Title :
Convergence properties of the block orthogonal projection algorithm
Author :
Ikeda, Kazushi ; Sakai, Hideaki
Author_Institution :
Graduate Sch. of Inf., Kyoto Univ., Japan
Abstract :
The normalized LMS (N-LMS) algorithm has a disadvantage that the convergence rate is much worse when the input signal is colored. To overcome this, the affine projection algorithm and the block orthogonal projection (BOP) algorithm which applied the block signal processing technique to the N-LMS algorithm are proposed although the reason why they are tough against the colored signal is not given yet. This paper gives the convergence rate of the BOP algorithm for colored input signals, which shows the superiority of the BOP algorithm. To put it concretely, we derive the expression of the convergence rate, propose an approximation method to calculate it, and confirm the result by computer simulations. We also consider the relation between the block size and the convergence rate formally and geometrically
Keywords :
convergence of numerical methods; least mean squares methods; signal processing; BOP algorithm; NLMS algorithm; affine projection algorithm; approximation method; block orthogonal projection algorithm; block signal processing; block size; colored input signals; computer simulations; convergence properties; convergence rate; formal view; geometrical view; normalized LMS algorithm; Adaptive algorithm; Algorithm design and analysis; Computer simulation; Convergence; Informatics; Least squares approximation; Projection algorithms; Signal processing algorithms; Stability;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on
Conference_Location :
Phoenix, AZ
Print_ISBN :
0-7803-5041-3
DOI :
10.1109/ICASSP.1999.756312