• Journal of KIISE:Software and Applications
• /
• v.35 no.3
• /
• pp.179-188
• /
• 2008

An important issue in multiagent reinforcement learning is how an agent should team its optimal policy through trial-and-error interactions in a dynamic environment where there exist other agents able to influence its own performance. Most previous works for multiagent reinforcement teaming tend to apply single-agent reinforcement learning techniques without any extensions or are based upon some unrealistic assumptions even though they build and use explicit models of other agents. In this paper, basic concepts that constitute the common foundation of multiagent reinforcement learning techniques are first formulated, and then, based on these concepts, previous works are compared in terms of characteristics and limitations. After that, a policy model of the opponent agent and a new multiagent reinforcement learning method using this model are introduced. Unlike previous works, the proposed multiagent reinforcement learning method utilize a policy model instead of the Q function model of the opponent agent. Moreover, this learning method can improve learning efficiency by using a simpler one than other richer but time-consuming policy models such as Finite State Machines(FSM) and Markov chains. In this paper. the Cat and Mouse game is introduced as an adversarial multiagent environment. And effectiveness of the proposed multiagent reinforcement learning method is analyzed through experiments using this game as testbed.

• Archives of Pharmacal Research
• /
• v.29 no.1
• /
• pp.50-58
• /
• 2006

Translationally controlled tumor protein (TCTP), also known as histamine releasing factor (HRF), is found abundantly in different eukaryotic cell types. The sequence homology of TCTP between different species is very high, belonging to the MSS4/DSS4 superfamily of proteins. TCTP is involved in both cell growth and human late allergy reaction, as well as having a calcium binding property; however, its primary biological functions remain to be clearly elucidated. In regard to many possible functions, the TCTP of Plasmodium falciparum (Pf) is known to bind with an antimalarial agent, artemisinin, which is activated by heme. It is assumed that the endoperoxide-bridge of artemisinin is opened up by heme to form a free radical, which then eventually alkylates, probably to the Cys14 of PfTCTP. Study of the docking of artemisinin with heme, and subsequently with PfTCTP, was carried out to verify the above hypothesis on the basis of structural interactions. The three dimensional (3D) structure of PfTCTP was built by homology modeling, using the NMR structure of the TCTP of Schizosaccharomyces pombe as a template. The quality of the model was examined based on its secondary structure and biological function, as well as with the use of structure evaluating programs. The interactions between artemisinin, heme and PfTCTP were then studied using the docking program, FlexiDock. The center of the peroxide bond of artemisinin and the Fe of heme were docked within a short distance of $2.6{\AA}$, implying the strong possibility of an interaction between the two molecules, as proposed. When the activated form of artemisinin was docked on the PfTCTP, the C4-radical of the drug faced towards the sulfur of Cys14 within a distance of $2.48{\AA}$, again suggesting the possibility of alkylation having occurred. These results confirm the proposed mechanism of the antimalarial effect of artemisinin, which will provide a reliable method for establishing the mechanism of its biological activity using a molecular modeling study.

• The Journal of the Korea Contents Association
• /
• v.14 no.1
• /
• pp.537-547
• /
• 2014

In this paper, the ALT (ALTernative) board and a NetLogo extension module are developed for the active participatory simulation (APS) learning. Through the participatory simulation with HubNet each student can attend the experiment as one of clients. Only one HubNet server, however, is able to use an external device so that the bifocal modeling based learning with multiple users is impossible. In order to overcome the drawback, and enable clients participate into the experiment and collect the experimental data and the measured data, an ATmega 32 based board and its firmware are developed. In addition, Java extension module based on TCP/IP socket interfaces is developed to exchange the data with HubNet server. Finally, we show some NetLogo program examples to use the developed hardware and software for APS and seek the way to use them for science education.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.15 no.1
• /
• pp.8-15
• /
• 2007

Freeway corridors consist of urban freeways and parallel arterials that drivers can use alternatively. Ramp metering in freeways and signal control in arterials are contemporary traffic control methods that have been developed and applied in order to improve traffic conditions of freeway corridors. However, most of the existing studies have focused on either optimal ramp metering in freeways, or progression signal strategies between arterial intersections. There have been no traffic control systems in Korea that integrates the freeway ramp metering and arterial signal control. The effective control strategies for freeway operations may cause negative effects on arterial traffic. On the other hand, traffic congestion and bottleneck phenomenon of arterials due to the increasing peak-hour travel demand and ineffective signal operation may generate an accessibility problem to freeway ramps. Thus, the main function of the freeway which is the through-traffic process has not been successful. The purpose of this study is to develop an integrated control model that connects freeway ramp metering systems and signal control systems in arterial intersections. And Optimization of integrated control model which consists of ramp metering and signal control is another purpose. The design of experiment, neural network, and simulated annealing are used for optimization.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.9
• /
• pp.1038-1048
• /
• 2019

Recently, various systems have been developed to support ship navigation safety. In order to verify the usefulness of such a system, it is most ideal to try it on a real vessel, but there are many difficulties. As an alternative, usability verification methods applied with modelling and simulation (M&S) techniques are required such as FMSS, which is closest to reality, is very expansive to construct, and there needs the specialized operator. For this reason, this paper proposes a method to verify the navigation safety support system by modeling and simulation techniques based on the Discrete Event System Specification (DEVS) formalism. As a first step, we designed the navigation simulation architecture based on the SES/MB framework, and details on modelling ship core equipment and navigator agents based on the DEVS. Through this, we are able to implement the navigation simulation system for vessels, and evaluate the effectiveness of navigation safety support elements such as collision avoidance, etc. using developed scenarios.

• The Journal of Information Systems
• /
• v.12 no.2
• /
• pp.57-72
• /
• 2003

The purpose of this paper is to propose the modeling of multiagent based SCM and implement the prototype in the Internet environment. SCM process follows the supply chain operations reference (SCOR) model which has been suggested by Supply Chain Counsil. SCOR model has been positioned to become the industry standard for describing and improving operational process in SCM. Five basic processes, plan, source, matte, deliver and return are defined in the SCOR model, through which a company establishes its supply chain competitive objectives. A supply chain is a world wide network of suppliers, factories, warehouses, distribution centers and retailers through which raw materials are acquired, transformed or manufactured and delivered to customers by autonomous or semiautonomous process. With the pressure from the higher standard of customer compliance, a frequent model change, product complexity and globalization, the combination of supply chain process with an advanced infrastructure in terms of multiagent systems have been highly required. Since SCM is fundamentally concerned with coherence among multiple decision makers, a multiagent framework based on explicit communication between constituent agents such as suppliers, manufacturers, and distributors is a natural choice. Multiagent framework is defined to perform different activities within a supply chain. Dynamic and changing functions of supply chain can be dealt with multi-agent by cooperating with other agents. In the areas of inventory management, remote diagnostics, communications with field workers, order fulfillment including tracking and monitoring, stock visibility, real-time shop floor data collection, asset tracking and warehousing, customer-centric supply chain can be applied and implemented utilizing multiagent. In this paper, for the order processing event between the buyer and seller relationship, multiagent were defined corresponding to the SCOR process. A prototype system was developed and implemented on the actual TCP/IP environment for the purchase order processing event. The implementation result assures that multiagent based SCM enhances the speed, visibility, proactiveness and responsiveness of activities in the supply chain.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09b
• /
• pp.27-30
• /
• 2003

웹 기반하에서 사용자의 질의에 대한 효율적인 검색결과를 제공하기 위하여 다양한 검색 알고리즘들이 개발되어 왔으며, 이러한 알고리즘들의 대부분은 사용자의 선호도나 편의성을 고려하였다. 그러나 지금까지 개발된 검색 알고리즘들은 일반적으로 웹이라는 수평의 비계층적인 웹 환경에서 개발된 것으로서 기업의 전사적 네트워크와 같이 계층적이고 기능적으로 복잡하게 구성되어 있는 웹 기반 환경에서는 적용하기가 힘든 실정이다. 본 논문에서는 이러한 특수한 웹 기반 환경하에서 사용자에게 효율적으로 마이닝 결과를 제공할 수 있는 멀티-에이전트 기반의 웹 마이닝 시스템을 제안한다. 이를 위해 우리는 계층적 웹 기반 환경이라는 네트워크 모델을 제시하며, 제시된 웹 환경에서 적용할 수 있는 4개의 협력 에이전트와 14개의 프로세스 모듈을 가진 멀티-에이전트 기반의 웹 마이닝 시스템을 설계한다. 그리고 각 에이전트에 대한 세부기능을 계층적 환경을 고려하여 모듈별로 설명하며 특히, 새로운 머징 에이전트와 개선된 랭킹 알고리즘을 그래프 이론을 적용하여 제안한다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2004.05a
• /
• pp.458-462
• /
• 2004

eSCM은 고객과의 주 접촉 수단으로써 다른 어떤 수단보다 비용절감과 시간적 공간적 제약을 극복할 수 있는 인터넷을 통해 공급체인을 구성하고 있는 모든 기업을 하나로 묶어 네트워크를 형성함으로써, 정보공유와 커뮤니케이션을 가능하게 하여 네트워크상의 모든 자원의 효율을 높이는 것을 목적으로 한다. 이러한 공급체인상의 모든 구성원 간의 통합이 실질적으로 효과를 나타내기 위해서는 조정된 방법으로 운영되어야 한다. 기업 환경의 새로운 변화에 유연하게 대처, 구성원간의 거래에서 정상 루트를 벗어난 예측하지 못했던 상황 즉, 고객의 변심에 따른 주문량 변경/취소, 계절적 요인으로 인한 주문량 폭주, 원자재/부품의 공급지연에 대한 납기 일정 수정 등에 대해 능동적이고 자율적으로 대처할 수 있는 공급체인 내에 Intelligent 기능을 가진 조정 에이전트를 적용한 개선된 공급체인 도입을 요구하고 있다. 따라서 본 연구에서는 eSCM의 구성원을 에이전트로 나타내어 이를 바탕으로 조정 에이전트 기반의 eSCM을 모델링하고 시뮬레이션을 통하여 그 조정 능력을 분석한다.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2003.10a
• /
• pp.61-65
• /
• 2003

암의 성장을 정확하게 예측할 수 있다면 암으로 고통 받는 많은 사람들에게 적절한 치료 및 처방을 내릴 수 있을 것이다. 그 동안 암의 성장을 예측하기 위하여 많은 연구가 진행되어왔는데 크게 나누어 하향식 설계 방법과 상향식 설계 방법이 있다. 하향식 방법은 전체적인 흐름을 파악하기는 쉽지만, 지역적 특성을 고려하기 어렵다는 단점이 있고, 상향식 방법은 지역적 특성은 고려하기 쉽지만, 전체적인 흐름을 파악하기 어려운 단점이 있다. 본 논문에서는 두 가지 방법을 혼합한 방법을 사용하여 지역적으로는 불규칙적인 암의 성장 모습과 암이 다른 조직으로 전이되는 모습을 동시에 관찰 할 수 있게 하였다. 아울러 시뮬레이션된 암의 모형이 실제 임상학적인 모습과 유사하다는 것을 발견하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.305-310
• /
• 2010

최근 세계화의 흐름 속에 경제영역에서 더 높은 수준의 국가간 협력과 공조를 필요로 하는 실정이다. 하지만 복잡한 이해관계 속에서 적절한 무역 전략을 취하는 것은 쉬운 일이 아니다. 본 논문에서는 무역정책의 방향을 수립함에 참고하기 위한 방법으로, 국제 무역의 주체가 되는 국가를 진화 에이전트로 구성하고 이차원 공간상에 배치시켜 국제무역현상을 모델링 하였다. 국가 에이전트는 다양한 속성을 기반으로 구성되며, 진화 연산을 적용하여 무역 전략을 국제무역정세에 따라 동적으로 변화하도록 하였다. 국제무역에서 중요한 요인인 국가협력관계와 상대적 무역정책에서 파생되는 무역이익은 게임이론을 적용하여 모델링하였다. 다수의 실험을 통하여 본 모델링 방법이 실제 무역 현상을 재현함을 확인하였으며, 특히 상대 국가별 발전 정도에 따라 정책을 변화시키는 것이 자국의 이익을 추구에 중요한 요소임을 확인하였다.