• Title/Summary/Keyword: Set-net

Search Result 813, Processing Time 0.032 seconds

Automatic Volumetric Brain Tumor Segmentation using Convolutional Neural Networks

  • Yavorskyi, Vladyslav;Sull, Sanghoon
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2019.05a
    • /
    • pp.432-435
    • /
    • 2019
  • Convolutional Neural Networks (CNNs) have recently been gaining popularity in the medical image analysis field because of their image segmentation capabilities. In this paper, we present a CNN that performs automated brain tumor segmentations of sparsely annotated 3D Magnetic Resonance Imaging (MRI) scans. Our CNN is based on 3D U-net architecture, and it includes separate Dilated and Depth-wise Convolutions. It is fully-trained on the BraTS 2018 data set, and it produces more accurate results even when compared to the winners of the BraTS 2017 competition despite having a significantly smaller amount of parameters.

  • PDF

Performance measurement of safety-critical systems based on ordinary differential equations and Petri nets: A case study of nuclear power plant

  • Nand Kumar Jyotish;Lalit Kumar Singh;Chiranjeev Kumar
    • Nuclear Engineering and Technology
    • /
    • v.55 no.3
    • /
    • pp.861-869
    • /
    • 2023
  • This article proposes a novel approach to measure the performance of Safety-Critical Systems (SCS). Such systems contain multiple processing nodes that communicate with each other is modeled by a Petri nets (PN). The paper uses the PN for the performance evaluation of SCS. A set of ordinary differential equations (ODEs) is derived from the Petri net model that represent the state of the system, and the solutions can be used to measure the system's performance. The proposed method can avoid the state space explosion problem and also introduces new metrics of performance, along with their measurement: deadlock, liveness, stability, boundedness, and steady state. The proposed technique is applied to Shutdown System (SDS) of Nuclear Power Plant (NPP). We obtained 99.887% accuracy of performance measurement, which proves the effectiveness of our approach.

Analysis of the Effect of Deep-learning Super-resolution for Fragments Detection Performance Enhancement (파편 탐지 성능 향상을 위한 딥러닝 초해상도화 효과 분석)

  • Yuseok Lee
    • Journal of the Korea Institute of Military Science and Technology
    • /
    • v.26 no.3
    • /
    • pp.234-245
    • /
    • 2023
  • The Arena Fragmentation Test(AFT) is designed to analyze warhead performance by measuring fragmentation data. In order to evaluate the results of the AFT, a set of AFT images are captured by high-speed cameras. To detect objects in the AFT image set, ResNet-50 based Faster R-CNN is used as a detection model. However, because of the low resolution of the AFT image set, a detection model has shown low performance. To enhance the performance of the detection model, Super-resolution(SR) methods are used to increase the AFT image set resolution. To this end, The Bicubic method and three SR models: ZSSR, EDSR, and SwinIR are used. The use of SR images results in an increase in the performance of the detection model. While the increase in the number of pixels representing a fragment flame in the AFT images improves the Recall performance of the detection model, the number of pixels representing noise also increases, leading to a slight decreases in Precision performance. Consequently, the F1 score is increased by up to 9 %, demonstrating the effectiveness of SR in enhancing the performance of the detection model.

Assessments of Negotiation Options Regarding Post-2012 Rules for Land Use, Land-Use Change and Forestry (LULUCF) -With a Focus on the Forest Management Activities under the Kyoto Protocol - (Post-2012 LULUCF 협상 대안 평가 -산림경영 활동을 중심으로 -)

  • Bae, Jae-Soo
    • Journal of Korean Society of Forest Science
    • /
    • v.98 no.1
    • /
    • pp.55-65
    • /
    • 2009
  • Annex I parties continued its consideration of how to address, the definitions, modalities, rules and guidelines for the treatment of Land Use, Land-use Change and Forestry (LULUCF) in the second commitment period of the Kyoto Protocol by the year of 2009. In the AWG-KP conference held in Accra, Ghana in 2008, four alternatives (gross-net carbon accounting, net-net with base year or base period accounting, net-net with forward looking baseline accounting, and land-based accounting method) for negotiations were decided in order to revise gross-net accounting method applied during the first commitment period of the Kyoto Protocol. In this study, alternative scenarios are set in consideration with reporting system (voluntary or compulsory), discount factors and cap about these three alternatives except for the method of net-net with forward looking baseline accounting, and then estimates the Removal Unit (RMU) among the countries. In the case that article 3.4 activities under the Kyoto Protocol revises from voluntary reporting to mandatory reporting, it is estimated that the loss of RMU would be huge in Russia, Australia, New Zealand, as well as Canada potentially. Net-net with base year or base period carbon accounting and land-based carbon accounting method have big difference of RMU in accordance with the base year or the base period. So the more unfavorable the country with a lot of old-age forests was, the closer the base year or period comes to the commitment period in the context of RMU. If it is getting lowered for the current rate of 85% in discount factors, RMU is getting higher to the whole countries. Therefore in Korea with little potential for afforestation and reforestation, there was the most sensitive response to the change of discount factors. Post-2012 LULUCF hereafter, it is strongly expected for the succession of current carbon accounting system which is voluntary reporting of gross-net carbon accounting and the activity for article 3.4. Other carbon accounting method is hard to accept in aspect that there is big differentiated interests among the countries and it is required enormous cost and time to develop reliable method. Provide for Post-2012 mandatory greenhouse gas reduction, Korea needs to have a competitive negotiation strategies differentiated from Annex I countries. The most reliable alternative would be to lower the discounting factors about the activities for forest management.

Study on the Gathering Effects of Anchovy Scoop Net in the neighboring waters of the Cheju Island (제주도 근해 멸치 분기초망의 집어효과에 관한 연구)

  • SOHN Tae-Jun
    • Korean Journal of Fisheries and Aquatic Sciences
    • /
    • v.21 no.3
    • /
    • pp.184-192
    • /
    • 1988
  • Anchovy, Engraulis Japonica were caught by scoop net with fishing lamp in the surrounding water of Cheju and Seogwipo, and their gathering depth, gathering effects, change of catch by the age of the moon and submarine illumination were investigated from May to August 1985. Fish finder (SR-385) and fishing lamp (1 Kw incandescent) were set up at one meter of starboard of scoop net and one meter ahead of the prow together with two meters above the water surface respectively. The submarine illumunation was measured at 2m interval to both vertical direction of 0~18m and horizontal direction of 0~12m form the standard point which is to be 0.1m depth right under the fishing lamp. The catch of anchovy by scoop net was almost $90\%$ of total amount during the early period and the late period in moon age while as low as $10\%$ only was cought during the middle period. The catching depth of anchovy shoals by scoop net with fishing lamp was approximately 2~5m and submarine illuminations were 20~42 Lux, 24~48 Lux in Cheju and Seogwipo respec lively. Submarine illumination which could be cought by scoop net with fishing lamp should be 7~12 times lighter than before gathering since the shoals swiming at 10~15m depth which is 1.7~7 Lux illumination made by 1 Kw. AC 100V incandescent lamp, a surface gathering lamp of 2m high above anchovy scoop net came up to 2~5m depth which is 20~42 Lux illumination. The catching depth of anchovy by scoop net was 2~3m and this could be increased to 4m even though the AC voltage was decreased from 100V to 80V at final fishing stage.

  • PDF

Accuracy analysis of Multi-series Phenological Landcover Classification Using U-Net-based Deep Learning Model - Focusing on the Seoul, Republic of Korea - (U-Net 기반 딥러닝 모델을 이용한 다중시기 계절학적 토지피복 분류 정확도 분석 - 서울지역을 중심으로 -)

  • Kim, Joon;Song, Yongho;Lee, Woo-Kyun
    • Korean Journal of Remote Sensing
    • /
    • v.37 no.3
    • /
    • pp.409-418
    • /
    • 2021
  • The land cover map is a very important data that is used as a basis for decision-making for land policy and environmental policy. The land cover map is mapped using remote sensing data, and the classification results may vary depending on the acquisition time of the data used even for the same area. In this study, to overcome the classification accuracy limit of single-period data, multi-series satellite images were used to learn the difference in the spectral reflectance characteristics of the land surface according to seasons on a U-Net model, one of the deep learning algorithms, to improve classification accuracy. In addition, the degree of improvement in classification accuracy is compared by comparing the accuracy of single-period data. Seoul, which consists of various land covers including 30% of green space and the Han River within the area, was set as the research target and quarterly Sentinel-2 satellite images for 2020 were aquired. The U-Net model was trained using the sub-class land cover map mapped by the Korean Ministry of Environment. As a result of learning and classifying the model into single-period, double-series, triple-series, and quadruple-series through the learned U-Net model, it showed an accuracy of 81%, 82% and 79%, which exceeds the standard for securing land cover classification accuracy of 75%, except for a single-period. Through this, it was confirmed that classification accuracy can be improved through multi-series classification.

Study on the Improvement of Stow Net Fishing Technique and the Enlargement of Fishing Ground to the Distant Waters - 1 . Model Experiment of the Net - (안강망어법의 개량과 어장의 원해로의 확대를 위한 연구 - 1 . 어구의 모형실험 -)

  • Lee, Byoung-Gee;Kim, Jin-Kun;Lee, Ju-Hee
    • Journal of the Korean Society of Fisheries and Ocean Technology
    • /
    • v.24 no.2
    • /
    • pp.55-64
    • /
    • 1988
  • Stow nets have widely been used in the western sea of Korea from the olden age. The original structure of a stow net is a large square-sectional bag net made of 4 netting panels, and the front fringes of top and bottom panels are connected to the top and bottom beams respectively. Wire ropes, which is originated from the holding anchor are gradually forked and biforked, and finally 4 pieces of wire rope (biforked pendants) are jointed to each beam. Much convenience caused by long and heavy beams were problemed, then some studies have been carried out to improve the net since 1930's. The most effective improvement were achieved in 1980 by Mr. Han and his colleagues. The key point of improvement was that the beams were removed and the belt shaped shearing device made by canvas was attached to the side panels, the head rope and ground rope to the front fringe of top and bottom panel, and biforked pendants are joined to the shearing device. Even though this is the epoch-making improvement of a stow net, the further study should be required to find out more effective method. The authors carried out a model experiment on the stow net to determine the vertical and horizontal opening of a net mouth, and also examine the front, top and side-view configuration of the net. The model net was constructed depending on the Similarity Law of Fishing Gear in 1/10 and 1/20 scale and set against to the current at shallow and speedy flowing channel. The vertical and horizontal openings were determined by using scaled bamboo poles, and the configuration was observed by using specially prepared observation platform and underwater observation glass, and also photographed by using specially prepared underwater photographic equipment. The results obtained can be summarized as follows: 1. The opening height and width of the shearing device varied in accordance with the relative length of the biforked pendants. Considering the height and width of shearing device in 6 cases of the arrangement system of biforked pendants, the best result was obtained in the case that the 2nd, 3rd and 4th pendents from the bottom-most was 5%, 9% and 4% longer than that. 2. On the top-view configuration the excessive deformation of head rope and ground rope were observed. In the actual net, 54m long head rope and ground rope were attached to the front fringe of top and bottom panels so that the head rope may be lifted to make the net mouth open highly. But actually the head rope and the ground rope are streamed backward without any lift, and also the netting followed the ropes were deformed until the 2/5 in the whole length of the net. This deformation may be guessed to disturb the entrance of fish school into the net and also caused the net to get caught by obstacles in the sea bed and to be broken largely. 3. Hydrodynamic resistance R of the actual net may be deduced as R(kg)=29.2$\times$103 v1.65. It is also expressed as R(kg)=5.9$\times$d/l$\times$ab v1.65. depending on the formula deduced by Koyama to estimate the resistance of trawl nets, where d/l denote the ratio between diameter of netting twine and length of mesh leg in every part of side panel, a and b, the stretched circumference of the mouth and the stretched length of the net, respectively.

  • PDF

Dynamic Behavior of Model Set Net in the Flow (모형 정치망의 흐름에 대한 거동)

  • Jung, Gi-Cheul;Kwon, Byeong-Guk;Le, Ju-Hee
    • Journal of the Korean Society of Fisheries and Ocean Technology
    • /
    • v.33 no.4
    • /
    • pp.275-284
    • /
    • 1997
  • This experiment was carried out to measure the sinking depth of each buoy, the change in the net shape of the net, and the tension of sand bag line according to the R (from bag net to the fish court) and L (from fish court to the bag net) current directions and their velocity by the model experiment. The model net was one-fiftieth of the real net, and its size was determined after considering the Tauti’s Similarity Law and the dimension of the experimental tank. 1. The changes of the net shape were as follows : In the current R, the end net of fish court moved 20mm down the lowerward tide and 10mm upper part. So the whole model net moved up at 0.2m/sec. The shape of the net showed an almost linear state from bag net to the fish court at 0.6m/sec. In the current L, the door net moved 242mm down the lowerward tide and 18mm upper part. So the whole model net moved up at 0.2m/sec. The net shape showed an almost linear state from the fish court to the bag net at 0.5m/sec. 2. The sinking depths of each buoy were as follows: In the current R, the head buoy started sinking at 0.2m/sec and sank 20mm, 99mm at 0.3m/sec and 0.6m/sec, respectively. The end buoy didn't sink from 0m/sec to 0.6m/sec but showed a slight quake. In the current L, the end buoy started sinking at 0.1m/sec, and sank 5mm and 108mm at 0.2m/sec and 0.6m/sec, respectively. The whole model net sank at 0.5m/sec except the head buoy. 3. The changes of the sand bag line tension were as follows: In the current R, the tension affected by the sand bag line of the head buoy showed 273.51g at 0.1m/sec increased to 1298.40g at 0.6m/sec. In the current L, the tension affected by the sand bag line of the end buoy on one side showed 137.08g at 0.1m/sec increased to 646.00g at 0.6m/sec. The changes in the sand bag line tension were concentrated on the sand bag line of the upperward tide with increasing velocity at the R and L current directions. However, no significant increase in tension was observed in the other sand bag lines.

  • PDF

Species Composition and Assemblage Structure of Fish Collected by Set Net at the Coastal Waters of Goseong in Gangwon-do, Korea (강원도 고성연안에서 정치망으로 채집된 어류 종조성과 군집구조)

  • Lee, Soo Jeong;Yang, Jae-Hyeong;Seo, Young Il;Kim, Jin-Koo
    • Korean Journal of Ichthyology
    • /
    • v.33 no.2
    • /
    • pp.95-106
    • /
    • 2021
  • In order to understand the seasonal variations of species composition of fish in the Goseong, middle East Sea of Korea, we surveyed fish fauna using set net during 2 years. In this study, a total of 77 taxa belonging to 40 families were collected and 75 species were identified. The dominant family were Tetraodontidae and Pleuronectidae, and the dominant species were Arctoscopus japonicus, Konosirus punctatus, Stephanolepis cirrhifer, Thamnaconus modestus, and Trachurus japonicus. The results of the hierarchical clustering using the number of individuals of collected species showed that they are divided into three seasonal groups: Group A (Jan.~Apr.), Group B (May~Jun., Nov.~Dec.), Group C (Jul.~Oct.). The sea surface temperature (SST) was higher than the results of previous studies in winter and spring, and species composition in spring have changed from cold-water species to the warm-water species, recently. The species composition has become similar to the that of southern Gangwon-do regions (Samcheok and Gangneung) of the previous studies. The species diversity of family Tetraodontidae has increased, which is estimated to have an effect on increase in SST and the quantity of entering the East Sea. Therefore, we assumed that the change of species composition is related to the extension of northern distribution limits and survival temperature, and abundant preys. Therefore, it is necessary that an efficient resource management policy as well as the ways of commercially use of migratory warm-water fish, rapidly.

Study on the Improvement of Stow Net Fishing Technique and the Enlargement of Fishing Ground to the Distant Waters - 3 . Field Experiment on the Efficiency of Newly Designed Net and the Stern Operation System (안강망어법의 개량과 어장의 원해로의 확대를 위한 연구 - 3 . 시험어구의 전개성능과 선미식 어업방법에 관한 해상시험 -)

  • 이병기
    • Journal of the Korean Society of Fisheries and Ocean Technology
    • /
    • v.25 no.2
    • /
    • pp.75-81
    • /
    • 1989
  • In this paper, the authors describe on the field experiment of the newly designed actual stow net, standing on the result of the model experiment to examine the performance of the conventional net and the newly designed net, presented in two previous reports of this series. Concurrently the additional experiment to find out the possibility of changing of operating system from the side to the stern was carried out. 1. Fundamental shape of the experimented net was 20 times aslarge asthe newly designed model net. Performance of the net was detected by using two ultrasonic echo sounders: one was set downward at the top-most spreader of the shearing device to detect the opening height of the device from the sea bed, and the other sidewise at the starboard top-most spreader to detect the top-most opening width of the devices. Opening height of the newly designed net showed about 3m smaller than the conventional net at slow current of 0.6m/sec and less but it overcome 1m at speedy current of 0.8m/sec and more. Opening width of the newly designed net was 1.4 times as large as that of the conventional net, ant the front projection area of the newly designed net mouth was estimated as 1.3~1.6 times as large as that of the conventional net. 2. The experiment on the stern operating system was tightly limited by the structure of the ship employed in the experiment, which was a stern trawler of 2275 GT. The ship confronted by the wind with main anchor, while the net was put over the stern slipway and the hauling line of shearing device was operated through the top rollers of gallows. The experiment was very suggestive in the view point to mechanize the operating system, and so to decrease the man power except the following question. The of bow-stern line of ship, and that of net is much different.

  • PDF