Notice of Violation of IEEE Publication PrinciplesA novel super-resolution music-based pseudo-bispectrum

Notice of Violation of IEEE Publication Principles

"A Novel Super-Resolution Music-Based Pseudo-Bispectrum"
by Walid A. Zgallai,
in the 17th International Conference on Digital Signal Processing (DSP), July 2011

After careful and considered review of the content and authorship of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE\´s Publication Principles.

This paper contains substantial duplication of original text from the paper cited below. The original text was copied without attribution (including appropriate references to the original author(s) and/or paper title) and without permission.

Due to the nature of this violation, reasonable effort should be made to remove all past references to this paper, and future references should be made to the following article:

"Application of Higher-order Statistics and Subspace Based Techniques to the Analysis and Diagnosis of Electrocardiogram Signals,"
by Sahar El-Khafif,
PhD thesis, School of Engineering, City University, UK, 2002

The high-resolution capability of eigen-decomposition-based techniques motivates their extension to the higher-order domain. A two-dimensional version of the MUSIC algorithm for estimating the quadratic phase coupling between two frequency components in the bispectrum domain is proposed in this paper. The algorithm is based on the Singular Value Decomposition (SVD) of a toeplitz matrix derived from the third-order cumulant sequence of the process. This matrix is decomposed into two orthogonal subspaces, the signal and the noise subspaces. A frequency estimation function matching the one used in the MUSIC algorithm is then constructed using the noise singular vectors. The proposed algorithm is aimed at extracting the phase-coupled frequencies in the bispectrum. Comparable resolution to the parametric approach of bispectrum estimation based on a non-Gaussian white noise driven Auto Regress- ve (AR) model is achievable for the same data length and better resolution is obtained for short data segments.