The evaluation of evidence in the forensic investigation of fire incidents (Part 1): an approach using Bayesian networks

The forensic investigation of the origin and cause of a fire incident is a particularly demanding area of expertise. As the available evidence is often incomplete or vague, uncertainty is a key element. The present study is an attempt to approach this through the use of Bayesian networks, which have been found useful in assisting human reasoning in a variety of disciplines in which uncertainty plays a central role. The present paper describes the construction of a Bayesian network (BN) and its use for drawing inferences about, propositions of interest, based upon a single, possibly non replicable item of evidence: detected residual quantities of a flammable liquid in fire debris. (C) 2004 Elsevier Ireland Ltd. All rights reserved.