• 한국안전학회지
• /
• 제15권2호
• /
• pp.36-45
• /
• 2000

Automated production system is composed of many complicated techniques and it become a very difficult task to control, monitor and diagnose this compound system. Moreover, it is required to develop an effective diagnosing technique and reduce the diagnosing time while operating the system in parallel under many faults occurring concurrently. This study develops a Modular Artificial Neural Network(MANN) which can perform a diagnosing function of multiple faults with the following steps: 1) Modularizing a complicated system into subsystems. 2) Formulating a hierarchical structure by dividing the subsystem into many detailed elements. 3) Planting an artificial neural network into hierarchical module. The system developed is implemented on workstation platform with $X-Windows^{(r)}$ which provides multi-process, multi-tasking and IPC facilities for visualization of transaction, by applying the software written in $ANSI-C^{(r)}$ together with $MOTIF^{(r)}$ on the fault diagnosis of PI feedback controller reactor. It can be used as a simple stepping stone towards a perfect multiple diagnosing system covering with various industrial applications, and further provides an economical approach to prevent a disastrous failure of huge complicated systems.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2011년도 한국컴퓨터종합학술대회논문집 Vol.38 No.1(D)
• /
• pp.287-288
• /
• 2011

In this paper, we propose a hierarchical P2P architecture using clustering mobile peers. The proposed scheme utilizes the maximum connection time of connected peers to form the mobile network, which makes the network topology relatively stable. The connection time of connected peers can be determined by the location, velocity vector and communication range of each mobile peer. Therefore, the update overhead of the network is decreased and the success rate of contents search is increased. Experiments have shown that our proposed scheme outperforms the existing schemes.

• 한국산업정보학회:학술대회논문집
• /
• 한국산업정보학회 2008년도 추계 공동 국제학술대회
• /
• pp.507-511
• /
• 2008

Supporting energy efficiency and load balancing in wireless sensor network is the most important issue in devising the hierarchical routing protocols. Recently, the dual layered clustering scheme with GPS was proposed for the supporting of load balancing for cluster heads but there would be many collided messages in the overlapped area between two layers. Thereby, the purpose of this paper is to reduce the collision rate in the overlapped layer by concisely distinguish them with the same number of nodes in them. For the layer partition, this paper uses an equation $x^2+ y^2{\le}(\frac{R}{\sqrt{2\pi}})^2$ to distinguish layers. By using it, the scheme could efficiently distinguish two layers and gets the balanced number of elements in them. Therefore, the proposed routing scheme could prolong the overall network life cycle about 10% compared to the previous two layered clustering scheme.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1988년도 전기.전자공학 학술대회 논문집
• /
• pp.579-581
• /
• 1988

This paper proposes the logic simulation for hierarchical logic network with function descriptor base data structure and algorithm on which a macro cell is considered as a logic elements. Function descriptor base data structure is useful when many logic elements of which type is same exist in a network, for it lessens the computer memory size used during the simulation. And the proposed simulation algorithm may improve the simulation speed.

• 대한산업공학회지
• /
• 제22권3호
• /
• pp.427-440
• /
• 1996

Constraint networks are a major approach to knowledge representation in Concurrent Engineering (CE) systems. The networks model various factors in CE as constraints linked by shared variables. Many systems have been developed to assist constraint network processing. While these systems can be useful, their underlying assumption that a solution must simultaneously satisfy all the constraints is often unrealistic and hard to achieve. Proposed in this paper is a hierarchical representation of constraint networks using priorities, namely Prioritized Constraint Network (PCN). A mechanism to propagate priorities is developed, and a new satisfiability definition taking into account the priorities is described. Strength of constraint supporters can be derived from the propagated priorities. Several properties useful for investigating PCN's and finding effective solving strategies ore developed.

• Journal of Electrical Engineering and Technology
• /
• 제9권4호
• /
• pp.1188-1195
• /
• 2014

This paper presents an analytical technique for reliability evaluation of electrical distribution network (EDN) containing distributed generation (DG). Based on hierarchical levels of circuit breaker controlling zones and feeder sections, a directed-relation-graph (DRG) for an END is formed to describe the hierarchical structure of the EDN. The reliability indices of EDN and load points can be evaluated directly using the formed DRG, and the reliability evaluation of an EDN containing DGs can also be done without re-forming the DRG. The proposed technique incorporates multi-state models of photovoltaic and diesel generations, as well as weather factors. The IEEE-RBTS Bus 6 EDN is used to validate the proposed technique; and a practical campus EDN containing DG was also analyzed using the proposed technique.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 한국컴퓨터종합학술대회 논문집 Vol.32 No.1 (B)
• /
• pp.724-726
• /
• 2005

베이지안망(Bayesian network)은 다수의 변수들 사이의 확률적 관계(조건부독립성: conditional independence)를 그래프 구조로 표현하는 모델이다. 이러한 베이지안망은 비감독학습(unsupervised teaming)을 통한 데이터마이닝에 적합하다. 이를 위해 데이터로부터 베이지안망의 구조와 파라미터를 학습하게 된다. 주어진 데이터의 likelihood를 최대로 하는 베이지안망 구조를 찾는 문제는 NP-hard임이 알려져 있으므로, greedy search를 통한 근사해(approximate solution)를 구하는 방법이 주로 이용된다. 하지만 이러한 근사적 학습방법들도 데이터를 구성하는 변수들이 수천 - 수만에 이르는 경우, 방대한 계산량으로 인해 그 적용이 실질적으로 불가능하게 된다. 본 논문에서는 그러한 대규모 데이터에서 학습될 수 있는 계층적 베이지안망(hierarchical Bayesian network) 모델 및 그 학습방법을 제안하고, 그 가능성을 실험을 통해 보인다.

• 산업공학
• /
• 제13권2호
• /
• pp.234-245
• /
• 2000

In this paper, the conceptual framework of IBS(Intelligent Building Systems) is redefined, and we propose two ANP(Analytic Network Process) models for ranking IBS. Traditional models have ranked IBS according to technical features or the number of elements in IBS. But, we consider relative functional importance among IBS elements for efficient building operation. According to the structure of interactive-relationship among IBS elements, we present two types of model. The one is Model A that is composed of both hierarchical and network structures. It has $12{\times}12$ supermatrix consists of interdependent relationship between 6 benefit elements(Productivity, Saving, Safety, Convenience, Pleasantness, Environment Affinity) and 6 IBS elements(Building Operation, Security, Safety, Telecommunication(TC), Office Automation(OA), other elements). Each of 6 IBS elements has subelements in hierarchical structure. The other is Model B that has $25{\times}25$ supermatrix consists of interdependent relationship between 6 benefit elements and 19 IBS sub elements. Merits and demerits of each model are discussed in detail.

• ETRI Journal
• /
• 제41권5호
• /
• pp.574-584
• /
• 2019

A new Mirai variant found recently was equipped with a dynamic update ability, which increases the level of difficulty for DDoS mitigation. Continuous development of 5G technology and an increasing number of Internet of Things (IoT) devices connected to the network pose serious threats to cyber security. Therefore, researchers have tried to develop better DDoS mitigation systems. However, the majority of the existing models provide centralized solutions either by deploying the system with additional servers at the host site, on the cloud, or at third party locations, which may cause latency. Since Internet service providers (ISP) are links between the internet and users, deploying the defense system within the ISP domain is the panacea for delivering an efficient solution. To cope with the dynamic nature of the new DDoS attacks, we utilized an unsupervised artificial neural network to develop a hierarchical two-layered self-organizing map equipped with a twofold feature selection for DDoS mitigation within the ISP domain.

• 지능정보연구
• /
• 제28권3호
• /
• pp.185-207
• /
• 2022

최근 딥 러닝 기술의 발전으로 인해, 텍스트, 이미지 등 비정형 데이터 분석에 딥 러닝 알고리즘을 적용하는 연구가 활발히 수행되고 있다. 그중 텍스트 분류는 학계 및 업계에서 오랜 기간 연구되어 온 분야로, 분류의 성능을 향상시키기 위해 계층형 레이블 등 데이터 자체의 특성을 활용하기 위한 다양한 시도가 이루어지고 있다. 하지만 계층적 분류를 위해 주로 사용되는 하향식 접근법은 상위 레벨의 오분류가 하위 레벨의 정분류 기회를 차단한다는 한계가 있다. 따라서, 본 연구에서는 레이블의 계층적인 관계를 고려하면서도 상위 레벨의 분류가 하위 레벨의 분류를 차단하지 않도록 하여 분류 성능을 향상시키기 위해, 오토인코더 기반 심층 지도 네트워크를 활용한 계층형 데이터 분류 방법론을 제안한다. 제안 방법론은 오토인코더의 잠재변수에 하위 레이블을 예측하는 주 분류기를 추가하고, 인코더의 은닉층에 상위 레벨의 레이블 예측하는 보조 분류기를 추가하여 End-to-End 학습을 진행한다. 제안 방법론의 성능을 평가하기 위하여 국내 논문 데이터 총 22,512건에 대한 실험을 수행한 결과, 제안 모델이 기존의 지도 오토인코더 및 DNN 모델에 비해 분류 정확도와 F1-Score에서 우수한 성능을 나타냄을 확인하였다.