• 수산해양기술연구
• /
• 제34권3호
• /
• pp.294-301
• /
• 1998

Towing performance of a midwater trawl system was examined aboard the training ship KAYA(2900ps) at the East Sea using the midwater trawl gear that had been designed and manufactured in accordance with the vessel. In this experiment, the trawl system data, the towing speed, the length and tension of the warp, net mouth height, and the depth of otter boards and net were measured and analyzed. The results are as follows: 1. In case of heaving in the warp with constant towing speed, the tension was suddenly increased and then again was reduced and after returned to the original steady state tension. At this time, net height was reduced a bit by ascension of ground rope, but returned to it’s original value. In the case where the warp was paid out, the tension was suddenly decreased and after increased and then returned to the tension of the original state, and the net height was greatly increased instantly by the sinking of the ground rope and then returned to the steady state 2. In the case of increased towing speed mm constant warp length, the tension was increased, and reducing the net height, the gear depth was decreased. On the other hand, in the case where towing speed was reduced, the tension was reduced and the gear depth and net height was increased. 3. Otter boards show a swing motion in the scope of 5~ 10m continuously. Otter boards responded to the state change of the trawl system at first, and then the motion of the net appeared. 4. The depth of net center was about 20m deeper than that of the otter boards, it shows about 0.4 times the warp length at the 4knots towing speed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• pp.126-146
• /
• 2024

Caladium bicolor is one of the most popular plants in Thailand. The original species of Caladium bicolor was found a hundred years ago. Until now, there are more than 500 species through multiplication. The classification of Caladium bicolor can be done by using its color and shape. This study aims to develop a model to classify Caladium bicolor using a transfer learning technique. This work also presents a proof of concept, GUI design, and web application deployment using the user-design-center method. We also evaluated the performance of the following pre-trained models in this work, and the results are as follow: 87.29% for AlexNet, 90.68% for GoogleNet, 93.59% for XceptionNet, 93.22% for MobileNetV2, 89.83% for RestNet18, 88.98% for RestNet50, 97.46% for RestNet101, and 94.92% for InceptionResNetV2. This work was implemented using MATLAB R2023a.

• ETRI Journal
• /
• 제41권6호
• /
• pp.771-781
• /
• 2019

We propose the VS³-NET model to solve the task of question answering questions with machine-reading comprehension that searches for an appropriate answer in a given context. VS³-NET is a model that trains latent variables for each question using variational inferences based on a model of a simple recurrent unit-based sentences and self-matching networks. The types of questions vary, and the answers depend on the type of question. To perform efficient inference and learning, we introduce neural question-type models to approximate the prior and posterior distributions of the latent variables, and we use these approximated distributions to optimize a reparameterized variational lower bound. The context given in machine-reading comprehension usually comprises several sentences, leading to performance degradation caused by context length. Therefore, we model a hierarchical structure using sentence encoding, in which as the context becomes longer, the performance degrades. Experimental results show that the proposed VS³-NET model has an exact-match score of 76.8% and an F1 score of 84.5% on the SQuAD test set.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1363-1369
• /
• 2018

Breast cancer is one of the most common cancers in women worldwide. In Korea, breast cancer is most common cancer in women followed by thyroid cancer. The purpose of this study is to evaluate the possibility of using deep - run model for segmentation of breast masses and to identify the best deep-run model for breast mass segmentation. In this study, data of patients with breast masses were collected at Asan Medical Center. We used 596 images of mammography and 596 images of gold standard. In the area of interest of the medical image, it was cut into a rectangular shape with a margin of about 10% up and down, and then converted into an 8-bit image by adjusting the window width and level. Also, the size of the image was resampled to $150{\times}150$. In Deconvolution net, the average accuracy is 91.78%. In U-net, the average accuracy is 90.09%. Deconvolution net showed slightly better performance than U-net in this study, so it is expected that deconvolution net will be better for breast mass segmentation. However, because of few cases, there are a few images that are not accurately segmented. Therefore, more research is needed with various training data.

• 지질공학
• /
• 제27권3호
• /
• pp.191-205
• /
• 2017

본 연구에서는 불투과형 사방댐과 링네트에 가해지는 충격하중을 평가하기 위해 토석류 모형축소실험을 수행하였다. 실험 결과, 토석류는 유체와 유사한 거동을 함에 따라 불투과형 사방댐 배면에 가해지는 토석류 충격하중은 하부구간이 4.14 kN로 가장 높게 작용하며 중간, 상부구간이 3.66 kN, 1.66 kN 가해지는 것으로 측정되었다. 링네트 실험결과 또한 불투과형 사방댐 결과와 같이 충격하중은 하부구간이 크며 상부로 갈수록 감소하는 경향을 보인다(2.28 kN, 1.95 kN, 1.49 kN). 수치해석 결과를 이용하여 토석류 흐름에 의한 토석류 방지시설 충격하중 흡수메커니즘을 분석한 결과, 불투과형 사방댐은 콘크리트 옹벽과 같이 구조물 자체의 강성을 이용하여 수평력에 저항하므로 실제 구조물에 작용한 수평력은 이론식과 유사한 결과가 제시되는 반면, 링네트는 강연선 탄성늘음과 네트 전면으로의 입자 투과를 이용하므로 충격하중은 사방댐 결과보다 최대 45% 감소하는 결과가 제시되었다.

• 한국기계가공학회지
• /
• 제16권1호
• /
• pp.118-123
• /
• 2017

It is well known that water jetting is now widely used in the advanced cutting processes of polymers, metals, glass, ceramics, and composite materials because of some advantages, such as heatless and non-contacting cutting different from the laser beam machining. In this paper, we proposed the simulation model of waterjet by lengths and the inner spiral structure of the nozzle. The simulation results show that the outlet velocity of the nozzle is faster than the inlet. Furthermore, we found rapid velocity reduction after passing through the outlet. The nozzle of diameter ${\phi}500$ and length 70mm, shows the optimal fluid width and velocity distribution. Also, the nozzle with inner spiral structure shows a Gaussian distribution of velocity and this model is almost twice as fast as the model without spiral structure, within the effective standoff distance (2.5 mm). In the future, when inserting abrasive material into the waterjet, we plan to analyze the fluid flow and the particle behavior through a simulation model.

• 수산해양교육연구
• /
• 제27권6호
• /
• pp.1812-1821
• /
• 2015

In this study, we evaluate the eco-efficiency for recycling processes of Busan Resources Recycling Center for each year from 2010-2012. It analyze the impact of global warming on the power consumption by Life Cycle Assessment. Also calculate the economic value by net profit components those are sales amount and electric charge in accordance with the process operation. On the basis of these results, each of the eco-efficiency Factor analysis and dynamics analysis of 2011 and 2012 as the base year to 2010 are performed. As a result, the impact of global warming in all the recycling processes is increased by increasing power consumption 2010-2012. But net profit is decreased. In addition, the eco-efficiency of all the recycling processes is decreased and analysis result of the eco-efficiency trends is located on the Fully non Eco-efficiency (--) level. Therefore, all the recycling processes are necessary improvement for power consumption reducing and net profit increasing to further the environmental and economically sustainable direction.

• 환경영향평가
• /
• 제21권2호
• /
• pp.239-246
• /
• 2012

Daily net radiation is essential for heat budget analysis for environmental impact assessment in the coastal zone and longwave radiation is an important element of net radiation because there is a significant exchange of radiant energy between the earth's surface and the atmosphere in the form of radiation at longer wavelengths. However, radiation data is not commonly available, and there has been no direct measurement for most areas where coastal environmental impact assessment is usually most needed. Often an empirical equation, e.g., Penman and FAO-24 formulae is used to estimate longwave radiation using temperature, humidity, and sunshine hour data but local calibration may be needed. In this study, local recalibration was performed to have best fit from a widely used longwave equation using the measured longwave radiation data in Korea Global Atmospheric Watch Center (KGAWC). The results shows recalibration can provided better performance AE=0.23($W/m^2$) and RMSE=14.73($W/m^2$). This study will contribute to improve the accuracy of the heat budget analysis in the coastal area.

• 한국어병학회지
• /
• 제22권2호
• /
• pp.163-166
• /
• 2009

The ectoparasite ciliate Trichodina has been recorded from above 100 species of freshwater and marine fishes. In April 2009, we investigated the trichodia infection in 13 species of marine fishes captured by emplacement net and gill net in order to understand trichodina infection status among the natural fish populations along the Namhae-Gun coast area, the southen coast of Korea. Trichodina infection was observed in 10 out of 10 sea basses Lateolabrax japonicus, 2 out of 5 finespotted flounder Pleuronichthys cornutus and 1 out of a stone flounder Kareius bicoloratus. The sea bass infected with the parasite showed hypertrophy and exfoliation in gill epithelium. In addition, hyperplasia and lamellar fusion of gill filament were noticed among naturally affected sea bass.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 추계학술발표대회
• /
• pp.1036-1038
• /
• 2020

This paper proposes a novel automated liver segmentation using Multi-Dilated U-Nets. The proposed multidilation segmentation model has the advantage of considering both local and global shapes of the liver image. We use the CT images subject-wise, every 2D image is concatenated to 3D to calculate the IOU score and DICE score. The experimental results on Jeonbuk National University hospital dataset achieves better performance than the conventional U-Net.