• Journal of the Korean housing association
• /
• v.18 no.5
• /
• pp.133-141
• /
• 2007

The purpose of this study is to secure an evacuation time and to ensure safety by using an Ubiquitous Sensor Network computing when a fire breaks out at a super high-rise apartment housing. A super high-rise apartment housing that is a type of building to solve the problem of separation of the urban function and the phenomenon of hollowing out downtown has been on the increase, high-rise apartment housings occupying 52.7% of whole housings in 2005. However, if a fire breaks out, there would be serious damage since it accommodates many people and facilities as existence of vertical gigantism in the city. The architectural law in force has no clause on it which is universally applicable to general building, it is difficult to be applicable to a densely super high-rise apartment housing and there would be in danger of a resident's evacuation in the fire. Therefore, as a previous study to introduce an USN-based fire-warning facility and evacuation equipment, this study shows the improvement way after analyzing factors that are barriers to evacuaee's behavior of a super high-rise apartment housing and also shows establishment of the grade of vertical evacuation rank by SimuleX, one of the best computer simulation program.

• Proceedings of the KIPE Conference
• /
• 2018.11a
• /
• pp.1-3
• /
• 2018

When a fire is detected by a sensor of a fire detector, the fire is notified to the manager through the siren. However, if the manager is not indoors, prompt action may not be taken in the event of a fire. In this study, we would like to propose a platform system for fire prevention applying IoT to prevent problems that arise when building manager is absent. This paper presents the structure and operation principle of fire prevention platform system design using IoT, describes the overall system design through fire detector H/W design, micom S/W design and Android application development, and is expected to develop a system that can respond a little faster in case of fire.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.1
• /
• pp.110-116
• /
• 2024

Despite the continuous advancement of science and technology, fire accidents continue to occur without decreasing over time, so there is a constant need for a system that can accurately detect fires at an early stage. However, because most existing fire detection systems detect fire in the early stage of combustion when smoke is generated, rapid fire prevention actions may be delayed. Therefore we propose an early fire detection system that can perform early fire detection at a reasonable cost using LSTM, a deep learning model based on multi-gas sensors with high selectivity in the early stage of decomposition rather than the smoke generation stage. This system combines multiple gas sensors to achieve faster detection speeds than traditional sensors. In addition, through window sliding techniques and model light-weighting, the false alarm rate is low while maintaining the same high accuracy as existing deep learning. This shows that the proposed fire early detection system is a meaningful research in the disaster and engineering fields.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.4
• /
• pp.63-71
• /
• 2012

Recently, because most of buildings in the city become bigger and higher, so various convenient facilities and high-tech management skills are required to prevent potential disasters. Especially, because fires in huge buildings can cause serious damage, technologies and methods that help people quickly and safely to escape from the building is very important to extinguish the fire in initial state and to minimize the damage. This paper suggests a context-aware service system that can provide optimal escape routes to tenants with their smart-phones. The proposed system collects contexts with real time through USN(Ubiquitous Sensor Network) and provides an optimum escape route based on the collected contexts through service users' smart phones. In addition, The system provides not only safe routes from the fire but also valuable information for rescue operations with real time.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.3 no.2
• /
• pp.121-130
• /
• 2000

A practical method is proposed to improve hit probability of the digital gun fire control system, when the measured rate of the tracking sensor becomes biased under some operational situation. For ground moving target it is shown that the well-known Kalman filter which uses position measurement only can be optimally used to eliminate the rate bias error. On the other hand, for 3D moving aircraft we present a new algorithm which incorporate FIR-type filter, which uses position and rate measurement at the same time, and the fixed-lag smoother using position measurement only, and show that it has the optimal performance in terms of both estimation accuracy and response time.

• Journal of Sensor Science and Technology
• /
• v.32 no.3
• /
• pp.180-186
• /
• 2023

Test devices can perform various functions, such as research on detection targets, sensors that detect detection targets, combined products containing sensors, and certification for the launch of combined products. However, the scope of use of test devices is limited because they perform only a single role or could only serve a particular purpose in the past. Therefore, studies on test devices that can perform various functions, such as research on detection targets, sensors that detect detection targets, combined products containing sensors, and certification for the release of combined products are necessary. Accordingly, this study proposes a test device that can increase the scope of use in the technical field of electric fires. In addition, we examine various outcomes of the proposed test device.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2011.11a
• /
• pp.187-190
• /
• 2011

본 논문은 초기화재 및 훈소화재에 적응성이 있는 CO센서의 응답특성을 분석하고자 접촉식 CO센서를 실험대상으로 하여 한국소방산업기술원의 실화재시험장에서 모형화재실험을 실시하였다. 화원의 종류로는 UL 268 시험화원인 종이, 목재, 인화성액체를 화원으로하여 각 화원에 따른 CO센서의 응답특성을 비교 분석하였다.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.77-80
• /
• 2023

Since fires in uncontrolled environments pose serious risks to society and individuals, many researchers have been investigating technologies for early detection of fires that occur in everyday life. Recently, with the development of deep learning vision technology, research on fire detection models using neural network backbones such as Transformer and Convolution Natural Network has been actively conducted. Vision-based fire detection systems can solve many problems with physical sensor-based fire detection systems. This paper proposes a fire detection method using the latest YOLOv8, which improves the existing fire detection method. The proposed method develops a system that detects sparks and smoke from input images by training the Yolov8 model using a universal fire detection dataset. We also demonstrate the superiority of the proposed method through experiments by comparing it with existing methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.9
• /
• pp.1649-1656
• /
• 2016

Performance of the existing sensor-based fire detection system is limited according to factors in the environment surrounding the sensor. A number of image-based fire detection systems were introduced in order to solve these problem. But such a system can generate a false alarm for objects similar in appearance to fire due to algorithm that directly defines the characteristics of a flame. Also fir detection systems using movement between video flames cannot operate correctly as intended in an environment in which the network is unstable. In this paper, we propose an image-based fire detection method using CNN (Convolutional Neural Network). In this method, firstly we extract fire candidate region using color information from video frame input and then detect fire using trained CNN. Also, we show that the performance is significantly improved compared to the detection rate and missing rate found in previous studies.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.275-276
• /
• 2021

In the event of a fire in a complex, the identification of isolated people's location information is delayed, resulting in many casualties. In order to prevent such an accident, research on estimating the location of the requesters by detecting the wireless signal of the mobile phone at fire sites is in progress. The main concept is to use a wireless signal scanner to detect the wireless signal of a mobile phones at fire sites, and then position the mobile phone based on this. However, it is difficult to secure visibility at the fire site due to the smoke, and there is a difficulty in rescuing requesters in need compared with general disaster sites. Therefore, it will be one of the important issues to be solved to determine the minimum number of rescuers to be deployed according to the number and condition of the requesters. In this study, we propose a method to calculate the number of rescuers put to fire sites by using the radio signal generated from mobile phones and the information generated from the inertial sensor of the mobile phones.