• International Journal of Control, Automation, and Systems
• /
• 제1권3호
• /
• pp.358-367
• /
• 2003

We consider discrete-time factorial Markov Decision Processes (MDPs) in multiple decision-makers environment for infinite horizon average reward criterion with a general joint reward structure but a factorial joint state transition structure. We introduce the "localization" concept that a global MDP is localized for each agent such that each agent needs to consider a local MDP defined only with its own state and action spaces. Based on that, we present a gradient-ascent like iterative distributed algorithm that converges to a local optimal solution of the global MDP. The solution is an autonomous joint policy in that each agent's decision is based on only its local state.cal state.

• Journal of Photoscience
• /
• 제9권2호
• /
• pp.47-50
• /
• 2002

Raft is a distinctive membrane domain enriched in a certain class of lipids, cholesterol, and proteins observed on the plasma membrane. Growing evidence has revealed that such membrane domains play key roles in signal transduction, fertilization, development, transmitter release, and so on. Recently, we have isolated raft-like detergent-resistant membrane (DRM) fraction from bovine photoreceptor rod outer segments. Transducin and its effecter, cGMP-phosphodiesterase, elicited stimulus-dependent translocation between detergent-soluble membrane and DRM. This suggested potential importance of such distinct membrane domains in vertebrate phototransduction. Here, we will discuss physiological meaning of the translocation of major components of cGMP cascade to raft-like membrane in phototransduction. We would like to propose a hypothesis that raft-like membrane domains on the disk membrane are the place where cGMP cascade system could be quenched.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.389-391
• /
• 2007

This paper describes about the printed character segmentation and recognition system for slabs in steel manufacturing process. To increase the recognition rate, it is important to improve success rate of character segmentation. Since Slabs front area surface are not uniform and surface temperature is very high, marked characters not only undergo damages but also have much noise. On the other hand, since almost marked characters are very thick and the space between characters is only about 10 $^{\sim}$ 15 mm, there are many touching characters. Therefore appropriate character image preprocessing and segmentation algorithm is needed. In this paper we propose a multi-local thresholding method for damaged character restoration, a modified touching character segmentation, algorithm for marked characters. Finally a effective Multi-Class SVM is used to recognize segmented characters.

• 대한전기학회논문지
• /
• 제34권10호
• /
• pp.407-417
• /
• 1985

This paper describes a new method for the design of adaptive model-following control systems. This design concept is developed using the theory of slide mode. Authors present new results on the sliding control methodology to achieve accurate tracking for a class of multi-input multi-output, time-varying systems in the presence of parameter variations and disturbances. This algorithm can be easily applied to the multivariable control systems and obtained a smoother control signal in comparison to variable structure model following control systems. The design technique is easy and the control structure is simple. The design requires little computational effort. The control system is less sensitive to plant parameter variations and noise disturbances.

• 지능정보연구
• /
• 제19권1호
• /
• pp.19-33
• /
• 2013

본 논문에서는 네트워크 기반 대용량의 자원들을 효율적으로 검색하기 위해 사용자의 요구사항에 기반해 검색에 요구되는 태그들 간의 의미론에 기반한 동적 가상 온톨로지(Dynamic Virtual Ontology using Tags: DyVOT)를 추출하고 이를 이용한 동적 검색 방법론을 제안한다. 태그는 소셜 네트워크 서비스를 지원하거나 이로부터 생성되는 정형 및 비정형의 다양한 자원들에 대한 자원을 대표하는 특성을 포함하는 메타적 정보들로 구성된다. 따라서 본 연구에서는 이러한 태그들을 이용해 자원의 관계를 정의하고 이를 검색 등에 활용하고자 한다. 관계 등의 정의를 위해 태그들의 속성을 정의하는 것이 요구되며, 이를 위해 태그에 연결된 자원들을 이용하였다. 즉, 태그가 어떠한 자원들을 대표하고 있는 지를 추출하여 태그의 성격을 정의하고자 하였고, 태그를 포함하는 자원들이 무엇인지에 의해 태그간의 의미론적인 관계의 설정도 가능하다고 보았다. 즉, 본 연구에서 제안하는 검색 등의 활용을 목적으로 하는 DyVOT는 태그에 연결된 자원에 근거해 태그들 간의 의미론적 관계를 추출하고 이에 기반 하여 가상 동적 온톨로지를 추출한다. 생성된 DyVOT는 대용량의 데이터 처리를 위해 대표적인 예로 검색에 활용될 수 있으며, 태그들 간의 의미적 관계에 기반해 검색 자원의 뷰를 효과적으로 좁혀나가 효율적으로 자원을 탐색하는 것을 가능하도록 한다. 이를 위해 태그들 간의 상하 계층관계가 이미 정의된 시맨틱 태그 클라우드인 정적 온톨로지를 이용한다. 이에 더해, 태그들 간의 연관관계를 정의하고 이에 동적으로 온톨로지를 정의하여 자원 검색을 위한 동적 가상 온톨로지 DyVOT를 생성한다. DyVOT 생성은 먼저 정적온톨로지로부터 사용자 요구사항을 포함하는 태그를 포함한 부분-온톨로지들을 추출하고, 이들이 공유하는 자원의 정도에 따라 부분-온톨로지들 간의 새로운 연관관계 여부를 결정하여 검색에 요구되는 최소한의 동적 가상 온톨로지를 구축한다. 즉, 태그들이 공유하는 자원이 무엇인가에 의해 연관관계가 높은 태그들 간에는 이들의 관계를 설명하는 새로운 클래스를 가진 생성된 동적 가상 온톨로지를 이용하여 검색에 활용한다. 온톨로지의 인스턴스는 자원으로 정의되고, 즉 이는 사용자가 검색하고자 하는 해로서 정의된다. 태그들 간의 관계에 의해 생성된 DyVOT를 이용해 기존 정적 온톨로지나 키워드 기반 탐색에 비해 검색해야 할 자원의 량을 줄여 검색의 정확성과 신속성을 향상 시킨다.

• Spatial Information Research
• /
• 제10권3호
• /
• pp.421-438
• /
• 2002

GIS을 활용하는 다양한 응용분야에서 공간데이터베이스의 상세한 정도(추상화 수준)는 그 목적에 따라 달라진다. 추상화 수준이 달라지면 공간자료의 기하학적인 단순화뿐 아니라, 객체(인스턴스), 공간 및 속성 자료, 위상관계, 의미관계 등이 변화되거나 유지되어야 한다. 이와 관련하여 본 연구에서는 원시 공간데이터베이스를 추상화하여 목표데이터베이스를 생성하는 방법을 제시하였다. 공간데이터베이스를 추상화하는 연산자를 재정의하고, 어떤 객체에 어떤 연산자들을 어떤 순서로 적용하여야 하는지에 대한 기준을 제시하고, 이 기준에 따라 워크플로우를 제시하였으며, 프로토타입시스템을 개발하여 타당성을 검토했다.

• Journal of Computing Science and Engineering
• /
• 제5권4호
• /
• pp.305-313
• /
• 2011

Due to the expansion of high-speed Internet access, the need for secure and reliable networks has become more critical. The sophistication of network attacks, as well as their severity, has also increased recently. As such, more and more organizations are becoming vulnerable to attack. The aim of this research is to classify network attacks using neural networks (NN), which leads to a higher detection rate and a lower false alarm rate in a shorter time. This paper focuses on two classification types: a single class (normal, or attack), and a multi class (normal, DoS, PRB, R2L, U2R), where the category of attack is also detected by the NN. Extensive analysis is conducted in order to assess the translation of symbolic data, partitioning of the training data and the complexity of the architecture. This paper investigates two engines; the first engine is the back-propagation neural network intrusion detection system (BPNNIDS) and the second engine is the radial basis function neural network intrusion detection system (BPNNIDS). The two engines proposed in this paper are tested against traditional and other machine learning algorithms using a common dataset: the DARPA 98 KDD99 benchmark dataset from International Knowledge Discovery and Data Mining Tools. BPNNIDS shows a superior response compared to the other techniques reported in literature especially in terms of response time, detection rate and false positive rate.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회/대한산업공학회 2005년도 춘계공동학술대회 발표논문
• /
• pp.332-339
• /
• 2005

We developed a similar product recommendation system for implementing a collaborative commerce model between the cooperating companies. The system is based on a similar product finding algorithm. The main idea of the proposed algorithm is using a multi-attribute decision making(MADM) to find the utility values of products in same product class of the companies. Based on the values we determine what products are similar. The system helps the companies to recommend products in accordance with the customer's preferences regarding product specifications.

• 대한산업공학회지
• /
• 제39권5호
• /
• pp.393-402
• /
• 2013

The Mahalanobis-Taguchi System (MTS) is a diagnostic and predictive method for multivariate data. In the MTS, the Mahalanobis space (MS) of reference group is obtained using the standardized variables of normal data. The Mahalanobis space can be used for multi-class classification. Once this MS is established, the useful set of variables is identified to assist in the model analysis or diagnosis using orthogonal arrays and signal-to-noise ratios. And other several techniques have already been used for classification, such as linear discriminant analysis and logistic regression, decision trees, neural networks, etc. The goal of this case study is to compare the ability of the Mahalanobis-Taguchi System and logistic regression using a data set.

• 대한전기학회논문지
• /
• 제37권8호
• /
• pp.557-562
• /
• 1988

This paper presents a class of discrete adaptive controller that can be applied to a plant without sufficient a priori information. It is well known that the GMV(Generalized Minmum Variance) contrlller performs satisfactorily if the plant time delay is known. By introducing the long-range prediction into the GMV controller, robustness to the time delay can be improved, although optimality is lost. Such an idea motivates a predictive control system to be proposed here, where the system minimizes multi-stage cost via the GMV approach. Moreover, the detuning control weight is determined by an on-line tuning method. It is shown that robustness, computational efficiency, and performance of the resulting control system are improved as compared with those of the GPC(Generalized Predictive Control)system.