ALGORITHM FOR CLASSIFICATION OF FIRE HAZARDOUS SITUATIONS BASED ON NEURAL NETWORK TECHNOLOGIES

Abstract

Modern technological requirements and developing urban infrastructure pose the task of developing methods for recognizing and classifying fire hazardous situations. Quickly and effectively recognizing the initial signs of a fire becomes a vital aspect of ensuring the safety of people as well as property. In this regard, systems are developed, implemented, tested and implemented that can automatically recognize and classify fire hazardous situations. Classification of fire hazardous situations allows you to determine the degree of danger of detected deviations, which contributes to making more effective decisions to prevent the consequences of fires and their signs, such as a one-time short-term increase in temperature and smoke level, which may indicate failure of electrical components located near the sensors. The algorithm for classifying fire hazardous situations is developed for a complex of interconnected sensors, which in turn, due to its structure, allows you to detect even the slightest sign of fire. Within the framework of this study, an algorithm for classifying fire hazardous situations based on neural network technologies is presented. A description of existing classes of fire hazardous situations is provided, as well as the criteria by which data for these classes were marked. The algorithm was modeled on training and test samples, presenting the accuracy parameters used, the formula for their calculations, and the results of classifying fire hazardous situations. A study was carried out of the influence of the sample step in the database sample on the accuracy parameters and training time of the neural network. The developed algorithm is implemented in the Python programming language in the PyCharm IDE. The dataset for training and testing was obtained from real sources containing information about detected fire hazardous situations in subways in which a complex of interconnected sensors is installed. The results of modeling the algorithm showed that the proposed algorithm has high accuracy for predictive classification of fire hazardous situations in real objects.