A New Adaptive Filter Algorithm for System Identification Using Independent Component Analysis

• Yang Jun-Mei

  Department of Systems Science, Graduate School of Informatics, Kyoto University

• Sakai Hideaki

  Department of Systems Science, Graduate School of Informatics, Kyoto University

Bibliographic Information

Other Title

• 独立成分分析を用いたシステムの同定のための新しい適応アルゴリズム

Abstract

This paper proposes a new adaptive filter algorithm for system identification using independent component analysis (ICA). A nonparametric Parzen window density estimator and the stochastic information gradient are used. The local convergence condition is shown. Some simulation results have been carried out to show its superiority to the conventional NLMS algorithm.

Journal

• Proceedings of the Annual Conference of the Institute of Systems, Control and Information Engineers

  Proceedings of the Annual Conference of the Institute of Systems, Control and Information Engineers SCI07 (0), 106-106, 2007

  The Institute of Systems, Control and Information Engineers

Keywords

• Independent component analysis
• Adaptive gradient descent algorithm
• Parzen window density estimate
• Convergence analysis

Details

• CRID: 1390001205621392256
• NII Article ID: 110007540849
• NII Article ID: 130006981272
• NII Book ID: AA10826239
• DOI: 10.11509/sci.sci07.0.106.0
• Text Lang: ja
• Data Source:
  • JaLC
  • CiNii Articles
• Abstract License Flag: Disallowed