• Journal of the Korean Society of Safety
• /
• v.35 no.4
• /
• pp.32-39
• /
• 2020

The fire compartments with fire-resistant construction are installed in the principal structural parts of a building in order to reduce damage in the event of a building fire. As a fire may spread through a crack in the fire compartment, the firestop with secured performance is used according to the procedure, methods, and standards specified in the detailed operation guideline. According to the current detailed operation guideline, vertical members (wall penetration) and horizontal members (floor penetration) are classified into different categories respective to each other for the classification of the firestop. Therefore, an accreditation applicant must apply for the performance test for each structure even if the wall and the floor have the same structure. Also, Grade T is used for the firestop that penetrates the fire compartment. However, in the case of foreign countries, the use of Grade F for the firestop is allowed even if it penetrates the fire compartment. The result of the precedent studies also showed that there was a significantly low possibility of fire to spread even if Grade F was applied for a metallic duct that penetrated the fire compartment. In this study, the improved scheme for the classification and performance standard of firestops was presented by analyzing the results of precedent studies regarding the firestop and domestic and overseas firestop qualification systems.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2005.11a
• /
• pp.21-34
• /
• 2005

• Proceedings of the KSR Conference
• /
• 2007.05a
• /
• pp.1163-1167
• /
• 2007

Many railway safety measures are carried out after Daegue subway fire accident. Such as replacement of train interior material, fire extinguish and toxic gas evacuation facilities, exercise on emergency response, setting up of national safety management system, and safety technology research. But these safety measures are not considered by system safety due to lack of risk and hazard information. In order to assess fire risk on system level, we proposed hazard events and causes classification for railway fire accident risk analysis.

• Land and Housing Review
• /
• v.11 no.4
• /
• pp.99-104
• /
• 2020

This paper presents the recent research developments identified through a review of literature on the application of artificial intelligence in developing automated designs of fire protection facilities. The literature review covered research related to image recognition and applicable neural networks. Firstly, it was found that convolutional neural network (CNN) may be applied to the development of automating the design of fire protection facilities. It requires a high level of object detection accuracy necessitating the classification of each object making up the image. Secondly, to ensure accurate object detection and building information, the data need to be pulled from architectural drawings. Thirdly, by applying image recognition and classification, this can be done by extracting wall and surface information using dimension lines and pixels. All combined, the current review of literature strongly indicates that it is possible to develop automated designs for fire protection utilizing artificial intelligence.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_2
• /
• pp.1095-1106
• /
• 2019

Damage of forest fire should be investigated quickly and accurately for recovery, compensation and prevention of secondary disaster. Using remotely sensed data, burn severity is investigated based on the difference of reflectance or spectral indices before and after forest fire. Recently, the use of high resolution satellite and UAV imagery is increasing, but it is not easy to obtain an image before forest fire that cannot be predicted where and when. This study tried to analyze availability of high-resolution images and supervised classifiers on the burn severity classification. Two supervised classifiers were applied to the KOMPSAT-3A image and the UAV multispectral image acquired after the forest fire. The maximum likelihood (MLH) classifier use absolute value of spectral reflectance and the spectral angle mapper (SAM) classifier use pattern of spectra. As a result, in terms of spatial resolution, the classification accuracy of the UAV image was higher than that of the satellite image. However, both images shown very high classification accuracy, which means that they can be used for classification of burn severity. In terms of the classifier, the maximum likelihood method showed higher classification accuracy than the spectral angle mapper because some classes have similar spectral pattern although they have different absolute reflectance. Therefore, burn severity can be classified using the high resolution multispectral images after the fire, but an appropriate classifier should be selected to get high accuracy.

• Journal of the Korean Society of Safety
• /
• v.32 no.2
• /
• pp.46-51
• /
• 2017

This paper presents classification of domestic fire detector using response time index. Response time is measured using fire detector distributed in Korea, and the response time index is estimated. Plunge test prescribed by FM is conducted to measure response time of fire detector. The detector used to test is fixed temperature type(thermistor and bimetal type) and rate of rise temperature type(thermistor and pneumatic type). The nominal operation temperature of fixed temperature type detector is $70^{\circ}C$ and rate of rise temperature is $15^{\circ}C/min$. The fixed temperature type is measured 7 products, and the rate of rise temperature type is measured 5 products. The results show that in case of fixed temperature type(thermistor) is classified "Quick" or "Standard" and fixed temperature type(bimetal) is not classified. The rate of rise temperature type(thermistor) is classified "Fast" or "Ultra Fast" and the rate of rise temperature type(pneumatic) is classified "Very Fast" or "Ultra Fast". The pneumatic type shows more fast response than thermistor type. Also these results indicate the fixed temperature type(bimetal) is not suitable for early stage fire detection.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2010.04a
• /
• pp.501-505
• /
• 2010

원문이미지 참조

• Fire Science and Engineering
• /
• v.24 no.3
• /
• pp.1-8
• /
• 2010

This study is searched in the on actual condition and analysis about the fire fighting measure of 123 main wooden cultural properties designated by the Cultural Heritage Administration. First, the management of wooden cultural properties and the present condition of fire occurrence are arranged. Second, The field research and the information research of related government agencies are done from August. 2008 to October. 2008 about 123 main wooden cultural properties: Cultural properties designation classification, location classification, building area, number of possession cultural properties, present condition of fire fighting, a fire engine drive direction for fire suppression, number of self-defense fire brigade, fire administrator nomination, and the distance and time from a fire station are arranged in this study. Third, the inside and outside present conditions are classified and analyzed by average index for the fire occurrence risk of 123 main wooden cultural properties. And the basic data is arranged for the fire fighting measure of main wooden cultural properties.

• Fire Science and Engineering
• /
• v.19 no.3 s.59
• /
• pp.64-69
• /
• 2005

In order to decrease the area damaged by forest fires and to prevent the occurrence of forest fires, we are making an effort to improve prevention measures for forest fires. The objective of this study is developing the forest fire occurrence probability model by means of forest site characteristics such as soil type, topography, soil texture, slope, and drainage and forest fire sites. Conditional probability analysis and GIS were used in developing the forest fire occurrence probability model that was used in the classification of forest fire occurrence risk regions.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.12
• /
• pp.1596-1603
• /
• 2018

Rapidly detecting and warning of fires is necessary for minimizing human injury and property damage. Generally, when fires occur, both the smoke and the flames are generated, so fire detection systems need to detect both the smoke and the flames. However, most fire detection systems only detect flames or smoke and have the disadvantage of slower processing speed due to additional preprocessing task. In this paper, we implemented a fire detection system which predicts the flames and the smoke at the same time by constructing a CNN model that supports multi-labeled classification. Also, the system can monitor the fire status in real time by using Grad-CAM which visualizes the position of classes based on the characteristics of CNN. Also, we tested our proposed system with 13 fire videos and got an average accuracy of 98.73% and 95.77% respectively for the flames and the smoke.