• Korean Journal of Cognitive Science
• /
• v.10 no.1
• /
• pp.67-78
• /
• 1999

Information providers on WWW have been rapidly increasing, and they provide a vast amount of information in various fields, Because of this reason, it becomes hard for users to get the information they want. Although there are several search engines that help users with the keyword matching methods, it is not easy to find suitable keywords. In order to solve these problems with a specific domain, we propose an intelligent information agent(HHA-la : HongIk Information Agent) that converts user's q queries to forms including related domain words in order to represent user's intention as much as it can and provides the necessary information of the domain to users. HHA-la h has an ontological knowledge base of animal domain, supplies necessary information for queries from users and other agents, and provides relevant web page information. One of system components is a WebDB which indexes web pages relevant to the animal domain. The system also supplies new operators by which users can represent their thought more clearly, and has a learning mechanism using accumulated results and user feedback to behave more intelligently, We implement the system and show the effectiveness of the information agent by presenting experiment results in this paper.

• Journal of Korean Society of Rural Planning
• /
• v.20 no.3
• /
• pp.143-154
• /
• 2014

For the purpose of drawing a representative type of utilizing idle farmlands, this study collected and analyzed newspaper articles about cases of utilizing idle farmlands in the past decade using Internet search engines. Prior to this, it clarified a concept of idle farmlands to raise accuracy of searching articles, and selected NAVER as a search engine. It set "idle farmland", "abandoned land", and "utilizing" as basic search words in search option, and also set search period from 1st of January in 2004 to 31st of December in 2013. This study primarily searched 1,593 articles, and extracted 165 articles excluding overlapped and unrelated articles. Furthermore, it investigated extracted articles by date, media, headline, content of use, region(province), particular area(city and country), main agent, item and keyword 1, 2, 3 for proper use. This study also examined frequencies by year according to indoor and outdoor environment as well as regional differences through frequencies by regional groups and chronology. Furthermore, it drew a diagram of frequency flow of keyword 2, 3 with each keyword 1 as the central figure in order to draw various types of using idle farmlands. Through the diagrams, this study drew 9 using types such as (1) community service. agriculture type, (2) high income. agriculture type, (3) sightseeing. landscape. agriculture type, (4) livestock. agriculture type, (5) weekend farm type, (6) high income. woodland type, (7) ecology. landscape. woodland type, (8) agricultural work-study type, (9) ecological environment type.

• The KIPS Transactions:PartA
• /
• v.10A no.5
• /
• pp.439-452
• /
• 2003

Mobile agent is one of the good technologies for overcoming network load and latency in distributed applications, and it may be a promising way of base technology of distributed applications because of its high adaptability for various network environments. In this paper, a mobile agent programming system, called HUMAN, is designed and implemented efficient use in various distributed applications based on mobile agents. HUMAN supports such high level utilities as file searhing, addressing by groups of nodes, storing path information, storing search information, and thus it gives us high easiness in agent-based programming. And it provides various itinerary modes and flexible reply modes for easy adaptation to given network environment. It also provides a management server for registering and active agents. Thus it can be efficiently applied for such varous distributed applications as searching distributed information, remote control, and file sharing in networks. A simple electronic commerce system is designed is designed and implemented as a HUMAN based illustrative application.

• Journal of KIISE:Software and Applications
• /
• v.30 no.1_2
• /
• pp.40-50
• /
• 2003

Ontology is the artifacts for representing the truth or the states of objects by defining objects and their relations. In this paper, we propose an agent that classifies Web documents and provides personalized information towards user`s information needs using ontology. the agent uses ontology in which semantic relations on Web documents are represented in ta hierarchical form to classify Web documents. In this paper, ontology consists of concepts, features(describing concepts), relations(among concepts) and constraints(among elements in a feature). The agent can capture user's information needs efficiently by using ontology and assist Web navigation by using users profiles and the results of identification of semantic relations in Web documents. Also, the agent obtains Web documents by a look-ahead search and represents them as concepts, therefore users can understand them easily by receiving recommendations expressed in the form of high-level concepts.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.107-109
• /
• 1999

본 논문에서는 사용자를 대행할 수 있는 분산 다중 에이전트 기술을 이용한 웹 문서 검색 시스템을 설계 및 구현한다. 분산 환경에서의 에이전트 기술은 문서의 근접도를 평가할 때 기존의 웹 검색 엔진보다 복잡한 알고리즘 적용이 가능하며, 이로써 좀 더 정확한 문서들을 사용자에게 제공할 수 있다. 또한 분산환경으로 네트워크의 부하를 분산시킴으로써, 빠르게 자료검색 결과를 얻을 수 있는 장점이 있다. 분산된 시스템에서 에이전트들의 효율적인 통신을 위하여 프로토콜 레이어를 구현하였으며, 에이전트들의 상호 협동과 의사 소통 및 중재를 위한 하부구조(infrastructure)를 구축하여 웹 문서검색을 효과적으로 하고, 사용자 이동성을 가능하게 하였다.

• Bulletin of the Korean Chemical Society
• /
• v.33 no.2
• /
• pp.575-582
• /
• 2012

In continuance of our search for newer antihepatotoxic agents some novel thiazolidinone derivatives containing 1,4-benzodioxane ring system were synthesized starting from 2,3-dihydro-1,4-benzodioxane-2-carbohydrazide. The synthesized compounds were evaluated for antihepatotoxic activity against $CCl_4$-induced hepatotoxicity in rats. Among them some compounds have shown significant antihepatotoxic activity comparable to standard drug silymarin.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.91-94
• /
• 2007

구글이나 야후와 같은 정보검색엔진은 사용자에게 편리성을 제공하나 사용자로 하여금 만족감을 제공하지는 못하고 있다. 이것은 사용자에 대한 검색목표가 사용자 프로파일마다 서로 다르기 때문이다. 따라서 검색엔진으로 검색된 결과를 사용자 프로파일에 따라서 재배치하는 것은 매우 필요하다. 이 논문에서는 키워드기반 검색엔진으로 검색된 결과를 사용자 프로파일에 따라 웹문서를 재배치하는 알고리즘을 제안한다. 각 키워드에 대한 가중치는 사용자가 웹문서에 대해서 수행한 행동 즉, 다운로드, 클릭, 아무행동 안함에 따라 차등 적용하여 업데이트하여 웹문서를 리스트하여 사용자에게 제공한다.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.631-632
• /
• 2008

In this paper, we propose service discovery mechanism, using CALM agent platform to guarantee scalability of scope of available services without modifying existing service discovery protocols. The proposed service discovery mechanism provides users with a wider selection of services, and convenient search methods.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.373-375
• /
• 2002

하이퍼 텍스트 구조의 특성을 이용한 순위 평가 알고리즘 중의 하나인 HITS 알고리즘은 웹 페이지들의 상호간에 연결된 링크 정보로부터 웹 문서들의 중요도를 평가하여 순위에 따른 결과를 제시한다. 그러나 초기의 HITS 알고리즘은 문서 내의 링크 빈도 수만을 고려하고, 입력 값으로 주어지는 웹 문서 집합의 특성에 의존적인 단점을 가지고 있다. 본 논문에서는 여러 웹 검색 엔진들로부터 얻어진 문서 집합에 수정된 HITS 알고리즘을 수행하는 메타 검색 에이전트를 설계하여 보다 나은 검색 성능을 구하고, 결과의 지역성을 보완한다.

• Journal of KIISE:Software and Applications
• /
• v.26 no.2
• /
• pp.203-212
• /
• 1999

디지털 도서관 시스템의 검색에서 발생하는 가장 큰 문제점은 질의에 있어 사용자의 의도와 시스템의 해석간의 의미적, 형식적 차이가 생긴다는 점에 있다. 우리는 보다 효과적으로 사용자의 의도를 반영할 수 있도록 사용자의 질의를 변환하는 지능적 검색 에이전트를 제안한다. 이를 위해서 의미적 질의 최적화기법에 근거를 둔 변환 알고리즘과 에이전트 아키텍쳐를 정의한다. 제안된 알고리즘은 범용 추론키보다 훨씬 간단하면서도 효과적으로 사용자의 질의를 변환한다.