Answers are grounded in this paper and cite their sources.
Introduction. Such a definition as "fire rank" is used in the practice of fire respond and elimination management for quite a long time and has several meanings, the main of which are two: to show in detail the degree of complexity of the fire based on the fire rank, to allocate an adequate number of different types of resources for its successful elimination. The chain of elements: fire — degree of complexity — necessary resources, has not yet been embodied in effective methods and regulatory documents, which gives relevance to this area of research. Goals and objectives . The purpose of the paper is to build a technology for constructing models of fire ranks based on the use of cluster analysis. The tasks include exploratory data analysis and construction of a stochastic model of fire ranks. Methods. The study used methods of mathematical statistics and unsupervised machine learning in the variant of cluster analysis. Results and discussion. The possibility of determining a grid of fire ranks and the corresponding number of allocated vehicles based on processing by cluster analysis methods of a selection of retrospective data is shown. It is shown that the obtained results are very close to the norms of allocation of vehicles for fires in Moscow. The concept of stochastic fire ranks as a more informative model for resource allocation is put forward. Conclusions. The presented results of solving the problem of identifying a grid of fire ranks using a selection of retrospective data make it possible not only to determine the amount of resources required to eliminate a particular fire, but also make it possible to build adaptive stochastic models of fire ranks that are adequate to the region, industry and other subsets of fire objects.
No takes yet. Share an insight, caveat, or question.
Vilisov et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: