Blind identification of second order volterra systemswith complex random inputs using higher order cumulants

Authors:
Gerasimos Mileounis;Nicholas Kalouptsidis
Affiliations:
Division of Communications and Signal Processing, Department of Informatics and Telecommunications, University of Athens, Ilissia, Athens, Greece;Division of Communications and Signal Processing, Department of Informatics and Telecommunications, University of Athens, Ilissia, Athens, Greece
Venue:
IEEE Transactions on Signal Processing
Year:
2009

Citing 6
Cited 1

Principles of Digital Transmission: With Wireless Applications

Principles of Digital Transmission: With Wireless Applications
Blind Channel Equalization and Identification

Blind Channel Equalization and Identification
Blind identification of a linear-quadratic model using higher-order statistics

ICASSP '93 Proceedings of the Acoustics, Speech, and Signal Processing, 1993. ICASSP-93 Vol 4., 1993 IEEE International Conference on - Volume 04
Blind identification of a linear-quadratic mixture of independent components based on joint diagonalization procedure

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 05
Harmonics in multiplicative and additive noise: parameterestimation using cyclic statistics

IEEE Transactions on Signal Processing
A cumulant interference subspace cancellation method for blind SISO channel estimation

IEEE Transactions on Signal Processing

A sparsity driven approach to cumulant based identification and order determination

Signal Processing

Quantified Score

Hi-index	35.68

Visualization

Abstract

In this correspondence, closed-form expressions for the blind identification of linear-quadratic Volterra systems are established. The system is excited by a complex valued random sequence and the output cumulants (of order up to 4) are employed. It is assumed that the memory of the linear part is greater than or equal to the memory of the quadratic part. Cumulant-based formulas are developed demonstrating that the system is uniquely identifiable. An SVD based variant with improved performance is also derived. Simulations and comparisons with existing techniques are presented.