Using Neural Networks for Route and Destination Prediction in Intelligent Transport Systems

Mikluscak, Tomas; Gregor, Michal; Janota, Aleš

doi:10.1007/978-3-642-34050-5_43

Cited by 16 publications

(8 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks have been also used in similar problems in the area of intelligent transport systems (ITS). Authors [12] use feed-forward neural network for route and destination prediction. Our location prediction algorithm (LPA) doesn't suffer from mentioned problems.…”

Section: A An Overview Of Existing Solutions For Location Predictionmentioning

confidence: 99%

How to predict location and for what to use it?

Mikluscak

Janota

2014

Proceedings of the 2014 15th International Carpathian Control Conference (ICCC)

View full text Add to dashboard Cite

Significant developments of technology over the last years, especially in pervasive/ubiquitous computing, have made the dream of smart environment technology true. Merging of this technology with mathematical prediction apparatus allowed raising a new level of smart environments -automating the routine control tasks and pro-active interaction. This paper deals with the potential of automation of the routine control tasks to significantly improve human experience in our houses, offices, buildings and environments in general. We present advantages, shortcomings and upcoming challenges of this technology, stateof-the-art research results as well as the results of our original research in focused area.

show abstract

Section: A An Overview Of Existing Solutions For Location Predictionmentioning

confidence: 99%

How to predict location and for what to use it?

Mikluscak

Janota

2014

Proceedings of the 2014 15th International Carpathian Control Conference (ICCC)

View full text Add to dashboard Cite

show abstract

“…Trajectory prediction using artificial neural networks is described in [14]. The previous five locations visited by the target vehicle are used to estimate the future trajectory by training a feedforward artificial neural network with two hidden layers consisting of 500 neurons each.…”

Section: Related Workmentioning

confidence: 99%

“…It has been suggested that advertising signs can be targeted for nearby locations based on trajectories of approaching travelers [14]. Similarly, mobile apps may suggest restaurants, hotels, or other services based on the driver's expected trajectory [11].…”

Section: Introductionmentioning

confidence: 99%

“…Today, more drivers are taking advantage of applications that use realtime data to inform them of traffic information such as existing congestion or obstructions (e.g., the mobile app Waze). Accurate simulation results may advise these users of suggested routes and departure times that reduce congestion [14] or reduce travel time globally or individually; we note that these objectives may conflict, and do not necessarily result in identical policies [18].…”

Section: Introductionmentioning

confidence: 99%

“…Sources of dynamic traffic data are numerous. The government uses toll collection transponders, embedded roadway loop detectors [14], automatic license plate recognition, satellite imagery etc., and companies use information collected from drivers who carry smartphones (e.g., Google Maps) and other technologies. Technologies such as Bluetooth and WiFi detectors offer the ability to obtain partial trajectory information of individual vehicles in real-time in an operational transportation network.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Data-Driven Vehicle Trajectory Prediction

Pecher

Hunter

Fujimoto

2016

Proceedings of the 2016 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation

View full text Add to dashboard Cite

Vehicle trajectory or route prediction is useful in online, datadriven transportation simulation to predict future traffic patterns and congestion, among other uses. The various approaches to route prediction have varying degrees of data required to predict future vehicle trajectories. Three approaches to vehicle trajectory prediction, along with extensions, are examined to assess their accuracy on an urban road network. These include an approach based on the intuition that drivers attempt to reduce their travel time, an approach based on neural networks, and an approach based on Markov models. The T-Drive trajectory data set consisting of GPS trajectories of over ten thousand taxicabs and including 15 million data points in Beijing, China is used for this evaluation. These comparisons illustrate that using trajectory data from other vehicles can substantially improve the accuracy of forward trajectory prediction in the T-Drive data set. These results highlight the benefit of exploiting dynamic data to improve the accuracy of transportation simulation predictions.

show abstract