Journal•
Journal of Highway and Transportation Research and Development
Research Institute of Highway
About: Journal of Highway and Transportation Research and Development is an academic journal. The journal publishes majorly in the area(s): Traffic engineering & Asphalt. Over the lifetime, 2411 publications have been published receiving 5178 citations.
Papers published on a yearly basis
Papers
More filters
Journal Article•
TL;DR: Review of existing forecasting models, probable frequency of traffic flow forecasting research field, and existing and new forecasting models established are presented.
Abstract: Real-time traffic flow forecasting is one of important issues of ITS research.Some forecasting models including history average,time-series,Kalman filtering,non-parametric regression,neural networks and synthetic model,etc,have been established.Review of these existing forecasting models,and probable frequency of traffic flow forecasting research field is presented..
92 citations
TL;DR: Asphalt mixture with Mafilon (abbreviated as MFL) is an automatic long-term snowmelt asphalt mixture, which replaces fine minerals and helps in the deicing process.
Abstract: Asphalt mixture with Mafilon (abbreviated as MFL) is an automatic long-term snowmelt asphalt mixture, which replaces fine minerals and helps in the deicing process. To validate the performa...
37 citations
Journal Article•
TL;DR: In order to find a function to replace the BPR function, an exponent parabolic regression equation is presented by regression method and the alfa and belta parameters of BPR funcition are gotten by means of regression method.
Abstract: Link Performance Function is a key factor to traffic assignment,and BPR function is one widely used,but the result is not satisfying when BPR function is used in some cases with its default parameter alfa and belta which are recommended by U.S Bureau of Public Roads.The paper deducted the relationship between link flow and travel time on link and gave an equation to express it.Comparing the equation with BPR function,it was found that there existed great difference between them.In order to find a function to replace the BPR function,an exponent parabolic regression equation is presented by regression method.In addition,the alfa and belta parameters of BPR funcition are gotten by means of regression method.
21 citations
TL;DR: The forecasting accuracy of the proposed hybrid prediction model, KNN-SVR, mimics the search mechanism of the KNN method to reconstruct a time series of historical traffic flow that is similar to the current traffic flow and is better than that of traditional prediction models, such as the SVR, and neural networks.
Abstract: To improve the forecasting accuracy of short-term traffic flow and provide precise and reliable traffic information for traffic management units and travelers, this study proposes a hybrid prediction model that is based on the characteristics of K-nearest neighbor (KNN) method and support vector regression (SVR). The proposed hybrid model, i.e. KNN-SVR, mimics the search mechanism of the KNN method to reconstruct a time series of historical traffic flow that is similar to the current traffic flow. Then, the SVR is used for short-term traffic flow forecasting. Using actual traffic flow data, we study the effect of the traffic flows on target and adjacent section roads and analyze the forecasting accuracy of the proposed model. Results show that the KNN-SVR model that considers the target and adjacent section roads has the best performance, having a mean absolute percentage error (MAPE) of 8.29%. The forecasting error of the KNN-SVR model that considers only the target section road is slightly large, having an average MAPE of 9.16%. Furthermore, the forecasting accuracy of the KNN-SVR model is better than that of traditional prediction models, such as the KNN method, SVR, and neural networks.
20 citations
TL;DR: The method of choosing the surveillance targets was proposed, and the K-means clustering algorithm was used to divide the UAV surveillance area into multiple sub-zones to convert this problem into UAV traffic surveillance scenarios without continuous flight distance constraint.
Abstract: Unmanned aerial vehicle (UAV) technology was introduced in traffic surveillance in sparse road networks, and a UAV allocation method with/without UAV continuous flight distance constraint was proposed. First, the method of choosing the surveillance targets was proposed. The UAV traffic surveillance problem without maximum flight distance constraint was then formulated as a traveling salesman problem, and the simulated annealing algorithm was introduced to solve this problem. As for UAV traffic surveillance problem with continuous flight distance constraint, the K-means clustering algorithm was used to divide the UAV surveillance area into multiple sub-zones to convert this problem into UAV traffic surveillance scenarios without continuous flight distance constraint. Finally, taking the Korla-Kuqa expressway of Xinjiang and its road network as the example, the proposed UAV-based traffic surveillance allocation method for sparse road networks was demonstrated and validated using several field experi...
18 citations