Nonlinear multivariate time–space threshold vector error correction model for short term traffic state prediction

Abstract

The time-space threshold vector error correction (TS-TVEC) model is proposed and developed in this research for short term (hourly) traffic state prediction. The theory and method of cointegration with error correction mechanism is employed in the general design of the new statistical model TS-TVEC. An inherent connection is revealed between the error correction model and the transformed fundamental diagrams in macroscopic traffic flow theory. Error correction model is a linear model established on difference space, whereas, the fundamental relations between traffic variables exhibit piecewise linearity when they are transformed to difference space. Meanwhile, dynamics of traffic variables can be reflected in difference space. A threshold regime switching framework is implemented to deal with unknown structural breaks in non-stationary traffic time series to capture multiple traffic states. Spatial cross-correlated information is incorporated with a piecewise linear vector error correction model. As the TS-TVEC model is designed for nonlinear multivariate forecasting, it is compared to Neural Network, and Support Vector Regression model that are commonly used in this regard to test the effectiveness and robustness of the new statistical model. The TS-TVEC model was experimented on a small scale case in our empirical study and applied on a larger scale case thereafter. Both cases show that the TS-TVEC model is an effective tool that is capable of modelling the complexity of stochastic traffic processes and potentially applicable to real time traffic state prediction.

Traffic Flow Prediction during the Holidays Based on DFT and SVR

“…The parametric approach includes the historical average (HA) method, autoregressive moving average method (ARIMA) [6,7], seasonal autoregressive integrated moving average method (SARIMA) [8][9][10], and Kalman filter (KF) [11,12]. The nonparametric approach includes artificial neural networks (ANNS) [13][14][15][16][17], k-nearest neighbor (KNN) [18][19][20][21][22], support vector regression (SVR) [23,24], and the Bayesian model [25,26]. The hybrid approach mainly combines the parametric approach with the nonparametric approach [27][28][29][30][31][32][33][34][35].…”

Short-Term Traffic Flow Forecasting via Multi-Regime Modeling and Ensemble Learning

“…For the multi-regime model, the identified regimes are treated as the most important features, and will be used in the modeling. In addition, the temporal correlations of the forecasted traffic flow measure and the interactive correlations of the multiple traffic flow measures are also two significant factors that can be used to improve the forecasting accuracy [14,24,45]. With this in mind, the time-lagged and interactive features of the traffic flow are also added to the representative feature pool.…”

Short-term speed predictions exploiting big data on large urban road networks

“…Although the majority of previous studies conducted independent forecasting for each single monitored section of the road (Cai et al, 2016), several attempts were made in the past to catch spatial correlation between traffic variables on the road network by extending time-series models to multivariate form (Kamarianakis and Prastacos, 2005;Chandra and Al-Deek, 2009;Guo et al, 2014;Mai et al, 2015;Li et al, 2015a), through implicit prediction models that include a network structure, such as artificial neural networks (Fusco and Gori, 1996;Dougherty and Cobbett, 1997;Zhang, 2000;Zhu et al, 2014;Ma et al, 2015aMa et al, , 2015b, Bayesian networks (Sun et al, 2006;Castillo et al, 2008;Hofleitner et al, 2012;Chen et al, 2015), deep architecture models (Lv et al, 2015). Several authors devised hybrid methods that combine different techniques and use multiple predictors (among others : Zhang, 2003;Zheng et al, 2006;van Hinsbergen et al, 2009;Wang et al, 2014).…”