Discovering characteristics of aberrant driving behavior

Authors:
Loukas Tsironis;Vassilis Moustakis;Harry Mavropoulos;Emmanuel Maravelakis;Nicholas Bilalis
Affiliations:
Department of Production and Management Engineering, Democritus University of Thrace, Xanthi, Greece;Department of Production Engineering & Management, Technical University of Crete, Chania, Greece;Department of Production Engineering & Management, Technical University of Crete, Chania, Greece;Department of Natural Resources Engineering, Technological Educational Institute of Crete, Chania, Greece;Department of Production Engineering & Management, Technical University of Crete, Chania, Greece
Venue:
SMO'05 Proceedings of the 5th WSEAS international conference on Simulation, modelling and optimization
Year:
2005

Citing 4
Cited 0

C4.5: programs for machine learning

C4.5: programs for machine learning
Data mining

Data mining
Machine Learning and Data Mining; Methods and Applications

Machine Learning and Data Mining; Methods and Applications
Induction of Decision Trees

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recent studies have shown that unsafe driver acts can be classified into two distinct categories (i.e. errors and violations) entailing different measures for reducing road traffic accidents [1], [2]. A survey of over 1400 drivers in Greece is reported in which a variety of aberrant driving behaviors were identified. Factor analysis was performed to the data collected and seven groups of violations were found. Further statistical analysis showed correlations between those groups and accident liability. Data mining software SEE5 was then applied to reveal the tendencies of the Greek drivers and the descriptions of "dangerous" drivers. The algorithm traced the violations that are responsible for the risky driving acts and brought out useful, but yet hidden, information.