EURASIP Journal on Applied Signal Processing
Volume 2002 (2002), Issue 12, Pages 1473-1484
doi:10.1155/S1110865702210033
Simultaneous Principal-Component Extraction with Application to Adaptive Blind Multiuser Detection
Computational NeuroEngineering Laboratory, Electrical and Computer Engineering Department, University of Florida, NEB 454, Gainesville 32611, FL, USA
Received 31 January 2002; Revised 30 July 2002
Abstract
SIPEX-G is a fast-converging, robust, gradient-based PCA algorithm that has been recently proposed by the authors. Its superior performance in synthetic and real data compared with its benchmark
counterparts makes it a viable alternative in applications where subspace methods are employed. Blind multiuser detection is one such area, where
subspace methods, recently developed by researchers, have proven effective.
In this paper, the SIPEX-G algorithm is presented in detail, convergence proofs are derived, and the performance is demonstrated in standard subspace
problems. These sub space problems include direction of arrival estimation for incoming signals impinging on a linear array of sensors, nonstationary random
process subspace tracking, and adaptive blind multiuser detection.