• Journal of Internet Computing and Services
• /
• v.19 no.6
• /
• pp.101-112
• /
• 2018

A lot of manpower and budgets are being used to prevent fires, and only a small portion of the data generated during this process is used for disaster prevention activities. This study develops a prediction model of fire occurrence probability based on data mining in order to more actively use these data for disaster prevention activities. For this purpose, variables for predicting fire occurrence probability of various buildings were selected and data of construction administrative system, national fire information system, and Korea Fire Insurance Association were collected and integrated data set was constructed. After appropriate data cleansing and preprocessing, various data mining methodologies such as artificial neural network, decision trees, SVM, and Naive Bayesian were used to develop a prediction model of the fire occurrence probability of buildings. The most accurate model among the derived models is Linear SVM model which shows 68.42% as experimental data and 63.54% as verification data and it is the best model to predict fire occurrence probability of buildings. As this study develops the prediction model which uses only the set values of the specific ranges, future studies may explore more opportunites to use various setting values not shown in this study.

• The KIPS Transactions:PartD
• /
• v.9D no.6
• /
• pp.1119-1126
• /
• 2002

In this paper, we propose two predictive spatial data mining based on spatial statistics and apply for predicting the forest fire hazardous area. These are conditional probability and likelihood ratio methods. In these approaches, the prediction models and estimation procedures are depending un the basic quantitative relationships of spatial data sets relevant forest fire with respect to selected the past forest fire ignition areas. To make forest fire hazardous area prediction map using the two proposed methods and evaluate the performance of prediction power, we applied a FHR (Forest Fire Hazard Rate) and a PRC (Prediction Rate Curve) respectively. In comparison of the prediction power of the two proposed prediction model, the likelihood ratio method is mort powerful than conditional probability method. The proposed model for prediction of forest fire hazardous area would be helpful to increase the efficiency of forest fire management such as prevention of forest fire occurrence and effective placement of forest fire monitoring equipment and manpower.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.1
• /
• pp.255-261
• /
• 2013

In this paper, we developed and tested a program for prediction flash fire in a combat system. Purposes of the program are flash fire prediction of combat system for analysis vulnerability and survivability, and visualization for fire-related information. To do this, we defined critical components of the combat system which has probabilities of flash fire occurrence, and proposed Flash Fire Probability Tree which is based on Fault Tree Analysis(FTA). The program visualizes positions of critical components in combat system, positions of penetrated components, selected Flash Fire Probability Tree, temperature profile, and tables for properties of matters.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.7 no.4
• /
• pp.57-64
• /
• 2004

In order to decrease the area damaged by forest fires and to prevent the occurrence of forest fires, the forest fire danger rating system was developed to estimate forest fire risk by means of weather, topography, and forest type. Forest fires occurrence prediction needs to improve continually. Logistic regression and spatial analysis was used in developing the forest fire occurrence probability model. The forest fire danger index in accordance to the probability of forest fire occurrence was used in the classification of forest fire occurrence risk regions.

• Safety and Health at Work
• /
• v.11 no.3
• /
• pp.322-334
• /
• 2020

Background: Spontaneous combustion of coal is one of the factors which causes direct or indirect gas and dust explosion, mine fire, the release of toxic gases, loss of reserve, and loss of miners' life. To avoid these incidents, the prediction of spontaneous combustion is essential. The safety of miner's in the mining field can be assured if the prediction of a coal fire is carried out at an early stage. Method: Adularya Underground Coal Mine which is fully mechanized with longwall mining method was selected as a case study area. The data collected for 2017, by sensors from ten gas monitoring stations were used for the simulation and prediction of a coal fire. In this study, the fuzzy logic model is used because of the uncertainties, nonlinearity, and imprecise variables in the data. For coal fire prediction, CO, O₂, N₂, and temperature were used as input variables whereas fire intensity was considered as the output variable.The simulation of the model is carried out using the Mamdani inference system and run by the Fuzzy Logic Toolbox in MATLAB. Results: The results showed that the fuzzy logic system is more reliable in predicting fire intensity with respect to uncertainties and nonlinearities of the data. It also indicates that the 1409 and 610/2B gas station points have a greater chance of causing spontaneous combustion and therefore require a precautional measure. Conclusion: The fuzzy logic model shows higher probability in predicting fire intensity with the simultaneous application of many variables compared with Graham's index.

• Journal of the Korean Institute of Gas
• /
• v.14 no.1
• /
• pp.28-36
• /
• 2010

We have garnered 3,593 data of gas accidents reported for 12 years from 1995, and then analyzed the LPG vaporizer accidents according to their types and causes based on the classified database. According to the results the gas rupture has been the most common accident followed by the release, explosion and then fire accidents, the most frequent accident-occurring sub-cause is LPG check floater faults. In addition, we have applied the Poisson Probability Functions to predict the most-likely probabilities of fire, explosion, release and rupture with the LPG vaporizer in the upcoming 5 years. In compliance with Poisson Probability Functions results, in the item which occurs below 3 "LPG-Vaporizer-Fire", in the item which occurs below 5 "LPG-Vaporizer-Products Faults-Check Floater" and the item which occurs below 10 appeared with "LPG-Vaporizer-Products Faults". From this research we have assured the successive database updating will highly improve the anticipating probability accuracy and thus it will play a key role as a significant safety- securing guideline against the gas disasters.

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.2101-2108
• /
• 2008

Most of train fires which occur in usual cases do not grow up significantly on a large scale enough to bring about casualties and harmful damages. However, the consequence of some train fire accidents can be devastating disaster so that it would be even recorded in history in unusual cases. Accordingly, such a probability of fire disaster cannot be ignored in aspect of the railway safety assesment. A scale of injury and damage is very difficult to predict and analyze. Because it is depend on various factors, i.e. fire load, burning period, facilities, environment condition, and so on. Thus, a prediction of fire load could be understood as a one methodology to estimate railway safety assesment. The summation method which is one of them is used to evaluate the overall fire load by assuming that sum of heat release rate per unit area or mass of each composite material equals the total. However, since the train fire is classified into a compartment fire in under-ventilation condition. The summation method do not estimate a fire load completely. In this journal, Various methods to predict fire load are introduced and evaluated. Especially the fire simulation tool FDS(Fire Dynamics Simulator)which is based on the CFD(Computational Fluid Dynamics) is introduced, too. Through the FDS simulation, numerical analyses for the fire load and flame spread are performed. Then, these results of the simulation are validated through the comparison study with the experimental data. Then, limitations and approximations including in simulation process are discussed. The future direction of research is proposed.

• Journal of the Korean Society of Systems Engineering
• /
• v.5 no.1
• /
• pp.1-6
• /
• 2009

Gun fire solution computed in ballistic computing unit (BCU) needs to evaluated before applying in real fire. In this paper, ballistic performance analysis method is studied for reasonable prediction or hit probability with ballistics error presentation on hitting plane. Also Gun fire solution using interacting multiple model (IMM) algorithm is analyzed through proposed method.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.20 no.1
• /
• pp.11-22
• /
• 2018

The safety of tunnels is quantified by quantitative risk assessment when planning the disaster prevention facilities of railway tunnels, and it is decided whether they are appropriate. The purpose of this study is to estimate the probability of the train stopping in the tunnels at train fire, which has a significant effect on the results of quantitative risk assessment for tunnel fires. For this purpose, a model was developed to calculate the coasting distance of the train considering the coefficient of train running resistance. The probability of stopping in case of train fire in the tunnel is predicted by the Monte Carlo simulation method with the coasting distance and the emergency braking distance as parameters of the tunnel lengths and slopes, train initial driving speeds. The kinetic equations for predicting the coasting distance were analyzed by reflecting the coefficient train running resistance of KTX II. In the case of KTX II trains, the coasting distance is reduced as the slope increases in a tunnel with an upward slope, but it is possible to continue driving without stopping in a slope downward. The probability of the train stopping in the case of train fire in tunnel decreases as the train speed increases and the slope of the tunnel decreases. If human error is not taken into account, the probability that a high-speed train traveling at a speed of 250 km/h or above will stop in a tunnel due to a fire is 0% when the slope of the tunnel is 0.5% or less, and the probability of stopping increases rapidly as the tunnel slope increases and the tunnel length increases.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.9 no.3
• /
• pp.95-100
• /
• 2009

Fine fuel moisture code (FFMC), a main component of forest fire weather index(FWI) in the Canadian forest fire danger rating system(CFFDRS), indicated a probability of ignition through expecting a dryness of fine fuels. According to this code, a rising of temperature and wind velocity, a decreasing of precipitation and decline of humidity in a weather condition showed a rising of a danger rate for the forest fire. In this study, we analyzed a weather condition during 5 years in Kangwon province, calculated a FFMC and examined an application of FFMC. Very low humidity and little precipitation was a characteristic during spring and fall fire season in Kangwon province. 75% of forest fires during 5 years occurred in this season and especially 90% of forest fire during fire season occurred in spring. For developing of the prediction model for a forest fire occurrence probability, we used a logistic regression function with forest fire occurrence data and classified mean FFMC during 10 days. Accuracy of a developed model was 63.6%. To improve this model, we need to deal with more meteorological data during overall seasons and to associate a meteorological condition with a forest fire occurrence with more research results.