Search

Abstract: Selective partial update of the adaptive filter coefficients has been a popular method for reducing the computational complexity of least mean-square (LMS)-type adaptive algorithms. These algorithms use a fixed step-size that forces a performance compromise between fast convergence speed and small steady state misadjustment. This paper proposes a variable step-size (VSS) selective partial update LMS algorithm, where the VSS is an approximation of an optimal derived one. The VSS equations are controlled by only one parameter, and do not require any a priori information about the statistics of the system environment. Mean-square performance analysis will be provided for independent and identically distributed (i.i.d.) input signals, and an expression for the algorithm steady state excess mean-square error (MSE) will be presented. Simulation experiments are conducted to compare the proposed algorithm with existing full-update VSS LMS algorithms, which indicate that the proposed algorithm performs as well as these algorithms while requiring less computational complexity. [Copyright &y& Elsevier]

Abstract: The dithered signed-error constant modulus algorithm (DSE-CMA) is an approach less computationally than CMA but exhibits ill-convergence. On the contrary, the concurrent CMA with soft decision-directed scheme () improves the convergence rate of CMA by adding SDD but brings lots of computational complexity. As a tradeoff, in this paper we combine the virtues of DSE-CMA and SDD, then propose a new algorithm, which compensates the phase shift and provides convergence faster than DSE-CMA with lower complexity than . More importantly, an approximation of its steady-state mean square error performance is derived. Simulation results show the superiority of the proposed algorithm. [Copyright &y& Elsevier]

Abstract: In this paper, we propose a new time-varying step-size for the affine projection (AP) algorithm based on the minimization of the mean-square error (MSE) at each time instant. The step-size is dependent on accessible quantities and, therefore, does not need approximation. In addition, we show how the new step-size control equations can be incorporated into the fast AP (FAP) algorithm leading to a reduced complexity implementation of the proposed algorithm. The algorithm improved performance characteristics are verified by simulation experiments. [Copyright &y& Elsevier]