Skip to content Skip to navigation
University of Warwick
  • Study
  • |
  • Research
  • |
  • Business
  • |
  • Alumni
  • |
  • News
  • |
  • About

University of Warwick
Publications service & WRAP

Highlight your research

  • WRAP
    • Home
    • Search WRAP
    • Browse by Warwick Author
    • Browse WRAP by Year
    • Browse WRAP by Subject
    • Browse WRAP by Department
    • Browse WRAP by Funder
    • Browse Theses by Department
  • Publications Service
    • Home
    • Search Publications Service
    • Browse by Warwick Author
    • Browse Publications service by Year
    • Browse Publications service by Subject
    • Browse Publications service by Department
    • Browse Publications service by Funder
  • Help & Advice
University of Warwick

The Library

  • Login
  • Admin

New applications of data science for intelligent transportation systems

Tools
- Tools
+ Tools

Cabrejas Egea, Alvaro (2020) New applications of data science for intelligent transportation systems. PhD thesis, University of Warwick.

[img]
Preview
PDF
WRAP_Theses_Cabrejas-Egea_2020.pdf - Submitted Version - Requires a PDF viewer.

Download (12Mb) | Preview
Official URL: http://webcat.warwick.ac.uk/record=b3678325~S15

Request Changes to record.

Abstract

Streets and motorways are the basic blocks in the core of our transportation networks. In recent years, increases in available sensory and computing power have allowed us to start massive gatherings of data related to their use and performance, and to obtain insightful information via data science. This, in turn, has increased our ability to create systems that estimate the state of the transportation networks and provide us with control capabilities over it, giving rise to the concept of Intelligent Transportation Systems. These systems aim to provide deeper levels of observability to our transportation networks so that their capacity can be increased without the need of further heavy investment to develop traffic infrastructure, especially in terms of laying new roads and streets.

In this thesis we aim to contribute to this process in both urban and interurban settings. Here we propose two different algorithms to estimate and forecast expected travel time in motorways over the long term, ranging from hours to a week. The first of them is centred around the identification of the different traffic regimes and leveraging their specific characteristics to improve estimation and forecasting. The second of them looks further into the differentiation between recurrent and non recurrent congestion from the point of view of statistical analysis in the frequency space, using the natural frequencies of the traffic system to tell them apart and exert prediction. We also delve into how Intelligent Transportation Systems can affect our cities, looking at how reinforcement learning can create independent agents capable of controlling traffic lights at intersections. We do this by first looking at the most effective agent architectures in different junctions of increasing complexity. Then we dive into the difference in performance for agents in charge of vehicular intersections, provided by an array of reward functions that use different measures obtained from the traffic flow. Finally, we expand these systems to also take pedestrians into account, investigating the rewards that produce the lowest waiting times when serving different modes of transportation with opposing needs.

Item Type: Thesis or Dissertation (PhD)
Subjects: H Social Sciences > HE Transportation and Communications
T Technology > TE Highway engineering. Roads and pavements
Library of Congress Subject Headings (LCSH): Traffic engineering -- Great Britain -- Data processing, Traffic congestion -- Great Britain -- Management, Intelligent transportation systems -- Great Britain
Official Date: November 2020
Dates:
DateEvent
November 2020UNSPECIFIED
Institution: University of Warwick
Theses Department: Mathematics for Real-World Systems Centre for Doctoral Training
Thesis Type: PhD
Publication Status: Unpublished
Supervisor(s)/Advisor: Connaughton, Colm
Sponsors: Alan Turing Institute
Format of File: pdf
Extent: xviii, 202 leaves : illustrations (some colour), colour map
Language: eng

Request changes or add full text files to a record

Repository staff actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics

twitter

Email us: wrap@warwick.ac.uk
Contact Details
About Us