论文信息 - A pipelined structure for QR adaptive LS system identification

A pipelined structure for QR adaptive LS system identification

A novel systolic array for LS system identification based on QR factorization via Givens rotations is proposed. The back-substitution step is circumvented, and the structure is fully pipelineable. Thus, the method is appropriate for continuous, sample-by-sample mode, adaptive operation. A modification of this structure is also suggested which is suitable for a wide range of linear algebraic operations and is solely based on Givens rotations. >

Sergios Theodoridis | Angelos P. Varvitsiotis

[1] Fuyun Ling,et al. A recursive modified Gram-Schmidt algorithm for least- squares estimation , 1986, IEEE Trans. Acoust. Speech Signal Process..

[2] S. Haykin,et al. Adaptive Filter Theory , 1986 .

[3] George Carayannis,et al. Efficient recursive in order least squares FIR filtering and prediction , 1985, IEEE Trans. Acoust. Speech Signal Process..

[4] J. Greg Nash,et al. Modified Faddeeva Algorithm for Concurrent Execution of Linear Algebraic Operations , 1988, IEEE Trans. Computers.

[5] George Carayannis,et al. A fast sequential algorithm for least-squares filtering and prediction , 1983 .

[6] John M. Cioffi,et al. High-speed systolic implementation of fast QR adaptive filters , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[7] J. G. McWhirter,et al. Systolic array for recursive least-squares minimisation , 1983 .