Reliable Real-Time Framework for Short-Term Freeway Travel Time Prediction
Journal of Transportation EngineeringPublished 16 November 2006
Hans van Lint
Citations92
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A reliable framework for online travel time prediction for freeways is presented, which could be used to generate traffic information messages on so-called dynamic route information panels on freeways and enables traffic managers to monitor in real time the reliability of this system without actually measuring travel times.
Abstract
It is widely acknowledged that traffic information has the potential of increasing the reliability in road networks and in alleviating congestion and its negative environmental and societal side effects. However, for these beneficial collective effects to occur, reliable and accurate traffic information is a prerequisite. Building on previous research, this article presents a reliable framework for online travel time prediction for freeways, which could, for example, be used to generate traffic information messages on so-called dynamic route information panels on freeways. Central in this framework is a so-called state-space neural network (SSNN) model, which learns to predict travel times directly from data obtained from real time traffic data collection systems. In this article we show that by using an ensemble of SSNN models also a measure for the reliability of each prediction can be produced. This enables traffic managers to monitor in real time the reliability of this system without actually measuring travel times.
Keywords
Social SciencesEngineering
Choice Reviews OnlineNeural networks for pattern recognition
18,687 Citations1994
This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition, and is designed as a text, with over 100 exercises, to benefit anyone involved in the fields of neural computation and pattern recognition.
Neural Networks for Pattern Recognition
12,198 Citations1995Chris Bishop
Proceedings of International Conference on Neural Networks (ICNN'97)Gauss-Newton approximation to Bayesian learning
1,391 Citations2002F. Dan Foresee, Martin Hagan
The application of Bayesian regularization to the training of feedforward neural networks is described, using a Gauss-Newton approximation to the Hessian matrix to reduce the computational overhead.
Fundamentals of Transportation and Traffic Operations
874 Citations1997Carlos F. Daganzo
This book contains chapters on "tools", covering topics such as graphical methods, optimization, probability, stochastic processes, statistics and simulation, which are complemented by application chapters on traffic dynamics, control, observation, and scheduled modes.
Network Computation in Neural SystemsProbable networks and plausible predictions — a review of practical Bayesian methods for supervised neural networks
838 Citations1995David Mackay
Practical techniques based on Gaussian approximations for implementation of these powerful methods for controlling, comparing and using adaptive networks are described.
Transportation Research Part C Emerging TechnologiesA multivariate state space approach for urban traffic flow modeling and prediction
508 Citations2003Antony Stathopoulos, Matthew G. Karlaftis
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.
Transportation Research Part C Emerging TechnologiesAccurate freeway travel time prediction with state-space neural networks under missing data
440 Citations2005Hans van Lint, Serge Hoogendoorn +1 more
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.
Computer-Aided Civil and Infrastructure EngineeringForecasting Freeway Link Travel Times with a Multilayer Feedforward Neural Network
350 Citations1999Dongjoo Park, Laurence R. Rilett
It was found that when predicting one or two time periods into the future, the ANN model that only considered previous travel times from the target link gave the best results, however, when predicting three to five time Periods into the Future, theANN model that employed travel time from upstream and downstream links in addition to thetarget link gave superior results.
Network Computation in Neural SystemsProbable networks and plausible predictions — a review of practical Bayesian methods for supervised neural networks
326 Citations1995David Mackay
Transportation Research Part C Emerging TechnologiesShort-term travel time prediction
320 Citations2003Xiaoyan Zhang, John A. Rice
The effectiveness of the proposed method to predict freeway travel times using a linear model in which the coefficients vary as smooth functions of the departure time is demonstrated by applying the method to two real-life loop detector data sets.
Transportation Research Part A Policy and PracticeEstimating travel times and vehicle trajectories on freeways using dual loop detectors
301 Citations2002Benjamin Coifman
This paper presents a method for estimating link travel time using data from an individual dual loop detector, without requiring any new hardware, that exploits basic traffic flow theory to extrapolate local conditions to an extended link.
Journal of Transportation EngineeringDynamic Travel Time Prediction with Real-Time and Historic Data
295 Citations2003Steven Chien, Chandra Mouly Kuchipudi
The results reveal that the travel times predicted with link- based data are better than that predicted with path-based data during off peak period and vice versa.
Transportation Research Record Journal of the Transportation Research BoardFreeway Travel Time Prediction with State-Space Neural Networks: Modeling State-Space Dynamics with Recurrent Neural Networks
286 Citations2002Hans van Lint, Serge Hoogendoorn +1 more
An approach to freeway travel time prediction based on recurrent neural networks is presented, which is capable of dealing with the spatiotemporal relationships implicitly and could develop an internal model linked to the underlying traffic processes.
Journal of Transportation EngineeringSpectral Basis Neural Networks for Real-Time Travel Time Forecasting
239 Citations1999Dongjoo Park, Laurence R. Rilett +1 more
This paper examines how real-time information gathered as part of intelligent transportation systems can be used to predict link travel times for one through five time periods ahead and found that the spectral basis artificial neural network (SNN) gave the best overall results.
Transportation Research Record Journal of the Transportation Research BoardForecasting Multiple-Period Freeway Link Travel Times Using Modular Neural Networks
225 Citations1998Dongjoo Park, Laurence R. Rilett
An examination on how realtime information gathered as part of intelligent transportation systems can be used to predict link travel times for one through five time periods found that the modular ANN outperformed a conventional singular ANN.
Travel time prediction with support vector regression
161 Citations2004Chun-Hsin Wu, Chia-Chen Wei +3 more
The feasibility of applying SVR in travel-time prediction is demonstrated and it is proved that SVR is applicable and perform well for traffic data analysis.
Transportation Research Record Journal of the Transportation Research BoardImproving a Travel-Time Estimation Algorithm by Using Dual Loop Detectors
156 Citations2003Hans van Lint, N.J. Van der Zijpp
Transportation Research Part A Policy and PracticeAccurate estimation of travel times from single-loop detectors
139 Citations1998Karl Petty, Peter J. Bickel +5 more
This paper presents a methodology to estimate link travl times directly from the single-loop loop detector flow and occupancy data without heavy reliance on the flawed speed calculations.
Journal of Transportation EngineeringTraffic Dynamics: Method for Estimating Freeway Travel Times in Real Time from Flow Measurements
107 Citations1996Do H. Nam, Donald R Drew
This paper presents a method for estimating freeway travel times in real time directly from flow measurements, which is desirable for present and future Intelligent Vehicle-Highway Systems applications and has potential applicable to automatic traffic control and automatic incident detection.
Transportation Research Record Journal of the Transportation Research BoardDirect Forecasting of Freeway Corridor Travel Times Using Spectral Basis Neural Networks
106 Citations2001Laurence R. Rilett, Dongjoo Park
A direct or one-step approach for freeway corridor travel time forecasting is proposed that automatically takes into account interrelationships between link travel times and found that the direct forecasting approach gave better results than any of the other models examined and that linkTravel time forecasting errors are not additive.
Short Term Traffic Forecasting Using the Local Linear Regression Model
98 Citations2002Hongyu Sun, Henry X. Liu +2 more
This paper proposes and applies local linear regression models to short-term traffic prediction and finds that the local linear methods consistently outperform the nearest neighborhood and kernel smoothing methods.
e-Archivo (Carlos III University of Madrid)On the asymptotic theory of subsampling
65 Citations1999Dimitris N. Politis, Joseph P. Romano +1 more
A simple and effective method for predicting travel times on freeways
61 Citations2002John Rice, Erik W. van Zwet
It is argued that the current situation of a stretch of freeway is well summarized by the 'current status travel time', the travel time that would result if one were to depart immediately and no significant changes in the traffic would occur.
STARS (University of Central Florida)Travel Time Prediction with Non-Linear Time Series
39 Citations1998Haitham Al-Deek, M P D'Angelo +1 more
A new approach for predicting travel times is developed and tested with travel time data for five incident free days with the goal of predicting recurrent congestion and produced reasonable errors for short-term travel time predictions.
University of Twente Research InformationA comparative analysis of short-range travel time prediction methods
38 Citations2003Giovanni Huisken, Eric C. van Berkum
Results of the assessment of short-range travel time predictions show that the Artificial Neural Network (ANN) method significantly outperforms the Dynamic Travel Time Estimation (DTTE) method, which in turn outperform the Static Travel time estimation method (STTE).
Infoscience (Ecole Polytechnique Fédérale de Lausanne)NETWORK STATE ESTIMATION AND PREDICTION FOR REAL-TIME TRANSPORTATION MANAGEMENT APPLICATIONS
19 Citations2002Moshe Ben‐Akiva, Michel Bierlaire +3 more
DynaMIT is a real-time system that can be used to generate guidance for travelers that implies that the traffic conditions experienced by the travelers are consistent with the condition assumed in generating the guidance.
Transportation Research Board 82nd Annual MeetingTransportation Research BoardToward a Robust Framework for Freeway Travel time Prediction: Experiments with Simple Imputation and State-Space Neural Networks
13 Citations2003Hans van Lint, Serge Hoogendoorn +1 more
This paper shows that incorporating corrupt data into the training procedure does increase the robustness of these SSNN models, but at the cost of predictive performance: there is a clear trade off between robustness and model accuracy.
8th World Congress on Intelligent Transport SystemsITS America, ITS Australia, ERTICO (Intelligent Transport Systems and Services - Europe)SHORT-TERM PREDICTION OF HIGHWAY TRAVEL TIME USING MLP-NEURAL NETWORKS
11 Citations2001Satu Innamaa
The purpose was to study the predictability of travel time on a 28-km long highway section based on on-line travel time measurements with video based on feedforward multilayer perceptron- (MLP)-neural networks.
PROCEEDINGS OF 6TH WORLD CONGRESS ON INTELLIGENT TRANSPORT SYSTEMS (ITS), HELD TORONTO, CANADA, NOVEMBER 8-12, 1999REAL-TIME APPLICATION OF METANET IN TRAFFIC MANAGEMENT CENTRES
6 Citations1999S A Smulders, Albert Meßmer +1 more
The METANET traffic simulation model was modified and extended to model the available traffic management controls and to be able to provide real-time predictions of speed, flow and travel times and was successfully connected to a real- time data interface.