Spatio-temporal analysis and machine learning for traffic accidents prediction

Diena Al-Dogom, Nour Aburaed, Mina Al-Saad, Saeed Almansoori

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

1 Citation (Scopus)
7 Downloads (Pure)

Abstract

Traffic accidents impose significant problems in our daily life due to the huge social, environmental, and economic expenses associated with them. The rapid development in data science, geographic data collection, and processing methods encourage researchers to evaluate, delineate traffic accident hotspots, and to effectively predict and estimate traffic accidents. In this study, traffic accidents dataset that covers United Kingdom for the time period between 2012-2014 is investigated. The methodology consists of extracting features weights, and then using these weights with statistical methods provided in ArcGIS in order to classify accidents according to severity and perform hotspot analysis and severity prediction. The proposed method can be effectively used by different authorities to implement an improved planning and management approaches for traffic accident reduction. Moreover, it can identify and locate road risk segments where immediate action should be considered.

Original languageEnglish
Title of host publication2019 2nd International Conference on Signal Processing and Information Security, ICSPIS 2019
Place of PublicationPiscataway, N.J.
PublisherIEEE
ISBN (Electronic)9781728138732
DOIs
Publication statusPublished - 26 Mar 2020
Event2nd International Conference on Signal Processing and Information Security, ICSPIS 2019 - Dubai, United Arab Emirates
Duration: 30 Oct 201931 Oct 2019

Conference

Conference2nd International Conference on Signal Processing and Information Security, ICSPIS 2019
Country/TerritoryUnited Arab Emirates
CityDubai
Period30/10/1931/10/19

Keywords

  • decision trees
  • GIS
  • gradient boosting
  • machine learning
  • spatial analysis
  • temporal analysis
  • traffic accidents

Fingerprint

Dive into the research topics of 'Spatio-temporal analysis and machine learning for traffic accidents prediction'. Together they form a unique fingerprint.

Cite this