Full metadata record
DC FieldValueLanguage
dc.contributorDepartment of Computingen_US
dc.contributor.advisorChan, C. C. Keith (COMP)-
dc.creatorZhang, Pingcheng-
dc.identifier.urihttps://theses.lib.polyu.edu.hk/handle/200/10148-
dc.languageEnglishen_US
dc.publisherHong Kong Polytechnic University-
dc.rightsAll rights reserveden_US
dc.titleTraffic state prediction using deep learning methodsen_US
dcterms.abstractTraffic state prediction is a very important part of smart city related research. In the era of big data, we can get access to unprecedented massive amount of data, which allow us to better perceive and observe the operation of the city and explore its the operation mechanism. In recent years, the vigorous development of deep learning has enabled these data to play a more valuable role, making it possible to obtain knowledge about cities from the data. Firstly, this dissertation discussed the necessity and significance of traffic state prediction in smart cities, and holds that accurate traffic state prediction is the basic prerequisite and necessary condition for the realization of smart cities. Then, through the survey of the related works, we summarized the related research on traffic forecasting using deep learning methods. Through literature review, it can be noticed that due to the nature of data, most of works focused on scalar value prediction while few work has been done to study the shifting of traffic states. To fill this gap, this dissertation attempts to study the state shift rule of traffic states using deep learning methods. By strictly defining the problem, the traffic state prediction problem is tranlated into the time series prediction problem of adjacency matrices, and an innovative data structure is proposed to describe the traffic state. The experiment results show that this method of describing traffic state can capture traffic characteristics, and the prediction ability of the model can also provide some reference at the macro level.en_US
dcterms.extentviii, 42 pages : color illustrationsen_US
dcterms.isPartOfPolyU Electronic Thesesen_US
dcterms.issued2019en_US
dcterms.educationalLevelM.Sc.en_US
dcterms.educationalLevelAll Masteren_US
dcterms.LCSHHong Kong Polytechnic University -- Dissertationsen_US
dcterms.LCSHTraffic estimationen_US
dcterms.LCSHTravel -- Forecastingen_US
dcterms.LCSHMachine learningen_US
dcterms.LCSHTraffic engineering -- Data processingen_US
dcterms.accessRightsrestricted accessen_US

Files in This Item:
File Description SizeFormat 
991022270058203411.pdfFor All Users (off-campus access for PolyU Staff & Students only)1.79 MBAdobe PDFView/Open


Copyright Undertaking

As a bona fide Library user, I declare that:

  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.

By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

Show simple item record

Please use this identifier to cite or link to this item: https://theses.lib.polyu.edu.hk/handle/200/10148