Accurate freeway travel time prediction with state-space neural networks under missing data

Lint, Hans van; Hoogendoorn, Serge P.; Zuylen, Henk J van

doi:10.1016/j.trc.2005.03.001

Cited by 390 publications

(173 citation statements)

References 28 publications

Supporting

Mentioning

168

Contrasting

Unclassified

Order By: Relevance

“…ANN is motivated by emulating the intelligent data processing ability of human brains. Its prominent advantage for solving complex non-linear problems makes ANN popular in travel time predicting (Van Lint et al 2005;Van Hinsbergen et al 2009). Chen et al (2004) developed a dynamic model that integrated the ANN and KF algorithms and used bus location data collected by APC system.…”

Section: Literaturementioning

confidence: 99%

Bus arrival time prediction using mixed multi-route arrival time data at previous stop

Hua

Wang

et al. 2017

Transport

View full text Add to dashboard Cite

Abstract. The primary objective of this paper is to develop models to predict bus arrival time at a target stop using actual multi-route bus arrival time data from previous stop as inputs. In order to mix and fully utilize the multiple routes bus arrival time data, the weighted average travel time and three Forgetting Factor Functions (FFFs) -F1, F2 and F3 -are introduced. Based on different combinations of input variables, five prediction models are proposed. Three widely used algorithms, i.e. Support Vector Machine (SVM), Artificial Neutral Network (ANN) and Linear Regression (LR), are tested to find the best for arrival time prediction. Bus location data of 11 road segments from Yichun (China), covering 12 bus stops and 16 routes, are collected to evaluate the performance of the proposed approaches. The results show that the newly introduced parameters, the weighted average travel time, can significantly improve the prediction accuracy: the prediction errors reduce by around 20%. The algorithm comparison demonstrates that the SVM and ANN outperform the LR. The FFFs can also affect the performance errors: F1 is more suitable for ANN algorithm, while F3 is better for SVM and LR algorithms. Besides, the virtual road concept in this paper can slightly improve the prediction accuracy and halve the time cost of predicted arrival time calculation.

show abstract

Section: Literaturementioning

confidence: 99%

Bus arrival time prediction using mixed multi-route arrival time data at previous stop

Hua

Wang

et al. 2017

Transport

View full text Add to dashboard Cite

show abstract

“…In review of literature, researchers have used parametric models in order to forecast the travel time, such as regression models or time series and nonparametric models that include ANN models [39,40,41]. Studies have shown that ANNs (including modular neural network model and statespace neural network model) are a powerful tool to predict travel time on freeways [41,40].…”

Section: Time Series Modelsmentioning

confidence: 99%

“…Studies have shown that ANNs (including modular neural network model and statespace neural network model) are a powerful tool to predict travel time on freeways [41,40].…”

Section: Time Series Modelsmentioning

confidence: 99%

Personal Advanced Traveler Assistant

Radu¹

2011

Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics

View full text Add to dashboard Cite

In spite of numerous road management schemes and developed infrastructure the society nowadays still faces the problem of highly congested roads due to the increasing trac demand.The focus of this thesis is to develop a complex and integrated system that addresses the challenges of dynamic trac assignment in modern times. To reach this goal we had to study the theory behind such systems, come with new ideas and implement them into a real world human-centered traveler information system. Taking into account state of the art systems in this eld we built a design for a Personal Advanced Traveler Assistant (PTA). The main purpose of PTA is to give routing advices depending on the users preferences and the available capacity in the network. The system incorporates a dynamic trac algorithm that employs a prediction model. The prediction model should use current trac updates and the routes of the guided cars in order to achieve an accurate prediction of the future traveling times.Next step was to implement a prototype. This is available through multiple interfaces like smart phones or desktop applications.The prediction model that the algorithm uses is based on historical data. Given the time constraints the prototype uses now only historical data but it can be easily extended to include live updates. This allowed us to build a prediction model that considers typical trac dynamics in order to estimate the traveling time.The performance measure of the trac assignment algorithm is the shortest traveling time. The algorithm that we implemented is a time dimensional-extended version of the Dijkstra algorithm. The algorithm is tested on real data collected from the highways in The Netherlands. We evaluate the performance of the algorithm by comparing it to two versions of the static Dijkstra algorithm.To conclude, we successfully implemented a working prototype that uses various technologies such as Java, the Open Street Map API for rendering the map or J2ME for the mobile phone client. The prototype that we have built represents a working proof of concept for a dynamic routing assistant. One advantage of the structure that we chose to implement is that each component can be further on extended independently. In this way we showed that such a system is feasible but we also left the possibility for dierent parts of the system to be extended into more advanced applications. The master thesis that you are reading represents my graduation project as a Master student at Delft University of Technology. I would like to take this opportunity and thank those who helped and supported me during the last 2 years. I thank especially to Prof. L.J.M. Rothkrantz for guiding my steps to successfully accomplish this master thesis. I am grateful to him for all the support he oered me, the eorts he invested in this research project, for giving me new ideas whenever I though I reached a dead end and not only. I would also like to thank him for trusting me and for making me feel more condent. I consider myself lucky to have met him and e...

show abstract

“…As is turns out, the provision of travel time information may reduce traffic congestion significantly and improve the performance of the whole network system (Ben-Akiva et al, 1991). Because of its critical role in traffic monitoring, extensive research has been conducted on the estimation and prediction of travel times on both freeways and urban roadways (Bhaskar et al, 2011, Coifman, 2002, Coifman and Krishnamurthy, 2007, Du et al, 2012, Ndoye et al, 2011, Sun et al, 2008, van Lint et al, 2005, van Lint and van der Zijpp, 2003. The widely used sensors to collect travel time data are loop detectors, which have been found to suffer from high maintenance costs and poor reliability (Rajagopal and Varaiya, 2007).…”

Section: Introductionmentioning

confidence: 99%

Probabilistic travel time progression and its application to automatic vehicle identification data

Nantes

Ngoduy

Miska

et al. 2015

Transportation Research Part B: Methodological

View full text Add to dashboard Cite

Travel time has been identified as an important variable to evaluate the performance of a transportation system. Based on the travel time prediction, road users can make their optimal decision in choosing route and departure time. In order to utilize adequately the advanced data collection methods that provide realtime different types of information, this paper is aimed at a novel approach to the estimation of long roadway travel times, using Automatic Vehicle Identification (AVI) technology. Since the long roads contain a large number of scanners, the AVI sample size tends to reduce and, as such, computing the distribution for the total road travel time becomes difficult. In this work, we introduce a probabilistic framework that extends the deterministic travel time progression method to dependent random variables and enables the off-line estimation of road travel time distributions. In the proposed method, the accuracy of the estimation does not depend on the size of the sample over the entire corridor, but only on the amount of historical data that is available for each link. In practice, the system is also robust to small link samples and can be used to detect outliers within the AVI data.

show abstract

Accurate freeway travel time prediction with state-space neural networks under missing data

Cited by 390 publications

References 28 publications

Bus arrival time prediction using mixed multi-route arrival time data at previous stop

Bus arrival time prediction using mixed multi-route arrival time data at previous stop

Personal Advanced Traveler Assistant

Probabilistic travel time progression and its application to automatic vehicle identification data

Contact Info

Product

Resources

About