• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.67-68
• /
• 2021

기존 객체탐지는 경계 상자 회귀방식을 적용하였지만, 문자는 왜곡과 변형이 심한 특성을 가진 객체로 U-net 구조의 이미지 분할 방식을 사용하는 경우가 많다. 따라서 최근 문자 탐지는 통계적 모델에 비해 높은 정확도를 보이는 심층 신경망 기반의 모델 연구가 많이 진행되고 있다. 본 연구에서는 이미지 분할을 통한 양방향 특징 결합 기법을 사용한 문자 탐지 모델을 제안한다. 이미지 분할 방식은 메모리의 효율이 떨어지기 때문에 이를 극복하고자 특징 추출 단계에서 경량화된 네트워크를 적용하였다. 또한, 객체 탐지에서 큰 성과를 보인 양방향 특징 결합 모듈을 U-net 구조에 추가하여 추출된 특징이 효과적으로 결합 되는 결과를 얻었다. 제안하는 모델의 문자 탐지 성능은 합성 문자 데이터셋을 이용한 실험을 통해 기존의 U-net 구조의 이미지 분할 방식보다 향상되었음을 확인하였다.

• Journal of Korean Society of Steel Construction
• /
• v.23 no.6
• /
• pp.679-690
• /
• 2011

Since the elastic buckling problem of the plate has been studied both experimentally and theoretically, the buckling loads with various boundary conditions and loads can be easily determined. Currently, flange and web design specifications are based on the buckling stress and the post-buckling strength and include a safety-factor. Therefore, this study extended suchresearch to the linear buckling theory with ideal conditions and to the ultimate state with post-buckling. The current specifications are based on elastic buckling stress; and therefore, further research on the ultimate behavior of the plate is required. The ultimate strength design concept, which allows finite deflection, is used in this studyto maximize the post-buckling strength in a steel box. An empirical equation, which provides the ultimate strength of the steel box due to the change in the slenderness and optimum rigidity, are suggested based on the experiment results. Moreover, the appropriateness of the current design specifications was analyzed and discussed.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.22-28
• /
• 2021

This is a basic study on the development of deep learning-based algorithms to detect smoke before the smoke detector operates in the event of a ship fire, analyze and utilize the detected data, and support fire suppression and evacuation activities by predicting the spread of smoke before it spreads to remote areas. Proposed algorithms were reviewed in accordance with the following procedures. As a first step, smoke images obtained through fire simulation were applied to the YOLO (You Only Look Once) model, which is a deep learning-based object detection algorithm. The mean average precision (mAP) of the trained YOLO model was measured to be 98.71%, and smoke was detected at a processing speed of 9 frames per second (FPS). The second step was to estimate the spread of smoke using the coordinates of the boundary box, from which was utilized to extract the smoke geometry from YOLO. This smoke geometry was then applied to the time series prediction algorithm, long short-term memory (LSTM). As a result, smoke spread data obtained from the coordinates of the boundary box between the estimated fire occurrence and 30 s were entered into the LSTM learning model to predict smoke spread data from 31 s to 90 s in the smoke image of a fast fire obtained from fire simulation. The average square root error between the estimated spread of smoke and its predicted value was 2.74.

• Nuclear Engineering and Technology
• /
• v.27 no.3
• /
• pp.301-316
• /
• 1995

experimental and computational studies ore carried out to investigate the natural convection of the single phase flow in a tank with a heated horizontal plate facing downward. This is a simplified model for investigations of the influence of a core melt at the bottom of a reactor vessel on the thermal hydraulic behavior in a oater filled cavity surrounding the vessel. In this case the vessel is simulated by a hexahedron insulated box with a heated plate Horizontally mounted at the bottom of the box. The box with the heated plate is installed in a water filled hexahedron tank. Coolers are immersed in the U-type water volume between the box and the tank. Although the multicomponent flows exist more probably below the heated plate in reality, present study concentrates on the single phase flow in a first step prior to investigating the complicated multicomponent thermal hydraulic phenomena. In the present study, in order to get a better understanding for the natural convection characteristics below the heated plate, the velocity and temperature are measured by LDA(Laser Doppler Anemometry) and thermocouples, respectively. And How fields are visualized by taking pictures of the How region with suspended particles. The results show the occurrence of a very effective circulation of the fluid in the whole How area as the heater and coolers are put into operation. In the remote region below the heated plate the new is nearly stagnant, and a remarkable temperature stratification can be observed with very thin thermal boundary. Analytical predictions using the FLUTAN code show a reasonable matching of the measured velocity fields.

• Journal of the Korean Magnetics Society
• /
• v.26 no.3
• /
• pp.71-75
• /
• 2016

Monolayer $MoS_2$ is energetically most stable when it has a 1H phase, but 1H to 1T phase transition ($1H{\rightarrow}1T$) is easily realized by various ways. Even though magnetic moment is not observed during $1H{\rightarrow}1T$, $0.049{\mu}_B/MoS_2$ is obtained in local 1T phase; 75% 2H and 25% 1T phases are mixed in ($2{\times}2$) supercell. Most magnetic moment is originated from the 1T phase Mo atom in the supercell, while the magnetic moments of other atoms are negligible. As a result, magnetic/non-magnetic boundary is created in the monolayered $MoS_2$. Our result suggests that $MoS_2$ can be applied for spintronics such as a spin transistor.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.24 no.3
• /
• pp.189-197
• /
• 2014

A simplified model in the shape of a wedge box with an opening on the roof was used to generate buffeting conditions at HMC. These measurements performed in controlled conditions are intended to validate the ability of CFD tools to predict buffeting. The results obtained by PowerFLOW are presented in this paper for buffeting and for the boundary layer development on the roof of the model when the roof opening is closed. The flow mechanisms that explain the behavior of the experimental sound pressure level(SPL) curve are described, and an improved setup is used to reproduce the flow structures that lead to the measured SPL.

• Journal of Korean Society of Steel Construction
• /
• v.11 no.1 s.38
• /
• pp.13-22
• /
• 1999

The objective of this paper is to develop a program for distortional analysis of steel box girder bridges. This program is formulated by using MSDM(modified slope deflection method). Two examples are carried out to verify the validity of the developed technique and its computation procedures. The analyzed results are compared with the previously proposed methods, BEF(beam on elastic foundation) and EBEF(equivalent beam on elastic foundation). The BEF method is limited only to prismatic straight box girders. In the EBEF method, stiffness of the intermediate diaphragms is infinitely considered. On the other hand, stiffness of the intermediate diaphragms is idealized as spring contant in this study. And then, nonprismatic straight box girders can be analyzed using the same procedure. Therefore, the comparison shows that the MSDM algorithm proposed in this paper is more efficient and reliable. Also parametric studies are perfomed using the proposed algorithm.

• Restorative Dentistry and Endodontics
• /
• v.28 no.6
• /
• pp.467-474
• /
• 2003

복합레진에 의한 구치부 2급 와동의 수복에서 치은부 변연이 법랑-백아 경계 하방에 위치하는 경우 복합레진의 중합 수축에 의한 응력은 변연부의 폐쇄능력을 저하시키고 이로인한 미세누출은 2차적인 우식이나 술후과민증을 일으켜 임상에서의 성공을 위협한다. 본 연구에서는 2급 와동에서 복합레진으로 수복하기 전에 치은 변연부를 중합수축에 의한 응력을 완화시킬 수 있는 것으로 알려진 몇가지 재료들을 중간층으로 먼저 충전한 후 충전용 복합레진으로 충전한 뒤 치은부 변연에서 이들 중간층과 치질 사이의 미세누출의 정도를 비교하였다. 20개의 발거된 구치의 근, 원심면에 각각 상자 모양의 2급 와동을 형성하고 40개의 와동을 무작위로 10개씩, 4개의군으로 나누었다. 1군은 중간층의 수복없이 Clearfil SE Bond과 Clearfil AP-X로 충전하였으며 2, 3 및 4군은 중간층으로 각각 Revolution, Dyract그리고 FujiII LG를 먼저 충전한 후 1군과 동일한 방법으로 복합레진을 충전하였다. 충전된 시편은 열순환후 2% methylene blue 용액에 12시간 침잠시킨 후 색소의 침투도를 stereomicroscope로 관찰하였으며 실험결과는 Kruskal-Wallis non-parametric independent analysis 및 Mann-Whitney U test로 통계분석하여 다음의 결론을 얻었다. 1. 레진강화형 글라스아이오노머를 중간층으로 먼저 수복하고 복합레진으로 충전한 경우에서 더 적은 미세누출을 보였다(p<0.05). 2. 유동성 레진과 콤포머를 중간층으로 수복한 경우와 복합레진만으로 수복한 경우는 미세누출에 있어서 유의한 차이를 나타내지 않았다(p>0.05).

• Journal of the Korean Magnetics Society
• /
• v.19 no.5
• /
• pp.180-185
• /
• 2009

Fe$_3$O$_4$ particles, prepared by a sol-gel method, were examined for their structural characteristic, particle shapes and sizes, and their magnetic properties. Two different chemical compositions (using a mol rate Fe$^{2+}$/Fe$^{3+}$ = 1/2 and only Fe$^{2+}$) and 2-methoxyethanol were used for making proper solutions. And the solutions were refluxed and dry in a dry oven and the samples were fired at 200$\sim$600$^{\circ}C$ in the N$_2$ atmosphere. The formation of single-phased spinel ferrite powders was identified with the X-ray diffraction measurement as they were fired at above 250$^{\circ}C$. The result of scanning electron microscopy measurement showed the increase of annealing temperature yielded the particle size increased. The magnetic transition was observed using the Mossbaur spectroscopy measurement. As the ferrite, prepared with the chemical composition (Fe$^{2+}$/Fe$^{3+}$ = 1/2), was fired at 250$^{\circ}C$, 78% of the ferrite had a ferrimagnetic property and 22% of the ferrite was non-magnetic. In case of preparing the sample with only Fe$^{2+}$ and annealed at 200$^{\circ}C$, it had a single phased spinel structure but its particle size was too small to be ferrimagnetic. The annealing temperature above 250$^{\circ}C$ made powders a spinel structure regardless of the preparation method. They had a typical soft magnetic property and their saturation magnetization and coercivity became larger as the annealing temperature increased.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.4 no.3
• /
• pp.188-197
• /
• 1999

In order to estimate the uranium flux from seawater to sediments, we took pore water samples and deployed benthic chambers on seafloor of Chonsu Bay, Korea. The uranium flux across the sediment-water interface was estimated from the pore water to be 0.112-0.566 mg/$m^2yr$, corresponding to a removal flux of $4.3-21.5{\times}10^7$ gU/yr for the entire Yellow Sea. Nutrient fluxes from sediment to bottom water were estimated to be 135.6 mmol/$m^2yr$ for ammonia, 228.2 mmol/$m^2yr$ for nitrate, 36.8 mmol/$m^2yr$ for phosphate and 23.9 mmol/$m^2yr$ for silicate. The redox boundary, based on the distribution of pore water nitrate and solid phase manganese, was located at 3-5 cm below the sediment surface. Phosphate flux obtained by benthic chambers was 28.S mmol/$m^2yr$. On the other hand, estimates of uranium and silicate fluxes were orders of magnitude greater than those based on pore water profiles. Flux estimates on the basis of pore water concentration is believed to have greater reliability than those obtained from benthic chamber data.