Title :
LSMI Algorithm Based on Inverse QR Decomposition
Author :
Jian-shu, Cao ; Xue-gang, Wang
Author_Institution :
Coll. of Electron. Eng., Univ. of Electron. Sci. & Technol. of China, Chengdu
Abstract :
Diagonal loaded sample-matrix inversion (LSMI) algorithm requires a high computational complexity. Thus, a new computationally efficient implementation for LSMI algorithm is presented, which is based on an inverse QR decomposition. The new method inserts the diagonal loading by only setting initial inverse Cholesky factor. It can offer good numerical properties and support parallel implementation with VLSI while avoiding backsubstitution operations. Hence, the new method can be applied for real-time signal processing. Simulations support the new algorithm
Keywords :
VLSI; computational complexity; matrix decomposition; matrix inversion; signal processing; Cholesky factor; LSMI algorithm; VLSI; computational complexity; diagonal loaded sample-matrix inversion; inverse QR decomposition; parallel implementation; real-time signal processing; Array signal processing; Computational complexity; Covariance matrix; Educational institutions; Matrices; Matrix decomposition; Maximum likelihood estimation; Robustness; Signal processing algorithms; Very large scale integration;
Conference_Titel :
Communications, Circuits and Systems Proceedings, 2006 International Conference on
Conference_Location :
Guilin
Print_ISBN :
0-7803-9584-0
Electronic_ISBN :
0-7803-9585-9
DOI :
10.1109/ICCCAS.2006.284631
