Neural network model for predicting pre-evacuation behavior of people in case of fire

Abstract

This article discusses a comprehensive study of pre-evacuation behavior of people in the event of an emergency. In this regard, it is advisable to use machine learning approaches, in particular neural networks, for data mining in the field of security. Statistical data obtained in emergency situations may be limited and generally uncertain, for this reason it is recommended to choose a neural network architecture - adaptive fuzzy inference Network System (ANFIS) based on the Takagi–Sugeno fuzzy inference system. The neural network architecture considered in the article in the form of an adaptive fuzzy inference network system architecture consists of five layers, where each layer performs a well-defined function. Data on the behavioral reaction of people before the evacuation to train an artificial neural network were obtained using such approaches as interviewing, questionnaire, survey.