A proposal of an evaluation method IPL for effects of individual quantity of domain knowledge on an intuitive classification in a distributed and cooperative KJ method and its application

Shigeki Sugiura, Jun Munemori, Tetsuo Kinoshita, Norio Shiratori

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a new evaluation method IPL (Island formation using Pseudo Label), and show its efficiency. In IPL method, the effects of domain knowledge of each participant can be evaluated based on an intuitive classification task in a distributed and cooperative KJ method. Experiments using IPL method show the influences upon the island formation caused by the distribution of knowledge quantitatively. There exists a similar method called LCR method which provides an evaluation method for the logical classification tasks. However the proposed IPL method provides an evaluation method for the intuitive classification tasks by which the creation of new idea can be done easily and effectively.

Original languageEnglish
Title of host publicationProceedings - 12th International Conference on Information Networking, ICOIN 1998
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages581-586
Number of pages6
ISBN (Electronic)0818672250, 9780818672255
DOIs
Publication statusPublished - 1998 Jan 1
Event12th International Conference on Information Networking, ICOIN 1998 - Koganei, Tokyo, Japan
Duration: 1998 Jan 211998 Jan 23

Publication series

NameProceedings - 12th International Conference on Information Networking, ICOIN 1998

Other

Other12th International Conference on Information Networking, ICOIN 1998
Country/TerritoryJapan
CityKoganei, Tokyo
Period98/1/2198/1/23

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems

Fingerprint

Dive into the research topics of 'A proposal of an evaluation method IPL for effects of individual quantity of domain knowledge on an intuitive classification in a distributed and cooperative KJ method and its application'. Together they form a unique fingerprint.

Cite this