<abstract xmlns="http://www.w3.org/1999/xhtml"><p> The 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) accident severity prediction via probabilistic neural networks and random forests, both of which independently accomplish over 96% correct prediction and a balanced proportion of under- and over-estimations of accident severity. An explanation of the superiority of the optimal combinations of parameters and models is given, as is a comparison with existing accident classification/prediction approaches</p></abstract>

The 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) accident severity prediction via probabilistic neural networks and random forests, both of which independently accomplish over 96% correct prediction and a balanced proportion of under- and over-estimations of accident severity. An explanation of the superiority of the optimal combinations of parameters and models is given, as is a comparison with existing accident classification/prediction approaches

Maximising Accuracy and Efficiency of Traffic Accident Prediction Combining Information Mining with Computational Intelligence Approaches and Decision Trees

Department of Industrial Management & Technology, University of Piraeus, 107 Deligiorgi St, Piraeus 185 34, Greece

School of Electrical and Computer Engineering, National Technical University of Athens, 9 Iroon Polytechniou St, Zografou 15780, Greece

Department of Business Administration, Technological Educational Institution of Peiraius, 250 Thivon and Petrou Ralli Av., 122 44 Egaleo, Greece

Department of Computer Science & Engineering, European University Cyprus, Cyprus

Journal of Artificial Intelligence and Soft Computing Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

The development of universal methodologies for the accurate, efficient, and timely prediction of traffic accident location and severity constitutes a crucial...

Maximising Accuracy and Efficiency of Traffic Accident Prediction Combining Information Mining with Computational Intelligence Approaches and Decision Trees

Published Online: Dec 30, 2014

Page range: 31 - 42

DOI: https://doi.org/10.2478/jaiscr-2014-0023

© 2015

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.