Predictive study of fire risk in building using Bayesian networks.
An object of class bn.fit. Refer to the documentation of bnlearn for details.
A discrete Bayesian network to calculate the probability of fire ignition in buildings (root nodes were given a uniform distribution). The probabilities were available from a repository. The vertices are:
Deficient electrical installation (T, F);
Bad quality of electical equipment (T, F);
Contact between incompatible products (T, F);
Mishandling of electrical devices (T, F);
Electrical overload (T, F);
Power cut (T, F);
Degradation of electrical wires (T, F);
Excessive heating in the conductors (T, F);
Insulation fault (T, F);
Short circuit (T, F);
Strong intensity electric (T, F);
Combustion of electrical equipment (T, F);
Appearance of electric arcs (T, F);
Appearence of sparks (T, F);
Chemical reactions (T, F);
Heat release (T, F);
Appearance of new products (T, F);
Electrical equipment malfunction (T, F);
Electrocution (T, F);
Fire ignition (T, F);
Poisoning (T, F);
Asphyxia (T, F);
Explosion (T, F);
Issa, S. K., Bakkali, H., Azmani, A., & Amami, B. (2024). Predictive study of fire risk in building using Bayesian networks. Journal of Theoretical and Applied Information Technology, 102(7).