Comparative analysis for traffic flow forecasting models with real-life data in Beijing

Ye, Rong; Zhang, Xingchen; Feng, Xia‐Ting; Ho, Т.K.; Wei, Wei; Xu, Dejie

doi:10.1177/1687814015620324

Cited by 17 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, the Wilcoxon signed rank test has been used in transportation studies, and it has been shown to be superior over traditional test approaches (19)(20)(21)(22)(23). The Wilcoxon signed rank test is mainly based on the ranking of the differences between pairs of samples.…”

Section: Methodsmentioning

confidence: 99%

Familiar versus Unfamiliar Drivers on Curves: Naturalistic Data Study

Pratt

Geedipally

Dadashova

et al. 2019

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Human factors studies have shown that route familiarity affects driver behavior in various ways. Specifically, when drivers become more familiar with a roadway, they pay less attention to signs, adopt higher speeds, cut curves more noticeably, and exhibit slower reaction times to stimuli in their peripheral vision. Numerous curve speed models have been developed for purposes such as predicting driver behavior, evaluating roadway design consistency, and setting curve advisory speeds. These models are typically calibrated using field data, which gives information about driver behavior in relation to speed and sometimes lane placement, but does not provide insights into the drivers themselves. The objective of this paper is to examine the differences between the speeds of familiar and unfamiliar drivers as they traverse curves. The authors identified four two-lane rural highway sections in the State of Indiana which include multiple horizontal curves, and queried the Second Strategic Highway Research Program (SHRP2) database to obtain roadway inventory and naturalistic driving data for traversals through these curves. The authors applied a curve speed prediction model from the literature to predict the speed at the curve midpoints and compared the predicted speeds with observed speeds. The results of the analysis confirm earlier findings that familiar drivers choose higher speeds through curves. The successful use of the SHRP2 database for this analysis of route familiarity shows that the database can facilitate similar efforts for a wider range of driver behavior and human factors issues.

show abstract

Section: Methodsmentioning

confidence: 99%

Familiar versus Unfamiliar Drivers on Curves: Naturalistic Data Study

Pratt

Geedipally

Dadashova

et al. 2019

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…The remaining problems are how to determine the time delay t i and embedding dimension m i , so that equation (2) or equation (3) holds.…”

Section: Methodsmentioning

confidence: 99%

“…Short-term traffic prediction is one of the most important areas in intelligent transportation system (ITS) research. [1][2][3] A number of ITS applications such as dynamic route guidance (DRG) and urban traffic control (UTC) can benefit from accurate prediction of traffic variables (including but not limited to traffic flow, travel time, traffic speed, and occupancy) for the shortterm future (less than 15 min). In reality, for traffic managers, the short-term traffic variables' prediction information would enable them to apply traffic control management early enough to prevent traffic congestion rather than to deal with the traffic problems after the traffic congestion has already occurred.…”

Section: Introductionmentioning

confidence: 99%

Short-term traffic flow prediction model using particle swarm optimization–based combined kernel function-least squares support vector machine combined with chaos theory

Shang

Lin

Yang

et al. 2016

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Short-term traffic flow prediction is an important part of intelligent transportation systems research and applications. For further improving the accuracy of short-time traffic flow prediction, a novel hybrid prediction model (multivariate phase space reconstruction-combined kernel function-least squares support vector machine) based on multivariate phase space reconstruction and combined kernel function-least squares support vector machine is proposed. The CC method is used to determine the optimal time delay and the optimal embedding dimension of traffic variables' (flow, speed, and occupancy) time series for phase space reconstruction. The G-P method is selected to calculate the correlation dimension of attractor which is an important index for judging chaotic characteristics of the traffic variables' series. The optimal input form of combined kernel function-least squares support vector machine model is determined by multivariate phase space reconstruction, and the model's parameters are optimized by particle swarm optimization algorithm. Finally, case validation is carried out using the measured data of an expressway in Xiamen, China. The experimental results suggest that the new proposed model yields better predictions compared with similar models (combined kernel function-least squares support vector machine, multivariate phase space reconstruction-generalized kernel function-least squares support vector machine, and phase space reconstruction-combined kernel function-least squares support vector machine), which indicates that the new proposed model exhibits stronger prediction ability and robustness.

show abstract

“…The vast availability of historical data and the ability to generalise non‐linear traffic condition has made k‐NN feasible for analysing the traffic structure [23, 30, 33–35]. Owing to complexity with seasonal ARIMA (SARIMA) models in modelling and forecasting extreme traffic conditions [36], recent enhancements to direct k‐NN methods are formulation of time constraint window to order the overlapping candidate, k‐NN – AVL binary tree to reduce search time [23, 26, 37, 38], and weighted Euclidean distance measure based k‐NN. Spatial and temporal information of traffic variables are used to formulate temporal k‐NN and spatial k‐NN, the enhanced k‐NN methods consider the temporal and spatial dependencies of traffic at successive steps [34].…”

Section: Related Workmentioning

confidence: 99%