Home Archive Organization Program News Contact
PDF download
Cite article
Share options
Informations, rights and permissions
Issue image
Vol 10, Issue 1, 2020
Pages: 378 - 386
Original scientific paper
See full issue

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. 

Metrics and citations
Abstract views: 9
PDF Downloads: 0
Google scholar: See link
Article content
  1. Abstract
  2. Disclaimer
Received: >> Accepted: >> Published: 10.10.2020. Original scientific paper

APPLICATION OF THE DECISION TREE TECHNIQUE IN THE ANALYSIS OF TRAFFIC ACCIDENTS

By
Aleksandar Mamić ,
Aleksandar Mamić

Faculty of Technical Sciences Čačak, University of Kragujevac , Kragujevac , Serbia

Marija Blagojević ,
Marija Blagojević

Faculty of Technical Sciences Čačak, University of Kragujevac , Kragujevac , Serbia

Danijela Milošević
Danijela Milošević

Faculty of Technical Sciences Čačak, University of Kragujevac , Kragujevac , Serbia

Abstract

 The aim of the research is to examine the possibility of applying Weka software in the process of analysing traffic accidents that occurred in the territory of the Republic of Serbia. During the analysis, the J48 algorithm of the decision tree technique was applied. The database of traffic accidents from 2019, in which a total of 35,956 accidents were recorded, was taken over from the portal of open resources. The analysis of the same in Weka software, and the application of the mentioned algorithm, it came to the results, which showed that a large number of instances of the downloaded database were incorrectly classified. The reason for this is the inadequately standardized database model used in the research. In conclusion, the dominant thesis is that, in order to obtain useful information from databases, they need to have a clear and logical structure, as well as standardized elements for entering the value of attributes. 

The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.