C4.5: programs for machine learning
C4.5: programs for machine learning
Data mining
Machine Learning and Data Mining; Methods and Applications
Machine Learning and Data Mining; Methods and Applications
Machine Learning
Hi-index | 0.00 |
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.