Dynamic Freeway Travel-Time Prediction with Probe Vehicle Data: Link Based Versus Path Based

Abstract

Short-term travel-time prediction is very important to the real-time traveler information and route guidance system. Various methodologies have been developed for dynamic travel-time prediction. However, most existing studies assume that path travel time is the simple addition of travel times on the consisting links. Through simulation, it is shown that, under recurrent traffic conditions, direct measuring of path-based (or movement-based) travel time rather than link-based travel time could generate a more accurate prediction. Factors that would have an effect on the prediction accuracy are analyzed.

GPS Data-based Non-parametric Regression for Predicting Travel Times in Urban Traffic Networks

“…In addition, there have been many attempts to estimate future conditions using data mining. Some are parametric linear and non-linear regression models [7][8][9][10], nonparametric regression models [11], ARIMA models [12], space-time ARIMA models [13][14][15], ATHENA models [16], Kalman filters [17], artificial neural networks [18][19][20][21][22], and support vector machines [23]. Emerging traffic data collection techniques make these extrapolation-based models easier to use.…”

Feasibility of expanding traffic monitoring systems with floating car data technology

“…However, this study was limited to the highway environment, concluding with an optimal penetration rate of 4-5% in combination with a sample interval of 10-30 seconds. Because this penetration rate is significantly higher than the 1% found for highways by Chen & Chien [9] and because of the lack a similar optimization study for the urban environment, it was chosen to investigate both environments in this paper. For each environment the five different types of traffic intensity are examined.…”

“…The other studies relied on simulations. For the highway environment, Chen & Chien [9] proposed 1%, Nanthawichit et al [10] suggested 4 to 5% and van Lint & Hoogendoorn [11] obtained 2 to 4%. In an urban setting, Hong et al [12] proposed 2% while Mu et al [13] obtained 10%.…”

An Integrated Framework for Allocation of New Emergency Response Facilities in Developing Nations

“…Sprawling over an area of 114 sq. km, Chandigarh is home to 1.05 million people (Chandramouli 2011). The city of Chandigarh was one of the early planned cities in postindependence India and is known internationally for its architecture and urban design.…”