A knowledge-based system for road accident remedial work.
Computing Systems in Engineering
337 - 348.
A major task in road accident remedial work is to select sites for treatment and to identify appropriate treatments for them. This involves both skilled judgement and the processing of large quantities of accident data. A knowledge-based system has been developed to automate the routine parts of this task. The main feature of this system is the integration of a data-base system, empirical Bayesian statistical techniques, and Bayesian inference with uncertain inference, within a knowledge-based system. This is in accordance with the character of road accident remedial work in which evidence is uncertain due to its derivation from accident data which are both sparse and subject to stochastic variation. The automation of the routine parts of this work using the present system could speed them up significantly and make them more comprehensive. This would enable road safety engineers to concentrate on applying their judgement and skills to more specialized tasks in the work. Relevant expertise and experience can be incorporated in the system, thus allowing the skills of the most effective practitioners to be shared more widely than is possible at the moment. © 1993.
|Title:||A knowledge-based system for road accident remedial work|
|UCL classification:||UCL > School of BEAMS > Faculty of Engineering Science > Civil, Environmental and Geomatic Engineering|
Archive Staff Only