Title :
A finite wordlength analysis of an LMS-Newton adaptive filtering algorithm
Author :
De Campos, Marcello L R ; Diniz, Paulo S R ; Antoniou, Athanasios
Author_Institution :
Dept. of Electr. & Comput. Eng., Victoria Univ., BC, Canada
Abstract :
The effects of quantization in an least-mean-square (LMS)-Newton adaptive filtering algorithm are investigated. The algorithm considered uses an optimum convergence factor that forces the output a posteriori error to become zero in each iteration. The propagation of errors due to quantization in the internal variables of the algorithm is investigated, and a closed-form formula for the excess mean square error due to quantization is derived. Fixed-point arithmetic is assumed throughout. Several simulations confirm the accuracy of the formulas presented
Keywords :
Newton method; adaptive filters; convergence; digital arithmetic; filtering theory; least mean squares methods; quantisation (signal); roundoff errors; LMS-Newton adaptive filtering algorithm; closed-form formula; error propagation; excess mean square error; finite wordlength analysis; optimum convergence factor; quantization; Adaptive filters; Algorithm design and analysis; Convergence; Equations; Filtering algorithms; Fixed-point arithmetic; Mean square error methods; Noise measurement; Quantization; Working environment noise;
Conference_Titel :
Circuits and Systems, 1993., ISCAS '93, 1993 IEEE International Symposium on
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-1281-3
DOI :
10.1109/ISCAS.1993.393862
