• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.979-995
• /
• 2023

As wildfires are difficult to predict, real-time monitoring is crucial for a timely response. Geostationary satellite images are very useful for active fire detection because they can monitor a vast area with high temporal resolution (e.g., 2 min). Existing satellite-based active fire detection algorithms detect thermal outliers using threshold values based on the statistical analysis of brightness temperature. However, the difficulty in establishing suitable thresholds for such threshold-based methods hinders their ability to detect fires with low intensity and achieve generalized performance. In light of these challenges, machine learning has emerged as a potential-solution. Until now, relatively simple techniques such as random forest, Vanilla convolutional neural network (CNN), and U-net have been applied for active fire detection. Therefore, this study proposed an active fire detection algorithm using state-of-the-art (SOTA) deep learning techniques using data from the Advanced Himawari Imager and evaluated it over East Asia and Australia. The SOTA model was developed by applying EfficientNet and lion optimizer, and the results were compared with the model using the Vanilla CNN structure. EfficientNet outperformed CNN with F1-scores of 0.88 and 0.83 in East Asia and Australia, respectively. The performance was better after using weighted loss, equal sampling, and image augmentation techniques to fix data imbalance issues compared to before the techniques were used, resulting in F1-scores of 0.92 in East Asia and 0.84 in Australia. It is anticipated that timely responses facilitated by the SOTA deep learning-based approach for active fire detection will effectively mitigate the damage caused by wildfires.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2009.11a
• /
• pp.219-219
• /
• 2009

ceramic metal halide lamps are a subset of high intensity discharge lamps so named because of their high radiance These lamps weak ionized plasma in a fire-resisting but light transmissive wrapping by the corridor of current through atomic and molecular vapors. for commercial applications, For commercial applications, the conversion of electric power to light must occur with good efficiency and with sufficient spectral content throughout the visible (380-800 nm) to permit the light so generated to render colors comparable to natural sunlight. the purpose of this paper is to carry out a study on the variation of ageing time(2000 On/Off[hr]) on the performance of 150W CMH lamps. Experimental results show that the blackening by reacting W(tungsten)with I atomic has been created in the arc tube of an ageing lamp(2000 On/Off[hr]), the arc was unstable, and increased a lamp resistance made lamp voltage increases significantly. Also, Color temperature of the ageing lamp was moved by the losses of Ho with Dy atomics and by recombination of Na with I.

• Journal of Korea Multimedia Society
• /
• v.18 no.10
• /
• pp.1197-1204
• /
• 2015

Smoke detection plays an important role for the early detection of fire. In this paper, we suggest a newly developed method that generated LBPV(Local Binary Pattern Variance)s as special feature vectors from RGB contrast images can be applied to detect smoke using SVM(Support Vector Machine). The proposed method rearranges mean value of the block from each R, G, B channel and its intensity of the mean value. Additionally, it generates RGB contrast image which indicates each RGB channel’s contrast via smoke’s achromatic color. Uniform LBPV, Rotation-Invariance LBPV, Rotation-Invariance Uniform LBPV are applied to RGB Contrast images so that it could generate feature vector from the form of LBP. It helps to distinguish between smoke and non smoke area through SVM. Experimental results show that true positive detection rate is similar but false positive detection rate has been improved, although the proposed method reduced numbers of feature vector in half comparing with the existing method with LBP and LBPV.

• Journal of the Korean Institute of Oriental Medical Informatics
• /
• v.15 no.2
• /
• pp.93-99
• /
• 2009

Objective: The aim of this study is to show one case of cerebral infarction patient with chest discomfort, insomnia and constipation improved by Daehwanghwangryeonsasim-tang. Methods: The patient was treated with herbal medicine (Daehwanghwangryeonsasim-tang) and acupuncture. Changes in symptoms for treatment period were observed. Result: Intensity and frequency of chest discomfort was decreased. Sleep time was increased and constipation was improved. Conclusion: Daehwanghwangryeonsasim-tang is effective on symptoms of the pattern of heart heat and fire-heat.

• Journal of The Korean Digital Architecture Interior Association
• /
• v.12 no.3
• /
• pp.59-66
• /
• 2012

Autoclaved Lightweight Concrete(ALC) features such as a high performance insulation, the fire resistance, the advantage of easy handing construction, and lightweight panels applied the curtain wall system. ALC materials are certified as non-toxic environmental and eco-friendly productions. But ALC external panels mixed with blast furnace slag pounder and silica fume have to be coated with a stucco compound or plaster because of resisting the ambient environment. This study is that mixing tests to evaluate a performance analysis of exterior paints to be make-up pigments(organic or inorganic) coated with panel surface. Testing compared by KS F 2476; flow test, KS F 2426; compression strength test, KS F 2762; bond strength test. In results, the case of the inorganic binder, ratio of alumina cement : anhydrite is 90:10 to 80:20 at the highest level of intensity. In the case of the organic binder, adhesive strength rating at surface of ALC, the pullout strength is below 0.5 $N/mm^2$ but the normal concrete is over 2.0$N/mm^2$. A contents ratio of EVA resin is more than 3% and then bond strength is effectively.

• Journal of Satellite, Information and Communications
• /
• v.9 no.4
• /
• pp.91-96
• /
• 2014

This paper proposed an adaptive threshold method for detecting flame candidate regions in a infrared image and it adapts according to the contrast and intensity changes in the image. Conventional flame detection systems uses fixed threshold method since surveillance environment does not change, once the system installed. But it needs a adaptive threshold method as requirements of surveillance system has changed. The proposed adaptive threshold algorithm uses the dynamic behavior of flame as featured parameter. The test result is analysed by comparing test result of proposed adaptive threshold algorithm and conventional fixed threshold method. The analysed data shows, the proposed method has 91.42% of correct detection rate and false detection is reduced by 20% comparing to the conventional method.

• Atmosphere
• /
• v.31 no.4
• /
• pp.405-420
• /
• 2021

Forest fire happens every year at Yeongdong, Gangwon-do, due to the strong local wind during the spring time and it causes a huge damage. This wind is named "Yangganjipung" or "Yanggangjipung" that blows along Yeongdong. However, the occurrence conditions of the wind have been still unclear. To identify the occurrence mechanism of local strong wind through three-dimensional observation data, Gangwon Regional Meteorological Administration performed Joint Gangwon-Yeongdong 3D Observation Project in 2020. The special observation was carried out for 6 times from March to April. The observation data was analyzed by focusing on the structure of synoptic pressure distribution and inversion layer. The result showed that the strength of wind is different depending on the latitude of low pressure, intensity of inversion layer, and changes on height in the south-high and north-low pressure distribution. As the interval of the upper and lower parts of the inversion layer was narrow, the strength of the wind became stronger, which is one of the observational characteristics of the springtime wind pattern at Yeongdong, Gangwon-do. In future, the clear mechanism of the local wind in the Yeongdong during the spring time is expected to be verified based on the accumulative observation data and close analysis.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.23 no.2
• /
• pp.141-147
• /
• 2019

This research focuses on developing the Smart material with Grease adopted as a base oil to overcome a particle deposition caused by the MR fluid consisting of a silicon, which maximizing the characteristics and advantage of the MR fluid. By adopting the SMG fluid to a shear damper, this paper aimed to evaluate the control performance of it according to the variation of intensity of electric current(0 A, 0.5 A, 1.0 A, 1.5 A, 2.0 A, 2.5 A) and frequency(0.5 Hz, 1 Hz, 2 Hz). Subsequently, the usability of the SMG damper was analyzed by comparing the dynamic model of it to that of the other types of dampers(Power(Involution) Model, Bingham Model). As a result, DR, the performance indicator of semi-active damper, shows approximately 5 in a condition of 2 Hz. Also while confirming the excellent performance like the Power and the Bingham model, it raises the possibility to exploit it as the semi-active damper.

• The Korean Journal of Legal Medicine
• /
• v.42 no.4
• /
• pp.126-140
• /
• 2018

The diagnosis of cause of death (COD) or estimation of postmortem interval (PMI) is hard to perform using postmortem blood or other bodily fluids due to various biochemical changes that occur during the agonal phase or after death. To solve these problems, new paradigms and new analytical methods are needed. In this study, postmortem blood was fractionated with specific gravity 1.021, 1.029, 1.038, and 1.045, and the absorbance patterns of each sample of the 131 total cases (12 kinds of COD) were analyzed using a spectrometer. The absorbance was grouped into 9 patterns (ABS pattern 1 to 9) according to the wave length and the signal intensity. These patterns of postmortem blood were found to be distinctly different from the absorbance pattern of fresh blood. The analysis of ABS patterns is useful for the diagnosis of deaths due to acute or rapid bleeding, fire death, drowning and, in some cases, poisoning, but is not useful for the estimation of PMI.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1731-1738
• /
• 2021

The objective of this study was to extract individual trees and tree heights using UAV drone images. The study site was Gongju national university experiment forest, located in Yesan-gun, Chungcheongnam-do. The thinning intensity study sites consisted of 40% thinning, 20% thinning, 10% thinning and control. The image was filmed by using the "Mavic Pro 2" model of DJI company, and the altitude of the photo shoot was set at 80% of the overlay between 180m pictures. In order to prevent image distortion, a ground reference point was installed and the end lap and side lap were set to 80%. Tree heights were extracted using Digital Surface Model (DSM) and Digital Terrain Model (DTM), and individual trees were split and extracted using object-based analysis. As a result of individual tree extraction, thinning 40% stands showed the highest extraction rate of 109.1%, while thinning 20% showed 87.1%, thinning 10% showed 63.5%, and control sites showed 56.0% of accuracy. As a result of tree height extraction, thinning 40% showed 1.43m error compared with field survey data, while thinning 20% showed 1.73 m, thinning 10% showed 1.88 m, and control sites showed the largest error of 2.22 m.