A Novel Approach for Fire Safety

2022 ◽  
pp. 189-209
Author(s):  
Ebru Efeoglu ◽  
Gurkan Tuna
Keyword(s):  
Random Forest ◽  
Fire Safety ◽  
Patch Antenna ◽  
Single Unit ◽  
Fire Hazard ◽  
Vector Network Analyzer ◽  
Prototype System ◽  
Random Forest Algorithm ◽  
Novel Approach

Liquids and solvents in industrial products produce flammable vapor which, when mixed with air, can ignite or explode. The ease by which those liquids produce flammable vapors depends on their flashpoints which allow them to be categorized according to the fire hazard they exhibit in their normal use. In this chapter, a novel approach for the classification of liquids is proposed. The proposed approach relies on the use of a vector network analyzer, a patch antenna, and a group of classifiers. In this study, random forest and REPTree algorithms are preferred as classifers. As proven in the study, random forest algorithm can provide higher accuracy than REPTree algorithm in the classification of hazardous liquids. A prototype system is currently under development in order to integrate the components of the proposed approach into a single unit. It is expected that the prototype system will quickly and reliable make a non-contact classification of liquids in different kinds of bottles.

Methodology for assigning objects of protection to a certain risk category in the field of fire safety

2020 ◽  
pp. 26-35
Author(s):  
Денис Валерьевич Зобков ◽  
Александр Алексеевич Порошин ◽  
Андрей Александрович Кондашов ◽  
Евгений Васильевич Бобринев ◽  
Елена Юрьевна Удавцова
Keyword(s):  
Fire Safety ◽  
Economic Activity ◽  
Fire Hazard ◽  
Fire Risk ◽  
Federal State ◽  
Risk Category ◽  
Negative Consequences ◽  
Fire Hazards ◽  
Risk Categories

Проанализирован международный опыт реформирования проверок соблюдения требований пожарной безопасности и внедрения риск-ориентированного подхода. Разработана модель отнесения объектов защиты к категориям риска в зависимости от вероятного причинения вреда, который рассчитывается исходя из количества погибших и травмированных при пожарах людей. Сформулированы критерии отнесения объектов защиты к категориям риска. Выполнен расчет категорий риска для групп объектов, однородных по группам экономической деятельности и классам функциональной пожарной опасности. Проведено сравнение с существующей классификацией объектов защиты по категориям риска. The international experience of reforming of fire safety compliance checks and implementing a risk-based approach is considered. There are presented methodological approaches to calculating the risk of causing harm (damage) in buildings (structures) as a result of fire for the purpose of assignment of buildings and structures according to risk categories as well as justification of the frequency of scheduled inspections at these facilities. There is calculated the probability of fire occurrence for a group of objects of protection that are homogeneous by type of economic activity and functional fire hazard classes in order to assign objects of protection to certain risk categories. The social damage expressed in the death and injury of people as a result of fire is also calculated in order to assign objects of protection to certain risk categories. Classification of objects of protection according to the risk categories is performed using the indicator of the severity of potential negative consequences of fires. This indicator characterizes the degree of excess of the expected risk of negative consequences of fires for the corresponding group of objects of protection in relation to the value of the permissible risk of negative consequences of fire. The permissible risk of negative consequences of fires is calculated on the basis of statistical data, taking into account the value of the individual fire risk of exposure of critical values of fire hazards on person in buildings and structures. The criteria for assigning groups of objects of protection to the appropriate risk categories are formulated on the basis of formation of distribution of numerical values of the severity of potential negative consequences of fires. There are carried out the assessment of the severity of potential negative consequences of fires for objects of protection that are homogeneous by type of economic activity and functional fire hazard classes, and also the risk categories of the corresponding groups of objects are determined. The proposed classification of objects of protection according to risk categories is compared with the existing classification. The obtained results of calculations showed that scheduled inspections of objects of protection by the Federal state supervision bodies, depending on the assigned risk category and with corresponding frequency, have significant role in improving the level of fire safety of objects. The decrease in the intensity of scheduled inspections, at the same time, may lead to a corresponding decrease in the level of fire protection of objects.

scholarly journals Classification of Continuous Sky Brightness Data Using Random Forest

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Rhorom Priyatikanto ◽  
Lidia Mayangsari ◽  
Rudi A. Prihandoko ◽  
Agustinus G. Admiranto
Keyword(s):  
Random Forest ◽  
Observation Time ◽  
Classification Model ◽  
Posterior Distributions ◽  
Random Forest Algorithm ◽  
Negative Effect ◽  
Sky Brightness ◽  
Global Statistics ◽  
Effect Of Light

Sky brightness measuring and monitoring are required to mitigate the negative effect of light pollution as a byproduct of modern civilization. Good handling of a pile of sky brightness data includes evaluation and classification of the data according to its quality and characteristics such that further analysis and inference can be conducted properly. This study aims to develop a classification model based on Random Forest algorithm and to evaluate its performance. Using sky brightness data from 1250 nights with minute temporal resolution acquired at eight different stations in Indonesia, datasets consisting of 15 features were created to train and test the model. Those features were extracted from the observation time, the global statistics of nightly sky brightness, or the light curve characteristics. Among those features, 10 are considered to be the most important for the classification task. The model was trained to classify the data into six classes (1: peculiar data, 2: overcast, 3: cloudy, 4: clear, 5: moonlit-cloudy, and 6: moonlit-clear) and then tested to achieve high accuracy (92%) and scores (F-score = 84% and G-mean = 84%). Some misclassifications exist, but the classification results are considerably good as indicated by posterior distributions of the sky brightness as a function of classes. Data classified as class-4 have sharp distribution with typical full width at half maximum of 1.5 mag/arcsec2, while distributions of class-2 and -3 are left skewed with the latter having lighter tail. Due to the moonlight, distributions of class-5 and -6 data are more smeared or have larger spread. These results demonstrate that the established classification model is reasonably good and consistent.

scholarly journals Classification of healthy and diseased retina using SD-OCT imaging and Random Forest algorithm

PLoS ONE ◽  
2018 ◽  
Vol 13 (6) ◽  
pp. e0198281 ◽  
Author(s):  
Md Akter Hussain ◽  
Alauddin Bhuiyan ◽  
Chi D. Luu ◽  
R. Theodore Smith ◽  
Robyn H. Guymer ◽  
...  
Keyword(s):  
Random Forest ◽  
Random Forest Algorithm ◽  
Oct Imaging ◽  
Sd Oct

Random forest algorithm for classification of multiwavelength data

2009 ◽  
Vol 9 (2) ◽  
pp. 220-226 ◽  
Author(s):  
Dan Gao ◽  
Yan-Xia Zhang ◽  
Yong-Heng Zhao
Keyword(s):  
Random Forest ◽  
Random Forest Algorithm
Sign in / Sign up

Export Citation Format

Share Document