Independent Component Analysis for Feature Extraction Concerning External Criteria

• HONDA Katsuhiro

  Graduate School of Engineering, Osaka Prefecture University

• MAENAKA Tatsuya

  Graduate School of Engineering, Osaka Prefecture University

• ICHIHASHI Hidetomo

  Graduate School of Engineering, Osaka Prefecture University

Bibliographic Information

Other Title

• 外的基準の説明を目的とした独立成分分析
• ガイテキ キジュン ノ セツメイ オ モクテキ ト シタ ドクリツ セイブン ブンセキ

Abstract

Independent component analysis (ICA) is an unsupervised technique for signal processing, and is useful for projection pursuit as well. This paper proposes an enhanced technique of ICA, which extracts independent components that are useful for revealing mutual relationship between observations and some external criteria. Fast ICA algorithm is performed after the preprocessing by regression-principal component analysis that extracts latent variables closely related to external criteria from observations. Numerical experiments including knowledge discovery from POS transaction data reveal the characteristic feature of the proposed method.

Journal

• Transactions of the Institute of Systems, Control and Information Engineers

  Transactions of the Institute of Systems, Control and Information Engineers 19 (9), 358-364, 2006

  THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE)

Keywords

• independent component analysis
• regressionprincipal component analysis
• external criterion

Details

• CRID: 1390001205166822784
• NII Article ID: 10018416698
• NII Book ID: AN1013280X
• DOI: 10.5687/iscie.19.358
• ISSN: 2185811X
• ISSN: 13425668
• NDL BIB ID: 8055727
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I8055727
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
• Abstract License Flag: Disallowed