Please use this identifier to cite or link to this item: https://ktisis.cut.ac.cy/handle/10488/18394
DC FieldValueLanguage
dc.contributor.authorTambouratzis, Tatiana-
dc.contributor.authorSouliou, Dora-
dc.contributor.authorChalikias, Miltiadis-
dc.contributor.authorGregoriades, Andreas-
dc.date.accessioned2020-05-18T14:01:09Z-
dc.date.available2020-05-18T14:01:09Z-
dc.date.issued2014-12-30-
dc.identifier.citationJournal of Artificial Intelligence and Soft Computing Research,2014, vol. 4 no. 1 pp. 31-42en_US
dc.identifier.issn2449-6499-
dc.description.abstractThe development of universal methodologies for the accurate, efficient, and timely prediction of traffic accident location and severity constitutes a crucial endeavour. In this piece of research, the best combinations of salient accident-related parameters and accurate accident severity prediction models are determined for the 2005 accident dataset brought together by the Republic of Cyprus Police. The optimal methodology involves: (a) information mining in the form of feature selection of the accident parameters that maximise prediction accuracy (implemented via scatter search), followed by feature extraction (implemented via principal component analysis) and selection of the minimal number of components that contain the salient information of the original parameters, which combined bring about an overall 74.42% reduction in the dataset dimensionality; (b)accidentseveritypredictionviaprobabilisticneuralnetworksandrandomforests,both of which independently accomplish over 96% correct prediction and a balanced proportionofunder-andover-estimationsofaccidentseverity. Anexplanationofthesuperiority of the optimal combinations of parameters and models is given, as is a comparison with existing accident classification/prediction approaches.en_US
dc.language.isoenen_US
dc.relation.ispartofJournal of Artificial Intelligence and Soft Computing Researchen_US
dc.rights© Sciendoen_US
dc.titleMaximising Accuracy and Efficiency of Traffic Accident Prediction Combining Information Mining with Computational Intelligence Approaches and Decision Treesen_US
dc.typeArticleen_US
dc.collaborationEuropean University Cyprusen_US
dc.collaborationUniversity of Piraeusen_US
dc.collaborationNational Technical University of Athensen_US
dc.subject.categoryElectrical Engineering - Electronic Engineering - Information Engineeringen_US
dc.journalsOpen Accessen_US
dc.countryCyprusen_US
dc.countryGreeceen_US
dc.subject.fieldEngineering and Technologyen_US
dc.publicationPeer Revieweden_US
dc.identifier.doi10.2478/jaiscr-2014-0023en_US
dc.relation.issue1en_US
dc.relation.volume4en_US
cut.common.academicyear2014-2015en_US
dc.identifier.spage31en_US
dc.identifier.epage42en_US
item.openairecristypehttp://purl.org/coar/resource_type/c_6501-
item.fulltextNo Fulltext-
item.languageiso639-1en-
item.grantfulltextnone-
item.cerifentitytypePublications-
item.openairetypearticle-
crisitem.author.deptDepartment of Hotel and Tourism Management-
crisitem.author.facultyFaculty of Management and Economics-
crisitem.author.orcid0000-0002-7422-1514-
crisitem.author.parentorgFaculty of Management and Economics-
Appears in Collections:Άρθρα/Articles
CORE Recommender
Show simple item record

Page view(s)

31
Last Week
0
Last month
2
checked on Jan 20, 2021

Google ScholarTM

Check

Altmetric


Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.