Vehicle incident hot spots identification: an approach for big data

In this work we introduce a fast big data approach for road incident hot spot identification using Apache Spark. We implement an existing immuno-inspired mechanism, namely SeleSup, as a series of MapReduce-like operations. SeleSup is composed of a number of iterations that remove data redundancies a...

Full description

Bibliographic Details
Main Authors: Triguero, Isaac, Figueredo, Grazziela P., Mesgarpour, Mohammad, Garibaldi, Jonathan M., John, Robert
Format: Conference or Workshop Item
Published: 2017
Online Access:https://eprints.nottingham.ac.uk/45214/
_version_ 1848797090880159744
author Triguero, Isaac
Figueredo, Grazziela P.
Mesgarpour, Mohammad
Garibaldi, Jonathan M.
John, Robert
author_facet Triguero, Isaac
Figueredo, Grazziela P.
Mesgarpour, Mohammad
Garibaldi, Jonathan M.
John, Robert
author_sort Triguero, Isaac
building Nottingham Research Data Repository
collection Online Access
description In this work we introduce a fast big data approach for road incident hot spot identification using Apache Spark. We implement an existing immuno-inspired mechanism, namely SeleSup, as a series of MapReduce-like operations. SeleSup is composed of a number of iterations that remove data redundancies and result in the detection of areas of high likelihood of vehicles incidents. It has been successfully applied to large datasets, however, as the size of the data increases to millions of instances, its performance drops significantly. Our objective therefore is to re-conceptualise the method for big data. In this paper we present the new implementation, the challenges faced when converting the method for the Apache Spark platform as well as the outcomes obtained. For our experiments we employ a large dataset containing hundreds of thousands of Heavy Good Vehicles incidents, collected via telematics. Results show a significant improvement in performance with no detriment to the accuracy of the method.
first_indexed 2025-11-14T19:58:21Z
format Conference or Workshop Item
id nottingham-45214
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:58:21Z
publishDate 2017
recordtype eprints
repository_type Digital Repository
spelling nottingham-452142020-05-04T19:05:46Z https://eprints.nottingham.ac.uk/45214/ Vehicle incident hot spots identification: an approach for big data Triguero, Isaac Figueredo, Grazziela P. Mesgarpour, Mohammad Garibaldi, Jonathan M. John, Robert In this work we introduce a fast big data approach for road incident hot spot identification using Apache Spark. We implement an existing immuno-inspired mechanism, namely SeleSup, as a series of MapReduce-like operations. SeleSup is composed of a number of iterations that remove data redundancies and result in the detection of areas of high likelihood of vehicles incidents. It has been successfully applied to large datasets, however, as the size of the data increases to millions of instances, its performance drops significantly. Our objective therefore is to re-conceptualise the method for big data. In this paper we present the new implementation, the challenges faced when converting the method for the Apache Spark platform as well as the outcomes obtained. For our experiments we employ a large dataset containing hundreds of thousands of Heavy Good Vehicles incidents, collected via telematics. Results show a significant improvement in performance with no detriment to the accuracy of the method. 2017-09-11 Conference or Workshop Item PeerReviewed Triguero, Isaac, Figueredo, Grazziela P., Mesgarpour, Mohammad, Garibaldi, Jonathan M. and John, Robert (2017) Vehicle incident hot spots identification: an approach for big data. In: 11th IEEE International Conference on Big Data Science and Engineering (IEEE BigDataSE)i, 1-4 August 2017, Sydney, Australia. http://ieeexplore.ieee.org/document/8029532/ doi:10.1109/Trustcom/BigDataSE/ICESS.2017.329 doi:10.1109/Trustcom/BigDataSE/ICESS.2017.329
spellingShingle Triguero, Isaac
Figueredo, Grazziela P.
Mesgarpour, Mohammad
Garibaldi, Jonathan M.
John, Robert
Vehicle incident hot spots identification: an approach for big data
title Vehicle incident hot spots identification: an approach for big data
title_full Vehicle incident hot spots identification: an approach for big data
title_fullStr Vehicle incident hot spots identification: an approach for big data
title_full_unstemmed Vehicle incident hot spots identification: an approach for big data
title_short Vehicle incident hot spots identification: an approach for big data
title_sort vehicle incident hot spots identification: an approach for big data
url https://eprints.nottingham.ac.uk/45214/
https://eprints.nottingham.ac.uk/45214/
https://eprints.nottingham.ac.uk/45214/