• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1091-1100
• /
• 2022

As deep learning technology advances and various high-resolution remote sensing images are available, interest in using deep learning technology and remote sensing big data to detect buildings and change in urban areas is increasing significantly. In this paper, for semantic building segmentation of high-resolution remote sensing images, we propose a new building segmentation model, Convolutional Block Attention Module (CBAM)-DRUNet that uses the DeepResUNet model, which has excellent performance in building segmentation, as the basic structure, improves the residual learning unit and combines a CBAM with the basic structure. In the performance evaluation using WHU dataset and INRIA dataset, the proposed building segmentation model showed excellent performance in terms of F1 score, accuracy and recall compared to ResUNet and DeepResUNet including UNet.

• Proceedings of the Korea Contents Association Conference
• /
• 2011.05a
• /
• pp.573-574
• /
• 2011

기존의 4-State 바코드 인식 방법은 정확한 바코드 인식을 위해 모든 윤곽선을 이용하여 외곽선을 추출하고, 학습에 따른 분석 모델을 적용하는 방식이었지만, 본 논문에서는 바코드의 최외각의 윤곽선을 이용하여 불필요한 연산 작업을 최소화하고 인식과정에서 3-line 화소 구분법으로 학습데이터의 사용의존도를 최소화하는 고속 우편물 인식 시스템 개발에 목적을 둔다.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.18 no.3
• /
• pp.724-728
• /
• 2004

Several studies have shown that a low frequency stimulation can depress blood pressure in hypertension. We had developed a new auriculoelectrostimulator as an electronic blood pressure regulator for simple and easy stimulation. The new auriculoelectrostimulator was employed in hypertensive rat model induced by immobilization stress, diabetic and essential hypertensive rat models. Rats were stimulated by auriculoelectrostimulator at ear acupoint (Ear point for hypertension) bilaterally. Ear stimulation by auriculoelectrostimulator significantly decreased blood pressure in all hypertensive rat models and inhibited the increase of heart rates in stressed and spontaneous hypertensive rats. The results showed that auriculoelectrostimulator had depressive effects on hypertension in rat hypertensive models, suggesting that it is useful in treatment of hypertension.

• Journal of the Korean Solar Energy Society
• /
• v.31 no.4
• /
• pp.1-8
• /
• 2011

In this paper, inverse building modeling was applied to building perimeter zones which have different window orientation. Two test zones of east-facing and west-facing zones in ERS(Energy Resource Station) building, which is representative of small commercial building, was used to test performance of cooling load calculation and peak cooling load reduction. The dynamic thermal load model for the east and west zone was validated using measured data for the zones and then it was used to investigate the effect of peak cooling load reduction by adjustment of indoor cooling temperature set points during on-peak time period. For the east zone, the peak load can be reduced to about 60% of the peak load for conventional control even without any precooling. For the west zone, PLR is nearly independent of the start of the on-peak period until a start time of 1pm. Furthermore, PLR has a small dependence on the precooling duration. Without any precooling, the peak cooling load can be reduced to about 35% of the peak load associated with conventional control.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.32 no.6
• /
• pp.587-601
• /
• 2020

The ocean circulation was simulated in the East Sea and Ulleungdo-Dokdo region using ROMS (Regional Ocean Modeling System) model. By adopting the East Sea 3 km model and the HYCOM 9 km data, Ulleungdo 1 km model and Ulleungdo-Dokdo 300 m model were constructed with one-way grid nesting method. During the model development, a correction method was proposed for the distortion of the open boundary data which may be caused by the bathymetry data difference between the mother and child models and the interpolation/extrapolation method. Using this model, a super-high resolution ocean circulation with a horizontal resolution of 300 m near the Ulleungdo and Dokdo region was simulated for year 2018. In spite of applying the same conditions except for the initial and boundary data, the numerical models result indicated significantly different characteristics in the study area. Therefore, these results were compared and verified by using the surface current data estimated by satellites altimeter data and temperature data from NIFS (National Institute of Fisheries Science). They suggest that in general, the improvement of the one-way grid nesting with the HYCOM data on RMSE, Mean Bias, Pattern correlation and Vector correlation is greater in 300 m model than in the 1 km model. However, the nesting results of using East Sea 3 km model showed that simulations of the 1 km model were better than 300 m model. The models better resolved distinct ridge/trough structures of isotherms in the vertical sections of water temperature when using the higher horizontal resolution. Furthermore, Karman vortex street was simulated in Ulleungdo-Dokdo 300 m model due to the terrain effect of th islands that was not shown in the Ulleungdo 1 km model.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.3 no.4
• /
• pp.83-93
• /
• 1983

A non-linear numerical tidal model of the Yellow Sea and the East China Sea is used to derive the mean and maximum bed stress the mean and maximum transport potential on the continental shelf. It has provided a preliminary assessment of relation between sediment transport paths and the mean and maximum bed stress distribution determined from the numerical model.

• 한국해양학회지
• /
• v.20 no.1
• /
• pp.56-73
• /
• 1985

The three-dimensional hydrodynamic numerical model of the Yellow Sea and the East China Sea has been further utilised to provide S$\sub$2/,K$\sub$1/,O$\sub$1/ tidal currents distribution in addition to previously provided M$\sub$2/ tidal current distribution(Choi, 1984), especially the vertical variation of horizontal current in the region. Model results have been compared with current meter data acquired from recent China-USA Marine Sedimentation Dyamics Programme (Larsen and Cannon, 1983). Results were also used to provide maps of the S$\sub$2/,K$\sub$1/,O$\sub$1/ tidal current constants and tidal ellipses at three depths to complement previous M$\sub$2/ tidal current information.

• Water for future
• /
• v.17 no.4
• /
• pp.293-302
• /
• 1984

The tidal and meteorological condition associated with wintertime surges in the Ease China Sea are described. The vertically-integrated finite difference model of the East china Sea have been used to investigate the surges generated during a period of 5 days in November, 1983 dynamically. Computed residual elevations are compared with hourly records form selected tide gauges along the west coast of Korea. Preliminary results on circulation pattern derived from the numerical model are presented and discussed. Further refinement of the model using current meter observation is presently being performed to provide more accurate information on bottom stress distribution.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.4 no.1
• /
• pp.1-12
• /
• 1986

An attempt to obtain equipotential surface over the East China Sea along the three SEASAT ground tracks are described. Total correction of sea surface heights above the reference ellipsoid provided by SEASAT GDR Altimeter data consists of ocean tides and surges, body tides, sea level pressure inverse barometer effect corrections for the present study. It was shown that three equipotential surface derived from the corrections were qualitatively in agreement with GEM l0B Model and SS3 Mean Sea Surface Model.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.27-28
• /
• 2022

최근 우리나라에서도 인공지능 모델을 이용한 수온 예측 관련 연구가 활발히 진행되고 있으나 한반도 주변 해역의 수온 예측 연구에서는 주로 해수면 온도만을 예측하는데 중점을 두고 있다. 본 논문에서는 XBT(eXpendable Bathy-Thermograph) 데이터와 LightGBM(Light Gradient Boosting Model)을 이용하여 잠수함 작전 및 대잠전(Anti Submarine Warfare)에 있어서 군사적으로 중요한 동해의 수직 수온분포를 예측하였다. 동해 특정해역의 해수면부터 수심 200m까지 측정된 XBT 데이터를 이용하여 모델을 학습시키고 성능 평가지표(MAE, MSE, RMSE)와 수직 수온분포 그래프를 통해 예측 정확도를 평가하였다.