PROJECT TITLE :
On Convergence of Proportionate-Type Normalized Least Mean Square Algorithms
During this paper, a new convergence analysis is presented for a widely known sparse adaptive filter family, particularly, the proportionate-kind normalized least mean square (PtNLMS) algorithms, where, in contrast to all the present approaches, no assumption of whiteness is made on the input. The analysis depends on a “rework” domain based model of the PtNLMS algorithms and brings out certain new convergence options not reported earlier. In particular, it establishes the universality of the steady-state excess mean sq. error formula derived earlier beneath white input assumption. In addition, it brings out a replacement relation between the mean square deviation of every faucet weight and the corresponding gain factor employed in the PtNLMS algorithm.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here