : 251 - 277
  • [7] A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting
    Cai, Pinlong
    Wang, Yunpeng
    Lu, Guangquan
    Chen, Peng
    Ding, Chuan
    Sun, Jianping
    [J]. TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2016, 62 : 21 - 34
  • [8] Caltrans, 2021, CAL DEP TRANSP DISTR
  • [9] Chen WQ, 2020, AAAI CONF ARTIF INTE, V34, P3529
  • [10] A priori sparsity patterns for parallel sparse approximate inverse preconditioners
    Chow, E
    [J]. SIAM JOURNAL ON SCIENTIFIC COMPUTING, 2000, 21 (05) : 1804 - 1822