ANALYSIS OF LMS ALGORITHM WITH INPUTS FROM CYCLOSTATIONARY RANDOM-PROCESSES

被引：23
作者：
MCLERNON, DC
机构：
[1] Department of Electrical and Electronic Engineering, South Bank Polytechnic, London SE1 OAA
来源：
ELECTRONICS LETTERS | 1991年 / 27卷 / 02期
关键词：
ALGORITHMS;
D O I：
10.1049/el:19910089
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
The least mean square (LMS) algorithm is investigated for inputs from nonstationary random processes having periodic (period P) statistics. By defining P different coefficient vectors, each vector can be shown to 'coverage in the mean' to a biased solution which is dependent upon the algorithm step size mu.
引用
收藏
页码：136 / 138
页数：3
相关论文
共 7 条
[1]   STATISTICS OF REGENERATIVE DIGITAL TRANSMISSION [J].
BENNETT, WR .
BELL SYSTEM TECHNICAL JOURNAL, 1958, 37 (06) :1501-1542
[2]   CHARACTERIZATION OF CYCLOSTATIONARY RANDOM SIGNAL PROCESSES [J].
GARDNER, WA ;
FRANKS, LE .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1975, 21 (01) :4-14
[3]  
HASSELMANN K, 1981, J ATMOS SCI, V38, P2275, DOI 10.1175/1520-0469(1981)038<2275:TOLPFS>2.0.CO
[4]  
2
[5]   ON THE STATISTICAL EFFICIENCY OF THE LMS ALGORITHM WITH NONSTATIONARY INPUTS [J].
WIDROW, B ;
WALACH, E .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1984, 30 (02) :211-221
[6]   STATIONARY AND NONSTATIONARY LEARNING CHARACTERISTICS OF LMS ADAPTIVE FILTER [J].
WIDROW, B ;
MCCOOL, JM ;
LARIMORE, MG ;
JOHNSON, CR .
PROCEEDINGS OF THE IEEE, 1976, 64 (08) :1151-1162
[7]  
WIDROW B, 1960, IRE WESCON CONV RE 4, P96
1