The extent to which accident severity can be predicted from accident-related data collected at a variety of locations is investigated. The 2005 accident dataset brought together by the Republic of Cyprus Police is employed; this dataset comprises 1407 records of 43 continuous and categorical input parameters and a single categorical output parameter representing accident severity. No transformation of the database has been opted for, either by extracting the parameters that are significant for the prediction task or by modifying the records in any way (e.g. via record selection or transformation). Aiming at maximally accurate and efficient prediction, a combination of probabilistic neural networks (PNN's) and decision trees (DT's) is implemented: the simple training and direct operation of the PNN is complemented by the hierarchical, exhaustive and recursive construction of the DT. By training pairs of PNN's on data from the partitions derived from the minimal necessary number of top DT nodes, both efficiency and accident prediction accuracy are maximized.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.