Variable step size modified clipped LMS algorithm
سال انتشار: 1394
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 667
فایل این مقاله در 5 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
KBEI02_292
تاریخ نمایه سازی: 5 بهمن 1395
چکیده مقاله:
In this paper we introduce an Modified Clipped LMS (MCLMS) algorithm with a variable step size. In the MCLMS algorithm 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 MCLMS algorithm. 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.
کلیدواژه ها:
adaptive filter ، LMS algorithm ، modified clipped LMS algorithm ، variable step size ، convergence rate
نویسندگان
Amin Aref
Department of Electrical and Computer Eng. Shahrood University Shahrood, Iran
Mojtaba Lotfizad
Department of Electrical and Computer Eng. Tarbiat Modares University Tehran, Iran