Show simple item record

dc.contributor.advisorKofod-Petersen, Anders
dc.contributor.advisorAamodt, Torkil
dc.contributor.advisorLevin, Tomas
dc.contributor.authorKanestrøm, Per Øyvind
dc.coverage.spatialNorway, Oslonb_NO
dc.date.accessioned2018-09-20T08:26:58Z
dc.date.available2018-09-20T08:26:58Z
dc.date.issued2017
dc.identifier.urihttp://hdl.handle.net/11250/2563560
dc.descriptionMaster of Science in Informatics. NTNU - Norwegian University of Science and Technology. Department of Computer Science.nb_NO
dc.description.abstractIn recent years there has been a vast increase in available data with the advancement of smart cities. In the domain of Intelligent Transportation Systems (ITS) this modernisation can positively effect transportation networks, thus cutting down travel time, increase efficacy, and reduce environmental impact from vehicles. Norwegian Public Roads Administration (NPRA) is currently deploying a new vehicle detector system named Datainn on all public roads in Norway. Datainn sends metadata on all detected vehicles in real time. This includes information about speed, gap between vehicles, weight, and classification of vehicle type. Many machine learning approaches has been researched in literature on how to forecast traffic flow information. One such approach is that of using Artificial Neural Networks (ANNs). In this research ANN based methods have been explored. This was done by first performing a state-of-the-art Structured Literature Review (SLR) on ANN methods in literature. From the review, Stacked Sparse Autoencoder (SSAE) model was compared with recent advances of Long Short-Term Memory (LSTM) and Deep Neural Network (DNN) on four different prediction horizons. The data foundation was the new Datainn system using traffic data from a highway around Norway’s capitol, Oslo. Further, the model performance was assessed with extended feature vectors including more metadata from Datainn. The results found that the LSTM model always outperformed DNN and SSAE, although in general the performance characteristics was somewhat similar. Extending the feature vector with more variables had a negative effect on DNN, while resulting in better performance for Recurrent Neural Network (RNN) on long-term (60 minute) forecasting horizons. For SSAE it had a slight positive effect, but not enough get better results than RNN or DNN.nb_NO
dc.description.sponsorshipStatens vegvesen Vegdirektoratetnb_NO
dc.language.isoengnb_NO
dc.publisher[P.Ø. Kanestrøm]nb_NO
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/deed.no*
dc.subjectStatens vegvesen Vegdirektoratetnb_NO
dc.subjectITSnb_NO
dc.subjectTrafikkflytnb_NO
dc.subjectTransportforskningnb_NO
dc.subjectTransportteknologinb_NO
dc.subjectKjøretøynb_NO
dc.titleTraffic flow forecasting with deep learningnb_NO
dc.typeMaster thesisnb_NO
dc.source.pagenumber96nb_NO


Files in this item

Thumbnail

This item appears in the following Collection(s)

  • Avhandlinger [600]
    Inneholder studentavhandlinger skrevet for og i samarbeid med Statens vegvesen.

Show simple item record

Attribution-NonCommercial-NoDerivatives 4.0 Internasjonal
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivatives 4.0 Internasjonal