Loading...

Sequential blind source extraction for quasi-periodic signals with time-varying period

Tsalaile, T ; Sharif University of Technology | 2009

743 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/TBME.2008.2002141
  3. Publisher: 2009
  4. Abstract:
  5. A novel second-order-statistics-based sequential blind extraction algorithm for blind extraction of quasi-periodic signals, with time-varying period, is introduced in this paper. Source extraction is performed by sequentially converging to a solution that effectively diagonalizes autocorrelation matrices at lags corresponding to the time-varying period, which thereby explicitly exploits a key statistical nonstationary characteristic of the desired source. The algorithm is shown to have fast convergence and yields significant improvement in signal-to-interference ratio as compared to when the algorithm assumes a fixed period. The algorithm is further evaluated on the problem of separation of a heart sound signal from real-world lung sound recordings. Separation results confirm the utility of the introduced approach, and listening tests are employed to further corroborate the results. © 2009 IEEE
  6. Keywords:
  7. Blind source extraction (BSE) ; Time-varying period ; Quasi-periodic ; Second-order statistics ; Statistical nonstationarity ; Convergence of numerical methods ; Sequential switching ; Sound recording ; Statistics ; Time varying systems ; Blind source separation ; Algorithm ; Article ; Binocular convergence ; Blind source extraction ; Controlled study ; Electrocardiogram ; Extraction ; Heart sound ; Lung ; Recording ; Simulation ; Sound detection ; Time ; Algorithms ; Computer Simulation ; Electrocardiography ; Heart Sounds ; Humans ; Models, Statistical ; Normal Distribution ; Respiratory Sounds ; Signal Processing, Computer-Assisted
  8. Source: IEEE Transactions on Biomedical Engineering ; Volume 56, Issue 3 , 2009 , Pages 646-655 ; 00189294 (ISSN)
  9. URL: https://ieeexplore.ieee.org/document/4564196