In this paper we introduce an modifiedclippedlms (MClms) algorithm with a variable step size. In the MClmsalgorithm two parameters, the step size and the threshold control the convergence rate of the adaptive filte...
详细信息
ISBN:
(纸本)9781467365062
In this paper we introduce an modifiedclippedlms (MClms) algorithm with a variable step size. In the MClmsalgorithm two parameters, the step size and the threshold control the convergence rate of the adaptive filter coefficients and also determine the final mean-square error. The computational complexity decreased dramatically by a large threshold. However, this selection results in a low convergence rate. Since the convergence time is inversely proportional to the step size, a large step size is often selected for fast convergence. But a large step size results in an increased final mean square error. Therefore in this paper we choose a large threshold and propose a variable step size for the MClmsalgorithm. The advantages of this proposed variable step size and a large threshold selection are that the computation complexity is low, final mean square error is low and that the convergence is fast.
暂无评论