본문 바로가기
  • Home

A FCA-based Classification Approach for Analysis of Interval Data

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2012, 17(1), pp.19-30
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

Suk-Hyung Hwang 1 Eunghee Kim 2

1선문대학교
2서울대학교

Accredited

ABSTRACT

Based on the internet-based infrastructures such as various information devices, social network systems and cloud computing environments, distributed and sharable data are growing explosively. Recently, as a data analysis and mining technique for extracting, analyzing and classifying the inherent and useful knowledge and information, Formal Concept Analysis on binary or many-valued data has been successfully applied in many diverse fields. However, in formal concept analysis, there has been little research conducted on analyzing interval data whose attributes have some interval values. In this paper, we propose a new approach for classification of interval data based on the formal concept analysis. We present the development of a supporting tool(iFCA) that provides the proposed approach for the binarization of interval data table, concept extraction and construction of concept hierarchies. Finally, with some experiments over real-world data sets, we demonstrate that our approach provides some useful and effective ways for analyzing and mining interval data.

Citation status

* References for papers published after 2022 are currently being built.