• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1989년도 추계학술대회 논문집 학회본부
• /
• pp.224-227
• /
• 1989

In this paper, The implementation of modular neural net for fault diagnosis in power system is presented. Until now, there have been many researches on expert system for fault diagnosis. On expert system, a lot of time for searching goal is needed. But, neural net processes with high speed, as it has parallel distributed processing structure. So neural net has good performance in on-line fault diagnosis. For fault diagnosis in large power system, the constitution of modular neural net with partition of large power system is presented.

• 대한전기학회논문지
• /
• 제41권4호
• /
• pp.331-338
• /
• 1992

The application of Connectionist expert system using neural network to fault diagnosis of power system is presented and compared with rule-based expert system. Also, the merits of Connectionist model using neural network is presented. In this paper, the neural network for fault diagnosis is hierarchically composed by 3 neural network classes. The whole power system is divided into subsystems, the neural networks (Class II) which take charge of each subsystem and the neural network (Class III) which connects subsystems are composed. Every section of power system is classified into one of the typical sections which can be applied with same diagnosis rules, as line-section, bus-section, transformer-section. For each typical section, only one neural network (Class I) is composed. As the proposed model has hierarchical structure, the great reduction of learning structure is achieved. With parallel distributed processing, we show the possibility of on-line fault diagnosis.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.866-871
• /
• 1991

The multi-layer neural network possesses the desirable characteristics of parallel distributed processing and learning capacity, by which the uncertain variation of the parameters in the dynamically complex system can be handled adoptively. However the error back propagation algorithm that has been utilized popularly in the learning procedure of the mulfi-Jayer neural network has the significant limitations in the real application because of its slow convergence speed. In this paper, an approach to improve the convergence speed is proposed using the fuzzy logic that can effectively handle the uncertain and fuzzy informations by linguistic level. The effectiveness of the proposed algorithm is demonstrated by computer simulation of PUMA 560 robot manipulator.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2014년도 추계 종합학술대회 논문집
• /
• pp.37-38
• /
• 2014

최근 SNS의 발전으로 인해 데이터의 양이 급격히 증가하였으며, 이에 따라 빅데이터 처리를 위한 분산 DBMS 기반 질의 처리 연구가 활발히 진행되고 있다. 이를 위해 CUBRID는 CUBRID Shard 서비스를 통해 데이터베이스를 shard 단위로 수평 분할하여 각기 다른 물리 노드에 데이터를 분산 저장하도록 지원한다. 그러나 CUBRID Shard는 shard간 데이터가 독립적으로 관리되기 때문에 세타 조인 및 중첩 질의와 같이 다수 서버에서의 테이블 참조가 필요한 질의는 처리가 불가능하다. 따라서 본 논문에서는 분산 CUBRID 상에서 세타 조인 및 중첩 SQL를 지원하는 질의 재구성 기법을 제안한다.

• 전자공학회논문지B
• /
• 제28B권11호
• /
• pp.934-940
• /
• 1991

The multi-layer neural network that has broadly been utilized in designing the controller of robot manipulator possesses the desirable characteristics of learning capacity, by which the uncertain variation of the dynamic parameters of robot can be handled adaptively, and parallel distributed processing that makes it possible to control on real-time. However the error back propagation algorithm that has been utilized popularly in the learning of the multi-layer neural network has the problem of its slow convergencs speed. In this paper, an approach to improve the convergence speed is proposed using fuzzy logic that can effectively handle the uncertain and fuzzy informations by linguistic level. The effectiveness of the proposed algorithm is demonstrated by computer simulation of PUMA 560 robot manipulator.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2017년도 춘계학술대회
• /
• pp.103-105
• /
• 2017

하둡 맵리듀스(MapReduce)는 사용자가 요청한 잡을 하둡 클러스터에서 효과적으로 병렬 분산 처리하기 위한 프레임워크이다. 맵리듀스의 태스크 스케쥴러는 사용자의 잡 태스크들을 여러 노드에 할당하기 위한 기법이다. 하지만, 기존의 스케쥴러는 노드의 가용 상태에 따라 규모가 동적으로 변화하는 하둡 클러스터를 고려하지 않음으로써 클러스터의 자원을 충분히 활용하지 못하는 문제가 있다. 본 논문에서는 노드의 가용성을 고려하여 잡 태스크를 효과적으로 할당함으로써 하둡 클러스터의 활용성을 높이는 태스크 할당 정책을 제시한다.

• 생물정신의학
• /
• 제3권1호
• /
• pp.3-13
• /
• 1996

Many studies have been conducted to search for the anatomical abnormalities in the brain which ore etiologically related with schizophrenia. Generally schizophrenia in known to be related with decreased brain tissue, hypofrontality and abnormalities in the temporal lobe including the hippocamypus, the agmygdala and the entorhinal cortex. Other areas related with the disorder ore basal ganglia, thalamus, brain stem, pons and nucleus accumbens. Abnormality in brain asymmetry is one of the new areas of interest which needs further study. The results so for ore inconsistent and it is unlikely that the abnormality in one structure is the only cause of the disorder. Rather, schizophrenia develops from the impairment of the parallel processing of integrated and reciprocal information which is distributed to the multiple structures. Histopathologic studies in the postmortem brain suggest that schizophrenia is related with neurodevelopmental abnormality rather than neurodegenerative abnormality.

• 한국정보통신설비학회:학술대회논문집
• /
• 한국정보통신설비학회 2005년도 하계학술대회
• /
• pp.382-387
• /
• 2005

There are many studies on arbitrarily divisible load scheduling problem in a distributed computing network consisting of processors interconnected through communication links. It is not efficient to arbitrarily distribute the load that comes into the system. In this paper, how to schedule in case that arbitrarily indivisible load comes into the system is studied. Also, the cases of the divisible load mixed with the indivisible load that come into network were dealt with optimal load distribution in parallel processing system by scheduling applied to linear programming.

• 물과 미래
• /
• 제29권4호
• /
• pp.109-118
• /
• 1996

신경망이론은 분산기억성질과 병렬국소처리를 수행하는 뇌의 활동을 이론화한 수학모형이다. 이러한 신경망이론의 장점은 분류문제, 대규모로 결합된 최적화문제, 비선형 사상문제 등에서 잘 나타나므로, 이 점을 이용하여 복잡한 강우의 예측을 시도하였다. 신경망이론을 적용하기 위해서 연속적인 값으로 표시되는 입력자료와 출력자료를 학습한 후 강우예측을 시행할 수 있는 다층신경망 모형을 구성하였다. 신경망이론에 의한 강우예측은 서울지역과 소양강유역의 1 시간 대위 강우자료에 적용하였다. 그 결과는 대체로 만족할 만하였다. 따라서 신경망이론은 양질의 자료가 충분히 확보될 경우복잡한 강우현상을 잘 예측할 것으로 기대된다.

• 소성∙가공
• /
• 제28권3호
• /
• pp.154-158
• /
• 2019

The hole expansion tests using conical punch, flat punch or hemispherical punch are widely used for stretch flangeability verification of HSS. In this study, we investigate the strain distribution on the shear edges of the hole expansion test using grid marking and a projector. A small crack at the edge is distributed, resulting in a large gap between the HER and the crack strain. The strain distribution at the edges is irregular due to anisotropy of sheet metal. While an edge perpendicular to the rolling direction indicate a lower strain level compared to an edge parallel to the rolling direction, edge cracks occur at the edge perpendicular to the rolling direction. To predict the manifestation of edge cracks in FE analysis, the result of the hole expansion test with a crack strain measurement may well be a better tool than FLD. In this case, the level of strain and the direction of the edge relative to the rolling direction should be well considered.