Predicting transient building fire based on external smoke images and deep learning

Development of a Smart System for Early Detection of Forest Fires based on Unmanned Aerial Vehicles

“…While this technology is characterized by zero direct risk to humans, it is unfortunately also very expensive to implement and very complex to manage and operate. Recently, it became possible to use the advancement in the UAV-related technologies in the forestry domain [1][2][3][4][5][6][7][8][9][14][15][16][17][18], including for fire detection, monitoring and suppression.…”

“…With the rapid advancements in the area of the Computer Vision (CV) and Artificial Intelligence (AI), modern smart visual surveillance systems have been successfully developed for many applications, including for detection of fire and smoke, for real-time evaluation and optimal decision-making in firefighting and rescue operations, etc. [5][6][7]. Fundamentally, the ability of the machines to learn, gain experience, adjust to new inputs, make adaptive decisions and perform different tasks in a human-like manner is generally described under the popular term Artificial Intelligence.…”

“…The applications of the UAVs have been well-documented with their huge potentials, benefits and impacts [3][4][5][6][7][14][15][16][17][18]. The data collection, remote measurements, estimation of the forest coverage, calculation of the biomass of the trees and evaluation of the different attributes of the forest vegetation are among the many examples of how the UAVs can be used for scientific activities, studies and protection of the forests.…”

Development of a Data-Based Machine Learning Model for Classifying and Predicting Property Damage Caused by Fire

“…Preprocessing of data is required for ML. The steps of data preprocessing are as follows: (1) identifying and removing outliers, (2) selecting factory building fires, (3) selecting building in use, i.e., the fire that occurs under construction or in the process of demolition can have a negative impact on the accuracy of the results, (4) excluding small fires which are less than 1 m 2 , i.e., very small fires are difficult to be analyzed precisely, (5) adjusting the levels of categorical variables, i.e., this step represents recategorizing, (6) changing nominal data to numeric data, i.e., this stage is needed to encourage learning efficiency, (7) generating derivative variables, and this step creates more meaningful variables, and (8) setting the dependent variable. After data preprocessing, learning of four different models by MATLAB is carried out.…”

“…Further, the framework research has been developed for the construction of algorithms that can secure time for safe evacuation (available safe egress time; ASET). In the process of the construction of algorithms, smoke movement was predicted by constructing a database by preparing profiles, such as the length of the atrium that can perform ventilation, fire size, ventilation conditions, and time after ignition [7]. In addition, other related studies have conducted the real-time prediction of temporary fire scenarios using external smoke images and deep learning algorithms.…”