MACHINE LEARNING IN ROAD ACCIDENT RESEARCH - DECISION TREES DESCRIBING ROAD ACCIDENTS DURING CROSS-FLOW TURNS

In-depth studies of behavioural factors in road accidents using conven tional methods are often inconclusive and costly. In a series of studi es exploring alternative approaches, 200 cross-flow junction road acci dents were sampled from the files of Nottinghamshire Constabulary, UK, coded for computer analysis using a specially devised 'Traffic Relate d Action Analysis Language', and then examined using different computa tional and statistical techniques. The present study employed an AI ma chine-learning method based on Quinlan's 'ID3' algorithm to create dec ision trees distinguishing the characteristics of accidents that resul ted in injury or in damage only; accidents of young male drivers; and those of the relatively more and less dangerous situations. For exampl e the severity of accidents involving turning onto a main road could b e determined with 79% accuracy from the nature of the other vehicle, s eason, junction type, and whether the Turner failed to notice another road user. Accidents involving young male drivers could be identified with 77% accuracy by knowing if the junction was complex, and whether the Turner waited or slowed before turning.