• Proceedings of the Korean Society of Computer Information Conference
• /
• 2010.07a
• /
• pp.301-306
• /
• 2010

본 연구는 창업분야의 공공부문 정보시스템인 BI-Net의 활용성을 제고하기 위한 요인들을 살펴보고자 한다. 이를 위하여 정보시스템의 성과를 측정하기 위한 정보시스템 성공모델과 기술수용과 사용에 관한 통합이론을 기반으로 BI-Net의 사용의도에 영향을 주는 요인들과의 관계를 실증분석을 통하여 파악하였다. 실증분석 결과 정보품질 및 시스템품질과 성과기대가 사용자 만족도에 영향을 주는 것으로 나타났으며, 정보품질 및 시스템품질과 성과기대 및 노력기대가 BI-Net의 사용의도에 영향을 주는 요인인 것으로 나타났다. 또한 운영평가수준과 사용자 성별이 사용의도와 영향요인과의 관계에서 조절효과가 있는 것으로 나타났다. 이러한 결과를 바탕으로 사용자 만족을 위해서 BI-Net의 품질수준을 높이는 것이 중요하며, BI-Net의 사용의도를 높이기 위해서는 사용자 만족과 함께 시스템에 대한 기대수준을 높여야 함을 제시하였다. 또한 창업보육센터의 상황과 사용자에 적합하게 시스템을 설계하는 것도 BI-Net의 사용의도를 높이는 방법임을 제시하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.633-635
• /
• 2016

Convolutional Networks (ConvNets) are powerful models that learn hierarchies of visual features, which could also be used to obtain image representations for transfer learning. The basic pipeline for transfer learning is to first train a ConvNet on a large dataset (source task) and then use feed-forward units activation of the trained ConvNet as image representation for smaller datasets (target task). Our key contribution is to demonstrate superior performance of multiple ConvNet layer features over single ConvNet layer features. Combining multiple ConvNet layer features will result in more complex feature space with some features being repetitive. This requires some form of feature selection. We use AdaBoost with single stumps to implicitly select only distinct features that are useful towards classification from concatenated ConvNet features. Experimental results show that using multiple ConvNet layer activation features instead of single ConvNet layer features consistently will produce superior performance. Improvements becomes significant as we increase the distance between source task and the target task.

• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.5
• /
• pp.330-337
• /
• 2022

Research on object detection algorithms using 2D data has already progressed to the level of commercialization and is being applied to various manufacturing industries. Object detection technology using 2D data has an effective advantage, there are technical limitations to accurate data generation and analysis. Since 2D data is two-axis data without a sense of depth, ambiguity arises when approached from a practical point of view. Advanced countries such as the United States are leading 3D data collection and research using 3D laser scanners. Existing processing and detection algorithms such as ICP and RANSAC show high accuracy, but are used as a processing speed problem in the processing of large-scale point cloud data. In this study, PointNet a representative technique for detecting objects using widely used 3D point cloud data is analyzed and described. And RandLA-Net, which overcomes the limitations of PointNet's performance and object prediction accuracy, is described a review of detection technology using point cloud data was conducted.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.97-99
• /
• 2022

For the early identification and treatment of colorectal cancer, accurate polyp segmentation is crucial. However, polyp segmentation is a challenging task, and the majority of current approaches struggle with two issues. First, the position, size, and shape of each individual polyp varies greatly (intra-class inconsistency). Second, there is a significant degree of similarity between polyps and their surroundings under certain circumstances, such as motion blur and light reflection (inter-class indistinction). U-net, which is composed of convolutional neural networks as encoder and decoder, is considered as a standard for tackling this task. We propose an updated U-net architecture replacing the encoder part with vision transformer network for polyp segmentation. The proposed architecture performed better than the standard U-net architecture for the task of polyp segmentation.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.41 no.1
• /
• pp.17-26
• /
• 2005

There are several problems in the commercial pound net in the heavy tide ; the breaking and loss of net, steeply variation of net shape and decreasing of fishing efficiency, etc. In order to solve these problems, we introduced method of added sinker used to coastal cultivating cage of Japan and investigated the possibility of application to the Korean pound net. The results are obtained as follows; 1. In case of the upperward flow with fish court net, tension of the frame line was increased about 10${\sim}$25% than that of prototype according to the added sinker from 1.3gf to 5.2gf. The tension of A-type and B-type was similar to the case of the prototype, the tension of C-type and D-type was increased about 10${\sim}$15% than that of prototype. 2. The variation of deformed angle of fish court net was from 0$^{\circ}$ to 70$^{\circ}$ and that of the slope net was from 0$^{\circ}$ to 64$^{\circ}$ and that of the second bag net was from 0$^{\circ}$ to 46$^{\circ}$ and the depth of the second bag net was increased about 10% when the added sinker was changed from 1.3gf to 5.2gf. The depth of the first bag net and the second bag net were decreased about 50% than that of initial depth. 3. For the deformed angle of fish court net according to the attached point of the added sinker, A-type and B-type were decreased about 25% and 10% than the prototype, respectively. C-type was similar to the case of the prototype and D-type was increased about 15% than that of the prototype. The depth of slope net became deep in turn of A-type, B-type, C-type and D-type. For the depth of the second bag net, A-type, B-type, C-type and D-type were increased about 10${\sim}$15% than that of prototype. The depth of the slope net was changed from 0$^{\circ}$ to 63$^{\circ}$ and that of the second bag net was changed from 0${\sim}$44$^{\circ}$ according to the increase of velocity. 4. The optimal weight of added sinker was about 2.6${\sim}$3.6gf and the optimal attached point of added sinker was the case of C-type and D-type.

• Journal of the Korean Wood Science and Technology
• /
• v.13 no.3
• /
• pp.3-26
• /
• 1985

The object of this study was to investigate the effects on physical and mechanical properties of wood particle and sawdust board combined with wire net. Conventional forming, press-lam, and veneer comply boards combining one to four wire net sheets were made from wood particle and sawdust with different spacings (8, 10, 12, and 18 Mok) and different wire diameters (0.35, 0.50, and 0.80mm) composing wire net. They were compared and analyzed statistically with specific gravity, thickness swelling, length swelling, bending properties (modulus of rupture, modulus of elasticity, work to proportional limit, and total work), internal bonding strength, and screw holding strength between wood particle and sawdust boards. The results obtained at this study as cording to the discussions might be concluded as follows; 1. In specific gravity, both particle and sawdust boards by press-lam method were higher than by conventional forming and veneer comply method, and the boards containing more wire net sheets also showed higher value. But the wire net spacings(Mok) had no influence on specific gravity. In general, particle board showed higher specific gravity than sawdust board. Veneer comply board showed lowest specific gravity values. 2. Both particle and sawdust boards by press-lam method was slightly lower than by conventional forming and veneer comply method in thickness swelling. The sawdust board containing 8, 12. and 18 Mok wire net showed lower thickness swelling than the corresponding particle board, but both sawdust and particle boards containing the T8 and 10 Mok wire net showed higher and similar thickness swelling. 3. Both particle and sawdust boards containing wire net showed no difference in MOR and MOE of bending. Comply board was the highest and particle board showed slightly higher than sawdust board in MOR and MOE values. 4. In work to proportional limit and total work in bending, both particle and sawdust boards containing thicker wire diameter and more wire net sheets showed higher value. From these facts, it is conceivable that boards with thicker wire diameter and more wire net sheets show increasing resistance against external force. But there was no significant difference between particle and sawdust borads. 5. In resistance against delamination (internal bonding strength), both sawdust and particle boards containing wire net showed lower value than control, and also showed decreasing tendency with more number of wire net sheet composed. Particle board showed higher resistance against delamination than sawdust board. 6. In screw holding strength, sawdust board containing thicker wire diameter and more wire net sheets showed higher value, but particle board by press-lam method was higher than by conventional forming and veneer comply method. Screw holding strength of particle board was higher than that of sawdust board.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.37 no.3
• /
• pp.223-231
• /
• 2001

For the purpose of providing the basic data on the improved fishing gear and the man power saving, which contribute to enhance fishing efficiency of set net in the coast of Jeju Island, this study executed the test of fish tank by reducing these actual nets by 1/30 and using the manufactured model nets, and observed and interpreted the behaviors of entering and escaping of the schools of mackerel Scomber japonicus, horse mackerel Trachurus japonicus and rabbit fish Siganus fuscescens. Thereby the result is as follows ; 1. After the elapsed time of 60 seconds, in case of rectangular set net, the ratio for entering by a school of fish marked 50% with mackerel, 18% with horse mackerel and 28% with rabbit fish, and in case of pound net, the ratio for entering net by a school of fish marked 70% with mackerel, 60% with horse mackerel and 30% with rabbit fish. 2. After the elapsed time of 60 seconds, in case of rectangular set net, the ratio for escaping by a school of fish marked 70% with mackerel, 40% with horse mackerel and 24% with rabbit fish, and in case of pound net, the ratio for escaping from net by a school of fish marked 0% with mackerel, 0% with horse mackerel and 3% with rabbit fish. 3. After the elapsed time of 60 seconds, in case of rectangular set net, the ratio for remaining by a school of fish marked 30% with mackerel, 60% with horse mackerel and 76% with rabbit fish, and in case of pound net, the ratio for remaining by a school of fish marked 100% with mackerel, 100% with horse mackerel and 97% with rabbit fish.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.15 no.2
• /
• pp.95-100
• /
• 1979

In fishing with the anchovy boat seine, it is required to haul up the bag net without injuring anchovy body. Not to injure anchovy body, the bag net is operated with 30 to 34 crews in the traditional method. With a view point of decreasing crews, the authors tried to operate the bag net with side drum winch and derrick boom. Side drum winch was installed beside the engine casing and it was operated by the main engine through the belt, pulley and bevel gear. The derrick boom, 7 meters long, was installed above the working deck which is located in the stern of the common boat seiner. Three single blocks are attached to the boom, each 2 meters apart from the top. A hook was attached to the free end of the block line for hooking up the bolch line which attached inside the bag net especially prepared for the purpose. The hauling end of the block line was induced to the side drum winch for hauling up the bag net. By using this mechanism, the bag net was hauled up with peeling the bag net just like in the traditional method. So the following results are found. (1) No injury of anchovy body was found in the process of hauling up. (2) The bag net can be operated by mere 14 crews. (3) Duration, spent in hauling up the bag net, was almost the same when the catch are a little amount, and less duration was needed by the experimented method than the traditional one when the catch are a large amount. the bag net. By using this mechanism, the bag net was hauled up with peeling the bag net just like in the traditional method. So the following results are found. (1) No injury of anchovy body was found in the process of hauling up. (2) The bag net can be operated by mere 14 crews. (3) Duration, spent in hauling up the bag net, was almost the same when the catch are a little amount, and less duration was needed by the experimented method than the traditional one when the catch are a large amount.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.47 no.4
• /
• pp.281-289
• /
• 2011

The purpose of this study is to identify the flow resistance of the bottom trawl net. The bottom trawl net being used in the training ship of Chonnam National University was selected as a full-scale net, and model nets such as 1/10, 1/25 and 1/50 of the actual net were made. Total resistance of the net part, the height of the net mouth and the flow resistance of components of the net such as wing, bag and cod-end part was measured, converted into full-scale and compared. Additionally, the model rule of Tauti (1934), which has been most frequently used in fishing net modeling experiments, was applied to interpret flow resistance and scale effect of model experiment was investigated. Presumed that the flow resistance R is $R=kS{\upsilon}^2$ against the flow velocity of each net ${\upsilon}$, resistance coefficient k was calculated by substituting R, ${\upsilon}$ and S of the net. From the result, it was found that k decreases exponentially when u increases which makes $k=c{\upsilon}^{-m}$. Whereas m of each net is ranged between 0.13-0.16 and there was not significant difference between nets. c does not show big difference in 1/10 and 1/25 model and the value itself was relatively bigger than in 1/50 model. The height of the net mouth of 1/25 and 1/50 model net h decreases exponentially according as ${\upsilon}$ increases to make $h=d{\upsilon}^{-n}$. Whereas d and n values were almost same in two nets. Additionally, when resistance of cod-end, wing and bag part in 1/25 and 1/50 model nets, both nets showed big resistance in bag part when flow is 1m/s as more than 60%. Wing and cod-end part showed almost same value or wing part had little bit larger value. On the other hand, when reviewing the reasons why both models showed difference in 1/50 model while c value against the resistance coefficient k did not show big difference in 1/10 and 1/25 model, it is inferred that the difference occurred not from material difference but from the difference in net size according to scale. It was judged that they are the scale effects concomitant to the model experiments.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.46 no.4
• /
• pp.281-291
• /
• 2010

To estimate the mesh selectivity of monofilament and multifilament gill net for Marbled sole, Pleuronectes yokohamae, the field testes were carried out 12 times with five different mesh sizes (86.6, 101.0, 121.2, 137.7, 151.5mm) in the western sea of Korea, 2007-2009. The master curve of selectivity was estimated by the extended Kitahara's method. In the field testes, the total number of species and catch were 26 and 987, respectively. The catch number of marbled sole was 728 and occupied 73.8% in total catch. The optimum values of l/m for 1.0 of retention probability in monofilament and multifilament gill net were estimated 0.288 and 0.307, respectively and l/m was estimated to be 0.189, 0.203, 0.213, 0.222 and 0.230 in case of monofilament gill net and 0.171, 0.191, 0.205, 0.216 and 0.227 in case of multifilament gill net when the retention probability were 0.1, 0.2, 0.3, 0.4 and 0.5, respectively. The 0.5 selection range of multifilament gill net was wider about 1.5 times than that of monofilament gill net according as multifilament gill net was 0.216 and monofilament gill net was 0.148. So the multifilament gill net has a low selectivity than that of the monofilament gill net. To estimate the optimum mesh size on first maturity length 19.5cm of marbled sole, the retention probability value of 0.1 was adopted in consideration of using the gill net for marbled sole at present. The optimum mesh size were estimated to be 103.2mm and 114.0mm in monofilament gill net and multifilament gill net, respectively, on first maturity length 19.5cm of marbled sole.