• Fire Science and Engineering
• /
• v.28 no.6
• /
• pp.58-61
• /
• 2014

Flame detectors has been used more than heat & smoke detector, because this is more effective to catch fire and ceiling height in spite of high price. For upgrade to flame detector, Compare to national or abroad standard about performance test, sensitivity test, sectioning indoor or outdoor, after service and management. As a result, Europe and America have only sensitivity test, no have not operation test and sectioning indoor & outdoor. In performance test, action is put to focus to credit and durability, Not operation test is to be able to tune the sensitivity to match the environment of the site. Also, we need code about aftercare, quality assurance responsibility and implement special detector institution by Certificate Authority implement.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.607-614
• /
• 2016

In this paper, we propose an intelligent fire learning and detection system using convolutional neural networks (CNN). Through the convolutional layer of the CNN, various features of flame and smoke images are automatically extracted, and these extracted features are learned to classify them into flame or smoke or no fire. In order to detect fire in the image, candidate fire regions are first extracted from the image and extracted candidate regions are passed through CNN. Experimental results on various image shows that our system has better performances over previous work.

• Analytical Science and Technology
• /
• v.11 no.2
• /
• pp.139-144
• /
• 1998

For the ambient monitoring of acrylamide, the adequate condition of sampling and analysis was checked. The adequate adsorbents and desorption solvents were tested. The combination of charcoal tube as a adsorbent and acetone as a desorption solvent showed 87% desorption efficiency. Flame ionization detector was used to detect acrylamide. The detection limit was 0.814 mg acrylamide in 1 L acetone. It is the equivalent concentration of 0.0203 mg acrylamide in $1m^3$ air if the volume of air collected was 40L. The permissible exposure level (PEL) of acrylamide in the workplace air recommended by Occupational Safety and Health Administration (OSHA, USA) is 0.3 mg acrylamide in $1m^3$ air. So, it is very simple and economic analytical method for acrylamide to be set in the industrial hygiene laboratories.

• Journal of KIISE:Software and Applications
• /
• v.28 no.5
• /
• pp.389-401
• /
• 2001

This paper proposes an abstraction mechanism of the low-level digital video features for the automatic retrievals of the explosion scenes from the digital video library. In the proposed abstraction mechanism, the regional dominant colors of the key frame and the motion energy of the shot are defined as the primary abstractions of the shot for the explosion scene retrievals. It is because an explosion shot usually consists of the frames with a yellow-tone pixel and the objects in the shot are moved rapidly. The regional dominant colors of shot are selected by dividing its key frame image into several regions and extracting their regional dominant colors, and the motion energy of the shot is defined as the edge image differences between key frame and its neighboring frame. The edge image of the key frame makes the retrieval of the explosion scene more precisely, because the flames usually veils all other objects in the shot so that the edge image of the key frame comes to be simple enough in the explosion shot. The proposed automatic retrieval algorithm declares an explosion scene if it has a shot with a yellow regional dominant color and its motion energy is several times higher than the average motion energy of the shots in that scene. The edge image of the key frame is also used to filter out the false detection. Upon the extensive exporimental results, we could argue that the recall and precision of the proposed abstraction and detecting algorithm are about 0.8, and also found that they are not sensitive to the thresholds. This abstraction mechanism could be used to summarize the long action videos, and extract a high level semantic information from digital video archive.

• Fire Science and Engineering
• /
• v.27 no.5
• /
• pp.15-18
• /
• 2013

This paper is concerned with the Performance and Reliability Certification for fire detection system in outdoor area such small and middle sized cultural assets, natural monument and outdoor facilities. Especially, if a fire were to occur in vulnerable area, it is difficulty to detect a fire. therefore we propose a high efficiency and low cost unmanned fire detection system in capable of an early detection regardless spontaneously fire or firebug. for Adoption of Intelligent Fire Detection System with movable and unmanned function breaking from the existing Conventional Fire Detection System, this Range of R&D includes the Performance test, Function test, Field test, Flame Detection test and EMI/EMS Compliance test. the Result data of Performance test, Function test and Field test is generally good during 3 months. also we checked that thermal variation test and EMI/EMS compliance test are good result data within allowable range. As a result of general test, we verified improvement results that the measure distance of fire detection extend 75 m, the Power of waiting time increase 4 hours, the Power of operation time increase 3 days and the context awareness with video as well as sensors.

• 한국가스학회:학술대회논문집
• /
• 2007.04a
• /
• pp.42-49
• /
• 2007

가스크로마토그래피 불꽃이온화검출기(FID)에서, 천연가스 표준물질만을 사용하여 분석할 때 발생할 수 있는 분석 불확도에 대하여 연구하였다. 일반적으로 $10^5$ 범위 농도까지 직선성이 확보된 것으로 알려진 FID 검출기에 대하여 실제 분석에서 동일한 직선성이 확보되는지를 확인하였다. 본 연구에서 7성분으로 조성된 천연가스용 표준가스를 샘프링 loop의 크기를 1.0mL, 0.50mL, 0.25mL로 변환시키면서 GC/FID를 사용하여 분석한 상대표준불확도 결과는 다음과 같다. 메탄은, 0.458 %, 에탄은 0.20247%, 프로판은 0.1497%, i-부탄은 0.1854 %, n-부탄은 0.2977%, i-펜탄은 0.263%, n-펜탄은 0.383%이었다. 각 경우에서 직선성 상대표준불확도값이 $0.15%{\sim}0.45 %$까지 이른다. 일반적으로 농도가 높은 메탄의 경우에 직선성 불확도값이 큰 값을 보여 주었고 농도범위가 1-5%인 $C2{\sim}C5$의 경우는 작은 직선성 표준불확도를 나타내었다.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1079-1087
• /
• 2018

Recently, computer vision field based deep learning artificial intelligence has become a hot topic among various image analysis boundaries. In this study, flames are detected in fire images using the Faster R-CNN algorithm, which is used to detect objects within the image, among various image recognition algorithms based on deep learning. In order to improve fire detection accuracy through a small amount of data sets in the learning process, we use image augmentation techniques, and learn image augmentation by dividing into 6 types and compare accuracy, precision and detection rate. As a result, the detection rate increases as the type of image augmentation increases. However, as with the general accuracy and detection rate of other object detection models, the false detection rate is also increased from 10% to 30%.

• The Journal of Korean Academy of Prosthodontics
• /
• v.50 no.1
• /
• pp.53-60
• /
• 2012

Purpose: The purpose of this study was to compare Ni-Cr alloy property of gas-oxygen torch soldering and infrared welding using optical microscope and Electron Probe Micro Analyzer (EPMA). Materials and methods: Ni-Cr alloys were casted for specimens. Specimens had 3.0 mm diameter, 30.0 mm length and were divided into two groups. Each group had 4 specimens. One group was for gas-oxygen torch soldering and the other was infrared welding. Specimens were cut with low-speed disc and soldered each other with gas-oxygen torch and infrared machine. After soldering and polishing, specimens were observed at 3 points (soldering point, 5 mm distance point, 10 mm distance point) with optical microscope and analyzed 3 points (soldering point, 5 mm distance point, 10 mm distance point with EPMA. Results: The results of this study were as follows: 1. The observation of gas-oxygen torch soldering at 10 mm distance point under the optical microscope was not founded any specific surface properties, but some crack lines were observed at 5 mm distance and soldering point. 2. There were no crack lines were founded at the observation of infrared welding at 10 mm distance and 5 mm distance points under the optical microscope. However, at the 5 mm distance, the surface was not smooth enough compared with at 10 mm distance point. Some crack lines were observed at the welding point as well. 3. In the EPMA analysis of the gas-oxygen torch soldering, the component of Ni was increased by 4.5%, Cr was increased by 7.5% than that of the Ni-Cr alloy at the 10.0 mm distance. At the 5 mm distance, the component of Ni was decreased by 6.1%, Mo was increased by 9.0% than that of the Ni-Cr alloy but Cr was equally shown at the 5.0 mm distance. Only Ni was shown at the soldering point. 4. In the EPMA analysis of the infrared welding, the component of Ni was increased by 9.1%, Cr was increased by 0.4% than that of the Ni-Cr alloy but Al was equal at the 10.0 mm distance. At the 5 mm distance, the component of Ni was increased by 4.7%, Cr was increased by 4.7% and Al was increased by 0.1% than that of the Ni-Cr alloy. At the welding point, the component of Ni was increased by 8.8%, Cr was increased by 8.2% than that of the Ni-Cr alloy. Conclusion: From these results, at the 5 mm distance from the soldering point, the surface of the infrared welding was more smoother than that of the gas-oxygen torch soldering. On the EPMA analysis, the component of the specimens with infrared welding was more similar than that of the gas-oxygen torch soldering compared with the component of the Ni-Cr alloy.

• Journal of the Korean Chemical Society
• /
• v.52 no.1
• /
• pp.16-22
• /
• 2008

on-line system for preconcentration and separation of lead(II) is presented. The method is based on the complex formation of Pb(II) with adsorbed Methyl thymol blue on activated carbon. The conditions of preparing the solid phase reagent and of quantitative recovery of Pb(II) from diluted solutions, such as acidity of aqueous phase, solid phase capacity, and flow variables were studied as well as effect of potential interfering ions. After preconcentration step, the metal ions are eluted automatically by 5 ml of 0.5 M HNO3 solution and the lead ions content was determined by flame atomic absorption spectrometry. Under the optimum conditions, the lead ions in aqueous samples were separated and preconcentrated about 1000-fold by the column. The detection limit was 0.001 g mL-1. Lead has been determined in river and tap water samples, with recovery of 98 to 102%.

• Analytical Science and Technology
• /
• v.14 no.2
• /
• pp.180-190
• /
• 2001

Oder-active compounds are complex in a sample. These compounds are usually analyzed by GC or GC/MSD while such analytical measurement can quantify specific volatile organic compounds, it has limitations in identifying odor-active compounds. To resolve this problem, GC-Sniffing or GC-Olfactometry method has been attempted. In this study, GC/FID/Olfactometry system was developed. This system can simultaneously sniff and detect GC effluents by traditional GC combined with human olfactory system. The time gap between FID and ODP response was dependent on the kinds and concentrations of chemicals and panels, with more volatile, stronger and shorten breath cycle panel showing narrow time gap. Thus, clear relationship between FID and ODP should be considered to identify the odor-active compounds.