Chunyang Han

TL;DR: This study comprehensively evaluated the multi-step prediction performance of models with different denoising algorithms using the traffic volume data collected from three loop detectors located on highway in city of Minneapolis to propose a prediction method by combiningDenoising schemes and support vector machine model to improve prediction accuracy.

TL;DR: A two-layer Stacking framework is proposed in this study to predict the crash injury severity and results show that Stacking model achieves superior performance evaluated by two indicators: accuracy and recall.

TL;DR: The RF model and RPHD model outperform the other three models in data fitting and model prediction in their respective methodological categories and three “heterogeneity” methods including RPHD, FM and QR outperform machine learning methods in model prediction as measured by MAPE.

TL;DR: It is found that ITPE method could effectively identify nodes or stations which are crucial both on network structure and passenger flow mobility while traditional undirected and unweighted network cannot completely identify.

TL;DR: The result shows that, in the hierarchical-random parameter model, the local regression coefficients and marginal effects of the roadlevel factors vary over a wide range in the selected counties, which clearly illustrates the non-stationary in the relationships between road level factors and crash frequency across the counties.