Journal ArticleDOI
Model for Predicting Distribution of Link Travel Times for Urban Signalized Roads
TLDR
A comparison of the distributions of link travel time predicted by the model with those derived from VISSIM simulation showed that travel time distributions can be predicted well under time-varying demand and different traffic conditions.Abstract:
Estimation and prediction of urban travel time are acknowledged as important yet challenging topics. The traffic flow theory as developed especially for freeway traffic does not give much help for modeling urban traffic processes. Urban travel times are irregular because of several disturbances on a path. The interruption of trips at signalized intersections causes a large part of the total delay that vehicles experience on a route. These delays vary with stochastic properties of traffic flow, including stochastic arrivals and departures at signalized intersections. As a result, a wide distribution of delay (travel times) can be found for a certain traffic condition and traffic control scheme. This paper proposes a procedure for predicting the distributions of urban link travel times. The core of this procedure is the proposed model of distributions of link travel times that considers stochastic arrivals and departures at intersections and the traffic control scheme explicitly. A comparison of the distrib...read more
Citations
More filters
Journal ArticleDOI
A tensor-based Bayesian probabilistic model for citywide personalized travel time estimation
TL;DR: A tensor-based Bayesian probabilistic model for citywide and personalized travel time estimation, using the large-scale and sparse GPS trajectories generated by taxicabs, which provides an effective and robust approach for urbanTravel time estimation and outperforms the considered competing methods.
Journal ArticleDOI
Clustering Approach for Assessing the Travel Time Variability of Arterials
TL;DR: The aggregated diagram graphically provides a direct assessment of vehicle travel times with respect to their departure and traffic flow and can be used to generate probabilistic travel time distributions when some input parameters are uncertain.
Journal ArticleDOI
Travel Time Reliability for Urban Networks: Modelling and Empirics
TL;DR: A network travel time distribution model based on the Johnson curve system is proposed and applied to field travel time data collected by Automated Number Plate Recognition cameras, finding a clear linear relation between the weighted average travel time rate and the weighted standard deviation can be observed for different time periods with time-varying demand.
Dissertation
Modélisation des lignes de bus pour la prévision temps réel et la régulation dynamique
TL;DR: In this paper, the authors propose a model of lignes-de-busses de bus, which is based on the modele LWR (long short-term memory).
Journal ArticleDOI
Development of Decision Support System for Integrated Active Traffic Management Systems Considering Travel Time Reliability
Whoibin Chung,Mohamed Abdel-Aty,Ho-Chul Park,Qing Cai,Mdhasibur Rahman,Yaobang Gong,Raj Ponnaluri +6 more
TL;DR: A new decision support system (DSS) using travel time reliability was developed for integrated active traffic management (IATM) including freeways and arterials and recommended an IATM strategy with the highest synergistic relationships in real time and contributed to enhancing the effectiveness of the IatM strategies.
References
More filters
Journal ArticleDOI
Dynamic prediction of traffic volume through Kalman filtering theory
TL;DR: In this article, two models employing Kalman filtering theory are proposed for predicting short-term traffic volume in Nagoya City, Japan, by taking into account data from a number of links.
Journal ArticleDOI
A multivariate state space approach for urban traffic flow modeling and prediction
TL;DR: Using 3-min volume measurements from urban arterial streets near downtown Athens, models were developed that feed on data from upstream detectors to improve on the predictions of downstream locations and it appears that the use of multivariate state space models improves on the prediction accuracy over univariate time series ones.
Journal ArticleDOI
Accurate freeway travel time prediction with state-space neural networks under missing data
TL;DR: This article proposes a freeway travel time prediction framework that exploits a recurrent neural network topology, the so-called state-space neural network (SSNN), with preprocessing strategies based on imputation that appears to be robust to the “damage” done by these imputation schemes.
Journal ArticleDOI
Short-term freeway traffic flow prediction : Bayesian combined neural network approach
TL;DR: A neural network model is introduced that combines the prediction from single neural network predictors according to an adaptive and heuristic credit assignment algorithm based on the theory of conditional probability and Bayes' rule and is found that most of the time, the combined model outperforms the singular predictors.
Journal ArticleDOI
Forecasting Traffic Flow Conditions in an Urban Network: Comparison of Multivariate and Univariate Approaches:
TL;DR: In this article, a comparison of the forecasting performance of these four models is undertaken with data sets from 25 loop detectors located in major arterials in the city of Athens, Greece, where the variable under study is the relative velocity, which is the traffic volume divided by the road occupancy.
Related Papers (5)
Uncertainty and Predictability of Urban Link Travel Time: Delay Distribution–Based Analysis
Fangfang Zheng,Henk J van Zuylen +1 more
Modeling Variability of Urban Travel Times by Analyzing Delay Distribution for Multiple Signalized Intersections
Fangfang Zheng,Henk J van Zuylen +1 more