Computational & Technology Resources
an online resource for computational,
engineering & technology publications
Civil-Comp Proceedings
ISSN 1759-3433
CCP: 12
Edited by: B.H.V. Topping
Paper III.3

A Knowledge-Based System for Road Accident Remedial Work

J. Wu and B.G. Heydecker

Transport Studies Group, University College, London, England

Full Bibliographic Reference for this paper
J. Wu, B.G. Heydecker, "A Knowledge-Based System for Road Accident Remedial Work", in B.H.V. Topping, (Editor), "Artificial Intelligence and Civil Engineering", Civil-Comp Press, Edinburgh, UK, pp 83-93, 1991. doi:10.4203/ccp.12.3.3
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 i s the integration of a database 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 will enable road safety engineers to concentrate on applying their judgement and skills to more specialised 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.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £60 +P&P)