Blind separation of piecewise stationary non-Gaussian sources

DOI10.1016/j.sigpro.2009.04.021zbMath1197.94070MaRDI QIDQ1957699

Petr Tichavský, Zbyněk Koldovský, Shahram Hosseini, Yannick Deville, Jiří Málek

Publication date: 27 September 2010

Published in: Signal Processing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.sigpro.2009.04.021

zbMATH Keywords

blind source separation; independent component analysis; Cramér-Rao lower bound; piecewise stationary model; fastica algorithm

Mathematics Subject Classification ID

94A12: Signal theory (characterization, reconstruction, filtering, etc.)

Uses Software

• FastICA
• TRINICON
• EFICA

Cites Work

• Unnamed Item
• Differential source separation for underdetermined instantaneous or convolutive mixtures: Concept and algorithms
• A unifying model for blind separation of independent sources
• Independent component analysis, a new concept?
• Second order nonstationary source separation
• Speed and Accuracy Enhancement of Linear ICA Techniques Using Rational Nonlinear Functions
• Maximum likelihood and lower bounds in system identification with non-Gaussian inputs
• Blind separation of mixture of independent sources through a quasi-maximum likelihood approach
• Corrections to “Performance Analysis of the FastICA Algorithm and CramÉr–Rao Bounds for Linear Independent Component Analysis”
• Fast Approximate Joint Diagonalization Incorporating Weight Matrices
• 10.1162/jmlr.2003.4.7-8.1261
• Jacobi Angles for Simultaneous Diagonalization
• Blind separation of instantaneous mixtures of nonstationary sources
• Linear Statistical Inference and its Applications