• Journal of information and communication convergence engineering
• /
• v.1 no.3
• /
• pp.104-108
• /
• 2003

A biologically inspired fuzzy multilayer perceptron is proposed in this paper. The proposed algorithm is established under consideration of biological neuronal structure as well as fuzzy logic operation. We applied this suggested learning algorithm to benchmark problem in neural network such as exclusive OR and 3-bit parity, and to digit image recognition problems. For the comparison between the existing and proposed neural networks, the convergence speed is measured. The result of our simulation indicates that the convergence speed of the proposed learning algorithm is much faster than that of conventional backpropagation algorithm. Furthermore, in the image recognition task, the recognition rate of our learning algorithm is higher than of conventional backpropagation algorithm.

• IE interfaces
• /
• v.21 no.1
• /
• pp.75-84
• /
• 2008

It is a difficult task for decision makers(DMs) to choose an appropriate release plan which balances the conflicts between water storage and hydro-electric energy generation in a multi-reservoir operation problem. In this study, we proposed a DEA-based ranking procedure by which the DM can rank the potential alternatives and select the best solution among the Pareto-optimal solutions. The proposed procedure can resolve the problem of mix inefficiency that may cause errors in measuring the efficiency of alternatives. We applied the proposed procedure to the multi-reservoir operation problem for the Geum-River basin and could choose the best efficient solution from the Pareto-set which were generated by the Coordinated Multi-Reservoir Operating Model.

• International Journal of Fluid Machinery and Systems
• /
• v.8 no.3
• /
• pp.209-219
• /
• 2015

A robust multi-fidelity optimization methodology has been developed, focusing on efficiently handling industrial runner design of hydraulic Francis turbines. The computational task is split between low- and high-fidelity phases in order to properly balance the CFD cost and required accuracy in different design stages. In the low-fidelity phase, a physics-based surrogate optimization loop manages a large number of iterative optimization evaluations. Two derivative-free optimization methods use an inviscid flow solver as a physics-based surrogate to obtain the main characteristics of a good design in a relatively fast iterative process. The case study of a runner design for a low-head Francis turbine indicates advantages of integrating two derivative-free optimization algorithms with different local- and global search capabilities.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.52-54
• /
• 2011

In this paper, efficient framework design to construct electromagnetic simulator is proposed and examined. Especially computing time for example problem is enhanced to be shorted than computed time for single task corresponding to increasing the number of network PCs. As a result, design and analysis for antenna, cavity, and waveguide problems with large scale complex structure can be applied.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.135-139
• /
• 1992

Control of tool-environment interaction force to comply the robot system to an environment is of vital in many automated process. This paper presents the implementation of an adaptive force control with commercial robot system in two dimensional contour following task. A model reference adaptive control system, combined with the linear compensators, is implemented. That is, a use of adaptive control is to provide an auxiliary control system so that the contour following performance can be improved from that of using linear control system only. Hyperstability is used to derive the adaptive control law. Experimental verification of the proposed control system is obtained using PUMA 560 robot system. Data obtained experimentally shows that the use of additional adaptive control system improves the contour following performance about 30% in RMS contact force errors upon that of the system controlled by the linear compensators only.

• Journal of Korea Society of Industrial Information Systems
• /
• v.18 no.6
• /
• pp.39-49
• /
• 2013

In recent, many countries and research institutes have been studying how to construct the high-speed subscriber access network. Task Force team of IEEE 802.3ah has accomplished the standardization of EPON which is the next generation subscriber access network. EPON doesn't still have the bandwidth enough to support the new service(e.g various multimedia service) which demands the high bandwidth. For these new multimedia services,10G EPON is the next generation subscriber access network which expanded the up-down bandwidth range of 1G EPON 10 times in order to support demanding high bandwidth. We have proposed the model which can accommodate IEEE 802.1 AVB traffics smoothly in 10G EPON and suggesting the Intra-ONU scheduling model which makes this model operate effectively.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.166-168
• /
• 2002

본 논문은 의료 분야에서 디지털 정보를 전송하기 위하여 사용되고 있는 다이콤의 기본적인 구조에 진단에 도움을 줄 수 있는 새로운 주석 기능을 삽입할 수 있는 방법을 제안한다. 본 논문에서 제안한 주석 처리 방법은 다양하고 편리한 기능을 제공하기 위해서 객체 기반 주석 처리 방법과 이미지 기반 주석 처리 방법으로 나누어진다. 객체기반 주석 처리 방법은 상대적으로 많은 주석을 작은 크기로 저장 할 수 있으며 수정 및 삭제가 가능하다. 이미지 기반 주석 처리 방법은 이미지 자체를 주석 정보로 사용하기 때문에 변경이 불가능하며 보안이 필요한 분야에 활용될 수 있다. 본 논문에서 제안한 데이터 구조는 서울 중앙 병원의 진단 방사선과와 PACS 개발팀에 의뢰하여 그 효율성을 검증 받았다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.209-212
• /
• 2002

최근 인터넷이 발달하면서 TCP/IP 프로토콜 기반의 분산 클러스터환경의 구축이 가능해졌다. 이렇게 서로 다른 네트워크를 통해 연결된 분산 클러스터 시스템에서는 기존의 클러스터 시스템과는 다르게 네트워크의 지연이나 노드의 결함 등에 유연히 대처해야 한다. 따라서 본 논문에서는 이러한 인터넷 기반의 분산 클러스터 환경에서 메시지 전달방식을 이용한 고성능 클러스터 컴퓨팅 작업 시 네트워크나 노드의 결함에 효과적으로 대처할 수 있도록 중복된 작업할당 기법을 통한 결함 허용 기법을 제시한다. 중복된 작업할당 기법을 적용하기 위해 Send, GSS, WF 와 같은 기존의 부하 공유 알고리즘에 대한 공통적인 스케줄러를 설계하였으며, 이 스케줄러를 이용한 TDS_for_FT 알고리즘을 작성하였다. 본 논문에서 제시한 중복된 작업할당 기법이 효과적임을 보이기 위하여 게이트웨이를 통해 연결된 두 개의 네트워크를 구성하여 분산 PC클러스터 환경을 구축하고, PVM을 이용한 행렬의 곱셈 프로그램을 통하여 실험하였다. 클러스터를 구성하는 임의의 한 노드에 일정시간의 delay 를 적용한 결과, 중복된 작업할당 기법을 통하여 결함허용성 보장이 가능함을 보였다.

• Journal of Chest Surgery
• /
• v.45 no.5
• /
• pp.275-286
• /
• 2012

The saphenous vein has been the principal conduit for coronary bypass grafting from the beginning, circa 1970. This report briefly traces this history and concomitantly presents one surgeons experience and personal views on use of the vein graft. As such it is not exhaustive but meant to be practical with a modest number of references. The focus is that of providing guidance and perspective which may be at variance with that of others and recognizing that there may be many ways to accomplish the task at hand. Hopefully the surgeon in training/early career may find this instructive on the journey to surgical maturity.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.525-528
• /
• 2019

Atmospheric particle removal is a challenging task and attacks wide interests in computer vision filed. In this paper, we proposed a single image snow removal framework based on deep residual networks. According to the fact that there are various snow sizes in a snow image, the inception module which consists of different filter kernels was adopted to extract multiple resolution features of the input snow image. Except the traditional mean square error loss, the perceptual loss and total variation loss were employed to generate more clean images. Experimental results on synthetic and realistic snow images indicated that the proposed method achieves superior performance in respect of visual perception and objective evaluation.