Fast algorithms for subspace tracking

被引:55
作者
Attallah, S
Abed-Meraim, K
机构
[1] Natl Univ Singapore, Ctr Wireless Commun, Singapore 117674, Singapore
[2] Telecom Paris, TSI Dept, Paris 13, France
关键词
numerical stability; normalized Oja; Oja's algorithm; orthogonal Oja; subspace estimation;
D O I
10.1109/97.928678
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
In this letter, we present two normalized versions of Oja's algorithm (NOja and NOOja), which can be used for the estimation of minor and principal subspaces of a vector sequence. The new algorithms offer, as compared to Oja, a faster convergence, orthogonality, and a better numerical stability with a slight increase in computational complexity.
引用
收藏
页码:203 / 206
页数:4
相关论文
共 9 条