• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.5 no.1
• /
• pp.11-16
• /
• 1972

During the period from 1966 to 1968, total catches of Spanish mackerel averaged 6,000 to 7,000M/T per annual in Korea, and approximately 70 per cent of this amount was captured by drift nets. In an effort to improve the efficiency of drift nets, some experiments were conducted in 1969 to investigate the selectivity of material and mesh sizes. Seven different mesh sizes (80,85,95,100,105,110 and 115 mm) of both multi- and mono-filament netting were used, and the following results were obtained : 1, The body weight of Spanish mackerel taken with the seven different mesh sizes ranges from 0.5kg to 2.9kg, and the mode of body weight consists of three groups, 1kg ($21%$), 1.3kg($15\%$) and 1.5kg($19\%$). 2. For multi-filament net, 80 to 105mm mesh sizes were suitable to catch those three groups, and a little smalter than these for mono-filament net. 3. For Spanish mackerel only, the mono-filament material proved to have 1.5 times better selectivity than multi-filament : however, the latter proved superior for miscellaneous fish species due to its different size and shape. 4. Multi-filament net showed better selectivity for smaller species than mono-filament. (and mono-filament in general indicated opposite phenomenon.)

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.508-510
• /
• 2019

본 연구에서는 딥 러닝을 이용하여 완전 자동화된 다중 클래스 전체 심장 분할 알고리즘을 제안하였다. 제안된 방법은 recurrent convolutional block과 residual multi-dilated block을 삽입하여 기존 U-Net을 개선한 인공신경망 모델을 사용하였다. 평가는 자동화 분석 결과와 수동 평가를 비교하였다. 그 결과 96.88%의 평균 DSC, 95.60%의 정확도, 97.00%의 recall을 얻었다. 이 실험 결과는 제안된 방법이 다양한 심장 구조에서 효과적으로 구분되어 수행되었음을 알 수 있다. 본 연구에서 제안된 알고리즘이 의사와 방사선 의사가 영상을 판독하거나 임상 결정을 내리는데 보조적 역할을 할 것을 기대한다.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.1
• /
• pp.142-148
• /
• 2003

Reinforcement learning is considered as an important tool for robotic learning in unknown/uncertain environments. In this paper, we propose an evaluation function expressed in a vector form to realize multi-dimensional reinforcement learning. The novel feature of the proposed method is that learning one behavior induces parallel learning of other behaviors though the objectives of each behavior are different. In brief, all behaviors watch other behaviors from a critical point of view. Therefore, in the proposed method, there is cross-criticism and parallel learning that make the multi-dimensional learning process more efficient. By ap-plying the proposed learning method, we carried out multi-dimensional evaluation (reward) and multi-dimensional learning simultaneously in one trial. A special neural network (Q-net), in which the weights and the output are represented by vectors, is proposed to realize a critic net-work for Q-learning. The proposed learning method is applied for behavior planning of mobile robots.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.551-552
• /
• 2021

In this paper, we present a multi-class image scene classification method based on transformation learning. ImageNet classifies multiple classes of natural scene images by relying on pre-trained network models on large image datasets. In the experiment, we obtained excellent results by classifying the optimized ResNet model on Kaggle's Intel Image Classification data set.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.59.5-59
• /
• 2001

Multi-agent robot system is the system which executes by cooperating with each robots and controlling several robots. Capability and function of each robot must be considered for cooperation behavior. Furthermore, it is necessary to analyze the given environment and to replace complex task with some simple tasks. Analysis of the given environment and role assignment for the given tasks are composed of discret event. In this paper, the hierarchical controller for multi-agent robot system using the petri-net state diagram is proposed. The proposed modeling method is implemented for soccer robot system. The effectiveness of proposed modeling method is shown through experiment.

• The Journal of Society for e-Business Studies
• /
• v.11 no.1
• /
• pp.113-126
• /
• 2006

The scope of e-Commerce process becomes wider as the emphasis on the enterprise collaboration grows. It has expanded from its initial settings of order management or billing processes to cover various collaborative processes in the company's value-chain. In order for those collaborative e-Commerce processes to be successful, corresponding business processes should be fully supported by standard bodies. The RosettaNet consortium, one of the most representative international B2B standard bodies, has steadily provided new PIPs to support those expansions. Since individual RosettaNet PIPs correspond to unit tasks that are executed separately in or between companies, multiple PIPs have to be integrally used to properly handle larger business cases. RosettaNet implementation, however, has suffered from the lack of standard guidelines or deliverables to refer under this multi-PIP environment. In this research, a contents-based document routing system is implemented. By applying this routing system to the RosettaNet e-Logistics program where multi-PIP environment is inevitable, we verified our contents-based document routing system is effective to support multi-PIP environment flexibly.

• Journal of the Society of Naval Architects of Korea
• /
• v.58 no.3
• /
• pp.158-166
• /
• 2021

In this paper, a numerical analysis technique using a body force model is investigated to estimate the available net thrust of multi-pod-driven ice-breaking vessels under bollard pull and overload conditions. To employ the body force model in present flow simulations, drag and thrust components acting on the pod unit are calculated by using Propeller Open Water (POW) test data. The available net thrusts according to the direction of operation are evaluated in both bollard pull and overload conditions under deep water. The simulation results are compared with the model test data. The available net thrusts, calculated by the present analysis for ahead operating modes at 3~6 knots which are typical speeds of the target vessel in arctic field, are agreed well with the model test results. It is also found that the present result for astern operating mode appears approximately 6 % larger than the model test result. In addition, the available net thrusts are calculated under the both operating conditions accompanied by shallow water effects, and the main cause of the difference is studied. Based on the result of the present study, it is confirmed that the body force model can be applied to the performance evaluation of multi-pod propulsion system and the main engine selection in early design stage of the vessel.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2008.10a
• /
• pp.401-404
• /
• 2008

In the present investigation, a high precision thermal imprint system for micro ceramic products was developed and the net-shape manufacturing of multi-layer ceramic reflector for LED (Light Emitting Diode) was conducted with a precision metal die. Workpiece used in the present investigation were the multi-layer laminated ceramic sheets with pre-punched holes. The cavity with arbitrary angle was formed on the circular and rectangular holes of the ceramic sheets. During the imprinting process, the ambient temperature of the imprint system was kept over the transition temperature of the ceramic sheet and then rapidly cooled. The results in this paper show that the present method can be successfully applied to the fabrication of very small size hole array for ceramic reflector in a one step operation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.179-182
• /
• 2008

웹의 방대한 데이터에서 사용자에게 유용한 정보를 제공하기 위하여 다양한 연구가 시도되고 있다. 웹 사용 마이닝은 웹 사용자의 로그 정보를 기반으로 웹페이지를 평가할 수 있는 유용한 방법이다. 하지만 웹 사용 마이닝을 이용한 웹 페이지 평가에는 사용자들의 다양한 성향 패턴을 무시한 일괄적인 모델을 생성하는데 주를 이루고 있다. 본 논문은 사용자 관심 키워드에 대한 웹 페이지 사용 정보를 수집하고 분석하여 멀티 컨셉 네트워크(Multi Concept Network : MC-Net)를 생성한다. MC-Net은 사용자 관심 키워드에 기반한 다양한 성향 정보에 따른 웹 페이지 연결망을 제공한다. 생성된 MC-Net은 웹 페이지 추천을 위하여 유용하게 사용할 수 있으며, 실험을 통하여 제안하는 방법의 유효함을 확인하였다.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.101-110
• /
• 2022

Histopathological analysis of biopsy specimens is still used for diagnosis and classifying the brain tumors today. The available procedures are intrusive, time consuming, and inclined to human error. To overcome these disadvantages, need of implementing a fully automated deep learning-based model to classify brain tumor into multiple classes. The proposed CNN model with an accuracy of 92.98 % for categorizing tumors into five classes such as normal tumor, glioma tumor, meningioma tumor, pituitary tumor, and metastatic tumor. Using the grid search optimization approach, all of the critical hyper parameters of suggested CNN framework were instantly assigned. Alex Net, Inception v3, Res Net -50, VGG -16, and Google - Net are all examples of cutting-edge CNN models that are compared to the suggested CNN model. Using huge, publicly available clinical datasets, satisfactory classification results were produced. Physicians and radiologists can use the suggested CNN model to confirm their first screening for brain tumor Multi-classification.