• DocumentCode
    350028
  • Title

    DASS: a discovery agent supporting system

  • Author

    Gouda, Karam A. ; Cheng, Jingde ; Ushijima, Kazuo

  • Author_Institution
    Dept. of Comput. Sci. & Commun. Eng., Kyushu Univ., Fukuoka, Japan
  • Volume
    5
  • fYear
    1999
  • fDate
    1999
  • Firstpage
    894
  • Abstract
    A discovery agent, which may be a human or a computing system to conduct and perform knowledge discovery from scientific data or from databases, makes extensive use of domain knowledge in order to increase the efficiency and effectiveness of the discovery process. This knowledge accumulates and becomes huge with the lapse of time or with the evolution of the discovery process. This huge amount of domain knowledge makes it difficult for the automatic or even human discovery agent to effectively use it and retrieve the relevant entities. It thus creates an urgent need to develop a supporting system addressing this issue. In this respect, we propose a supporting system named DASS (Discovery Agent Supporting System). DASS supports the discovery agent in finding the relevant entities of knowledge from its own domain knowledge base and probably from other knowledge based systems relevant to the field and available online. We give an outline of the architecture of DASS
  • Keywords
    data mining; inference mechanisms; information retrieval; knowledge based systems; very large databases; DASS; databases; discovery agent supporting system; discovery process; domain knowledge; domain knowledge base; human discovery agent; knowledge based systems; knowledge discovery; scientific data; supporting system; Automation; Computer science; Control systems; Data engineering; Databases; Humans; Intelligent agent; Intelligent systems; Knowledge based systems; Knowledge engineering;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on
  • Conference_Location
    Tokyo
  • ISSN
    1062-922X
  • Print_ISBN
    0-7803-5731-0
  • Type

    conf

  • DOI
    10.1109/ICSMC.1999.815672
  • Filename
    815672