This study seeks to investigate the variations associated with lane lateral locations and days of the week in the stochastic and dynamic transition of traffic regimes (DTTR). In the proposed analysis, hierarchical regression models fitted using Bayesian frameworks were used to calibrate the transition probabilities that describe the DTTR. Datasets of two sites on a freeway facility located in Jacksonville, Florida, were selected for the analysis. The traffic speed thresholds to define traffic regimes were estimated using the Gaussian mixture model (GMM). The GMM revealed that two and three regimes were adequate mixture components for estimating the traffic speed distributions for Site 1 and 2 datasets, respectively. The results of hierarchical regression models show that there is considerable evidence that there are heterogeneity characteristics in the DTTR associated with lateral lane locations. In particular, the hierarchical regressions reveal that the breakdown process is more affected by the variations compared to other evaluated transition processes with the estimated intra-class correlation (ICC) of about 73%. The transition from congestion on-set/dissolution (COD) to the congested regime is estimated with the highest ICC of 49.4% in the three-regime model, and the lowest ICC of 1% was observed on the transition from the congested to COD regime. On the other hand, different days of the week are not found to contribute to the variations (the highest ICC was 1.44%) on the DTTR. These findings can be used in developing effective congestion countermeasures, particularly in the application of intelligent transportation systems, such as dynamic lane-management strategies.
CITATION STYLE
Kidando, E., Moses, R., Sando, T., & Ozguven, E. E. (2019). An application of Bayesian multilevel model to evaluate variations in stochastic and dynamic transition of traffic conditions. Journal of Modern Transportation, 27(4), 235–249. https://doi.org/10.1007/s40534-019-00199-2
Mendeley helps you to discover research relevant for your work.