A study of human reaction during the initial stages of a dwelling fire using a Bayesian network model

Abstract

Probabilistic modelling under uncertainty within the field of fire safety is examined in this article through the application of the Bayesian network technique. A Bayesian network model has been built to represent the initial stages of fire development within a dwelling and the associated events leading to human reaction. The model incorporates both hard and soft data, delivering posterior probabilities for selected outcomes. Case studies demonstrate how the model functions and provide evidence that it could be used for planning purposes and accident investigation. Finally, following a sensitivity analysis, discussion is undertaken on how the model could be further developed to investigate specific areas of interest and how they affect dwelling fires.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 8 citations exist upstream.