DBPapers
DOI: 10.5593/SGEM2014/B21/S8.063

CLUSTERING ALGORITHM IN ORDER TO FIND ACCIDENT BLACK SPOTS IDENTIFIED BY GPS COORDIANTES

S. Szenasi, P. Csiba
Wednesday 1 October 2014 by Libadmin2014

References: 14th International Multidisciplinary Scientific GeoConference SGEM 2014, www.sgem.org, SGEM2014 Conference Proceedings, ISBN 978-619-7105-10-0 / ISSN 1314-2704, June 19-25, 2014, Book 2, Vol. 1, 497-504 pp

ABSTRACT
Black spots are areas in the public road network where the number of accidents is significantly higher than expected. There are several methods that may be used to find these black spots, they usually use the road number and road section based positioning system, which is very useful in cases when we want to find black spots in one road only. But it has several disadvantages in the case of junctions, interurban areas, etc. It would better to use GPS coordinates, but the already existing black spot search methods are not applicable in this case. This paper presents a modified DBSCAN based clustering method in order to find accident black spots. DBSCAN is a general clustering algorithm, so it has been adapted to work with road accidents identified by GPS coordinates. We also present a fast and accurate technique, which calculates the accident density in a given area.

Keywords: DBSCAN, clustering, accident, black spot, algorithm

Home | Contact | Site Map | Site statistics | Visitors : 213 / 353063

Follow site activity en  Follow site activity GEOINFORMATICS  Follow site activity Papers SGEM2014   ?

CrossRef Member    Indexed in ISI Web Of Knowledge   Indexed in ISI Web Of Knowledge
   

© Copyright 2001 International Multidisciplinary Scientific GeoConference & EXPO SGEM. All Rights Reserved.

Creative Commons License