Can I Park in the City Center? Predicting Car Park Occupancy Rates in Smart Cities

Daniel H. STOLFI, Enrique ALBA, Xin YAO

Research output: Journal PublicationsJournal Article (refereed)peer-review

12 Citations (Scopus)

Abstract

Finding an available parking space can be difficult in parts of most cities, especially in city centers. In this article, we address the study of parking occupancy data in Birmingham, Glasgow, Norfolk, and Nottingham in the United Kingdom. We test several prediction strategies, such as polynomial fitting, Fourier series, K-means clustering, and time series, and analyze their results. We use cross-validation to train the predictors and then test them with unseen occupancy data. Additionally, we develop a web service to visualize the current and historical parking data in a map, allowing users to consult the occupancy rate forecast up to one week in advance to satisfy their parking needs. We believe that the use of these accurate, intelligent techniques creates user services for citizens living in real smart cities as a way of improving their quality of life, decreasing wait times, and reducing fuel consumption. © 2019 The Society of Urban Technology.
Original languageEnglish
Pages (from-to)27-41
Number of pages15
JournalJournal of Urban Technology
Volume27
Issue number4
Early online date26 Apr 2019
DOIs
Publication statusPublished - 1 Oct 2020
Externally publishedYes

Bibliographical note

This research has been partially funded by the Spanish MINECO and FEDER projects TIN2016-81766-REDT (http://cirti.es), and TIN2017-88213-R (http://6city.lcc.uma.es)

Keywords

  • Smart mobility
  • parking prediction
  • open data
  • time series
  • machine learning

Fingerprint

Dive into the research topics of 'Can I Park in the City Center? Predicting Car Park Occupancy Rates in Smart Cities'. Together they form a unique fingerprint.

Cite this