• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.4
• /
• pp.395-399
• /
• 2005

In this paper, we presents HIGH-Q learning algorithm with reinforcement learning for more fast and exact topic-directed web spidering. The purpose of reinforcement learning is to maximize rewards from environment, an reinforcement learning agents learn by interacting with external environment through trial and error. We performed experiments that compared the proposed method using reinforcement learning with breath first search method for searching the web pages. In result, reinforcement learning method using future discounted rewards searched a small number of pages to find result pages.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.6
• /
• pp.548-556
• /
• 2000

멀티에이전트 시스템(MAS: Multi-Agent System)에서 에이전트는 각자의 목표 달성을 위해 주위 에이전트들과의 상호작용을 통해 목표의 충돌이 없는 일치 상황에 도달하도록 설계되어야 한다. 멀티에이전트 시스템에서 에이전트들 사이의 목표 충돌은 일반적으로 발생 가능한 상황이고, 어떤 에이전트가 다른 에이전트에 관한 모든 지식을 가진다는 것은 불가능하기 때문에 상대방에 관한 부분적인 지식만을 가진 상황에서 목표 충돌을 해결할 수 있는 협상은 중요하다. 본 논문은 멀티에이전트 시스템에서 믿음(Belief), 소망(Desire); 그리고 의도(Intention)을 에이전트 구조의 핵심 요소로 가정하고 이러한 구조를 가지는 BDI 에이전트를 논리 프로그래밍의 입장에서 표현한다. 또한 서로 다른 목표를 가진 BDI 에이전트들이 서로 협상하여 문제를 해결하는 과정에서 발생하는 에이전트들 상호간의 목표 충돌을 해결하는 방법을 제시하며, 이 방법의 효과성을 검증하기 위하여 JAVA와 PROLOG를 결합시킨 InterPROLOG 프로그래밍 언어로 구현하여 시험한다.

• Journal of Information Technology Services
• /
• v.1 no.1
• /
• pp.119-139
• /
• 2002

It is noteworthy that IMT -2000 communication network based on All-HP/AIN(Advanced Intelligent Network) should accomodate current and future wire/wireless AIN service easily through integration and gearing AIN construction elements. In this paper. Intelligent Farmer model(I-Farmer Model) and methodology are suggested in order to solve the several problems including standardization on implementation of Q3 interface in Telecommunication Management Network(TMN) agents which is caused by heterogeneous platform environment and future maintenance. Also this paper proposes ITI algorithm transforming the system which is designed by I-Farmer model to Interface Specification Model(ISM) applying the I-Farmer model. In addition to ITI algorithm. we suggest NTS(Node to SIB) algorithm converting entity node and ILB/OLB component in agent system designed by the I-Farmer model to SIB of AIN GFP(Global Functional Plane) and to ASIB for application program.

• Asia pacific journal of information systems
• /
• v.9 no.4
• /
• pp.41-67
• /
• 1999

ERP is now one of the prevailing applications for integrated information systems, So far, the conventional ERPs lack how to manage knowledge of making decisions, that is one of the important goal of ERP. This gives a motivation on adding decision support capabilities to the ERPs: active advice for business analysis, evaluation and control. In this paper, we proposed an agent-based intelligent ERP that is operated on the Internet. In special, knowledge of economic value added (EVA) is explicitly acquired as a set of data, models and methodologies, A new knowledge representation format, MIF, is suggested to show the communication mechanism between agents, The agent-based knowledge processing is adopted to deliver intelligence on the Internet.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.194-207
• /
• 2022

In the last decade, substantial progress has been achieved in intelligent traffic control technologies to overcome consistent difficulties of traffic congestion and its adverse effect on smart cities. Edge computing is one such advanced progress facilitating real-time data transmission among vehicles and roadside units to mitigate congestion. An edge computing-based deep reinforcement learning system is demonstrated in this study that appropriately designs a multiobjective reward function for optimizing different objectives. The system seeks to overcome the challenge of evaluating actions with a simple numerical reward. The selection of reward functions has a significant impact on agents' ability to acquire the ideal behavior for managing multiple traffic signals in a large-scale road network. To ascertain effective reward functions, the agent is trained withusing the proximal policy optimization method in several deep neural network models, including the state-of-the-art transformer network. The system is verified using both hypothetical scenarios and real-world traffic maps. The comprehensive simulation outcomes demonstrate the potency of the suggested reward functions.

• The Journal of Society for e-Business Studies
• /
• v.6 no.3
• /
• pp.63-80
• /
• 2001

The construction of the students knowledge in e-Learning systems, namely the student modeling, is a core component used to develop e-Learning systems. However, existing e-Learning systems have many problems to share the knowledge in a heterogeneous student model and a distributed knowledge base. Because the methods of the knowledge representation are different in each e-Learning systems, the accumulated knowledge cannot be used or shared without a great deal of difficulty. In order to share this knowledge, existing systems must reconstruct the knowledge bases. Consequently, we propose a new a Case Markup Language based on XML in order to overcome these problems. A distributed e-Learning systems fan have the advantage of easily sharing and managing the heterogeneous knowledge base proposed by CaseML. Moreover students can generate and share a case knowledge to use the communication protocol of agents. In this paper, we have designed and developed a CaseML by using a knowledge markup language. Furthermore, in order to construct an intelligent e-Learning systems, we have done our research based on the design and development of the intelligent agent system by using CaseML.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.511-515
• /
• 2001

Many intelligent agent systems are known to incorporate BDI architecture for cognitive reasoning. Since this architecture contains all the knowledge of world model and reasoning rule, it is very complex and difficult to handle. This paper describes a methodology to design and implement BDI architecture, BDIAXml based on XML for multi-agent systems. This XML-based BDI architecture is smaller than any other BDI architecture because it separates knowledge for reasoning from domain knowledge and enables knowledge sharing using XML technology. Knowledge for BDI mental state and reasoning is composed of specific XML files and these XML files are stored into a specific knowledge server. Most systems using BDIAxml architecture can access knowledge from this server. We apply this BDIAXml system to domain of Hospital Information System and show that this architecture performs more efficiently than other BDI architecture system in terms of knowledge sharing, system size, and ease of use.

• Journal of Intelligence and Information Systems
• /
• v.12 no.4
• /
• pp.73-90
• /
• 2006

When a consumer intends to purchase products through Internet stores, many difficulties are met because of limitations of the current search engines and the current web structure, and lack of tools supporting decision-makings. This paper raises an Internet shopping problem and proposes a framework of decision making process to settle it with an intelligent agent based on Semantic Web and Finite Domain Constraint. The agent uses finite domain constraint programming as modeling and solution methods for the decision problem under the Semantic Web environment.

• Proceedings of the Korea Database Society Conference
• /
• 1999.06a
• /
• pp.35-47
• /
• 1999

Raisin Bread Intelligent agents are ninety-nine percent computer science and one percent AI (Etzioni 1990). 에이전트의 정의 An agent is a computer system, situated in some environment, that is capable of flexible autonomous action in order to meet its design objectives (Wooldridge and Jennings 1995). ㆍsituatedness: the agent receives sensory input from its environment and can perform actions which change the environment in some way ㆍautonomy: the system is able to act without the direct intervention of humans and has control over its own actions and internal state. ㆍflexible: responsive, pro-active, social(omitted)

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.89.6-89
• /
• 2001

In Vehicle Information and Communication System (VICS), which is an active field of Intelligent Transport System (ITS), information of traffic congestion is sent to each vehicle at real time. However, a centralized navigation system is not realistic to guide millions of vehicles in a megalopolis. Autonomous distributed systems should be more flexible and scalable, and also have a chance to focus on each vehicle´s demand. This paper proposes a sub-optimal route planning mechanism of vehicles in urban areas using the non-network type immune system. Simulation is carried out using a cellular automaton model. This system announces a sub-optimal route to drivers in real time using VICS.