• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.10
• /
• pp.620-629
• /
• 2005

In this paper, a new protocol-based approach was proposed for development of a ubiquitous vision system. It is possible to apply the approach by regarding the ubiquitous vision system as a multiagent system. Thus, each vision sensor can be regarded as an agent (vision agent). Each vision agent independently performs exact segmentation for a target by color and motion information, visual tracking for multiple targets in real-time, and location estimation by a simple perspective transform. Matching problem for the identity of a target during handover between vision agents is solved by the Identified Contract Net (ICN) protocol implemented for the protocol-based approach. The protocol-based approach by the ICN protocol is independent of the number of vision agents and moreover the approach doesn't need calibration and overlapped region between vision agents. Therefore, the ICN protocol raises speed, scalability, and modularity of the system. The protocol-based approach was successfully applied for our ubiquitous vision system and operated well through several experiments.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.3 no.2
• /
• pp.133-137
• /
• 2003

Various bioinformatics tools for biological data processing have been developed and most of them are available in public. Most bioinformatics works are carried out by a composite application of those tools. Several integration approaches have been proposed for easy use of the tools. This paper proposes a new multi agent system to integrate bioinformatics tools in the perspective of workflow since the composite applications of tools can be regarded as workflows. For the easy integration, the proposed system employs wrapper agents for existing tools, uses XML-based messages in the inter-agent communication, and agents are supposed to extract necessary information from the received messages. This allows new tools to be easily added on the integration framework. The proposed method allows various control structures in workflow definition and provides the progress monitoring capability of the on-going workflows. In particular, agents in this system have the rule-based architecture which allows the defined rule set to be a special role agent. This feature provides fast and flexible agent development to aid in managing the complexity of bioinformatics application. This system has been partially implemented and has been proven to be a viable implementation for workflow-based bioinformatics tool integration.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.269-272
• /
• 2003

웹을 이용한 교수-학습모형인 WBI 학습을 촉진시키기 위해서 교육전문가에 의해 검증된 학습자료를 효율적으로 관리하는 시스템을 구축하고, 사용자가 원하는 문서를 추정하여 제시한다. 사용자가 참조한 문서들에 대하여 에이전트가 추가, 삭제 등을 자율적으로 하며, 참조 문서간의 유사도를 측정한다. 이 유사도를 이용하여 적합한 문서를 추정하고 제시함으로서 사용자의 불명확한 정보요구에도 적합한 문서를 제공할 수 있다. 따라서, 사용자의 정보수집을 지원하고 웹을 통한 학습환경을 개선하여 WBI 학습을 촉진시킬 수 있다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.59-62
• /
• 2003

에이전트에서 수행할 수 있는 작업들에 대한 처리시간이 실제 작업 전에는 퍼지값으로만 주어지고, 실제 작업이 수행될 때야 작업 시간이 결정되는 다중 에이전트 시스템에 대해서 작업을 조정하는 방법을 제안한다. 제안한 방법은 두 단계의 유전자 알고리즘으로 구성되는데, 상위 단계의 유전자 알고리즘에서는 작업들을 적합한 에이전트에 할당하는 역할을 하고, 하위 단계의 유전자 알고리즘은 첫 번째 유전자 알고리즘의 제시하는 작업 할당 방법에 가장 적합한 작업 스케줄을 탐색하는 역할을 한다. 이 논문에서는 제안한 유전자 알고리즘 기반 작업 조정 방법을 소개하고, 제안한 방법을 구현하여 실험한 결과를 보인다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.11a
• /
• pp.3-6
• /
• 2006

분산 환경에서의 자원 및 서비스를 활용하여 응용 시스템을 구축하기 위한 패러다임으로서 다중 에이전트 구조가 많아 연구되어 왔다. 이 논문에서는 다양한 자원 및 서비스를 개방적으로 활용하기 위해, 웹서비스의 개방적인 환경을 활용하여 에이전트 및 웹서비스 객체를 효과적으로 이용할 수 있도록 하는 개방형 다중 에이전트 시스템 구조에 대해서 소개한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.68-73
• /
• 2005

Various techniques have been proposed for detection and tracking of targets in order to develop a real-world computer vision system, e.g., visual surveillance systems, intelligent transport systems (ITSs), and so forth. Especially, the idea of distributed vision system is required to realize these techniques in a wide-spread area. In this paper, we develop a ubiquitous vision system for location-awareness of multiple targets. Here, each vision sensor that the system is composed of can perform exact segmentation for a target by color and motion information, and visual tracking for multiple targets in real-time. We construct the ubiquitous vision system as the multiagent system by regarding each vision sensor as the agent (the vision agent). Therefore, we solve matching problem for the identity of a target as handover by protocol-based approach. We propose the identified contract net (ICN) protocol for the approach. The ICN protocol not only is independent of the number of vision agents but also doesn't need calibration between vision agents. Therefore, the ICN protocol raises speed, scalability, and modularity of the system. We adapt the ICN protocol in our ubiquitous vision system that we construct in order to make an experiment. Our ubiquitous vision system shows us reliable results and the ICN protocol is successfully operated through several experiments.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.5
• /
• pp.598-606
• /
• 2002

We suggest a distributed communication and management methodology using PC to PC Query multicasting strategy for efficient management of medical images produced by DICOM(Digital Imaging and Communications in Medicine) Modalities. It is absolutely necessary to reduce strict degradation of PACS system due to large sire of medical images and their very high transport rates. DICOM PC to PC Component is composed of a Service Manager to execute requested queries, a Communication Manager to take charge of file transmission, and a DICOM Manager to manage stored data and system behavior Each Manager itself is a component to search for requested file by interaction or to transmit the file to other PCs. Distributed management and transformation of medical information based on PC to PC Query multicasting methodology will enhance performance of central server and network capacity, reducing overload on both. We organize three major components for system operation. Each component is implemented as Agent. Communication between agents uses XML encoded Agent Communication Language.

• Journal of KIISE:Software and Applications
• /
• v.30 no.12
• /
• pp.1220-1227
• /
• 2003

To perform rational decision-making, autonomous agents need considerable computational resources. When other agents are present in the environment, these demands are even more severe. In these settings, it may be difficult for the agent to decide what to do in an acceptable time in multiagent situations that involve many agents. These problems motivate us to investigate ways in which the agents can be equipped with flexible decision-making procedures that enable them to function in a variety of situations in which decision-making time is important. The flexible decision-making methods explicitly consider a tradeoff between decision quality and computation time. Our framework limits resources used for agent deliberation and produces results that are not necessarily optimal, but provide autonomous agents with the best decision under time pressure. We validate our framework with experiments in a simulated anti-air defense domain. The experiments show that compiled rules reduce computation time while offering good performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.4
• /
• pp.143-152
• /
• 2021

It is very important to learn behavioral policies that allow multiple agents to work together organically for common goals in various real-world applications. In this multi-agent reinforcement learning (MARL) environment, most existing studies have adopted centralized training with decentralized execution (CTDE) methods as in effect standard frameworks. However, this multi-agent reinforcement learning method is difficult to effectively cope with in a dynamic environment in which new environmental changes that are not experienced during training time may constantly occur in real life situations. In order to effectively cope with this dynamic environment, this paper proposes a novel multi-agent reinforcement learning system, C-COMA. C-COMA is a continual learning model that assumes actual situations from the beginning and continuously learns the cooperative behavior policies of agents without dividing the training time and execution time of the agents separately. In this paper, we demonstrate the effectiveness and excellence of the proposed model C-COMA by implementing a dynamic mini-game based on Starcraft II, a representative real-time strategy game, and conducting various experiments using this environment.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.407-410
• /
• 2007

자율컴퓨팅은 관리자나 사용자의 개입없이 시스템이나 서비스가 원활하게 동작되는 환경으로 구조조정, 최적화, 치료, 방어 등을 위한 여러가지 기술이 복합적으로 요구된다. 태스크를 자율적으로 완수하고 최적으로 수행하기위한 자율적 계획수립 및 계획실행은 자율컴퓨팅에서 필요한 요소기술이다. 이 논문에서는 목표의 실패없는 수행을 위한 여러 잠재적인 실행경로를 포함하는 강건한 계획수립과 다중 에이전트 구조를 이용하여 가용한 자원에 대한 전반적인 고려와 함께 실행시점의 상황을 반영하여 최적의 실행경로에 따라 계획을 실행하게 하는 방법을 제안한다.