Title :
Orthogonal Oja algorithm
Author :
Abed-Meraim, K. ; Attallah, S. ; Chkeif, A. ; Hua, Y.
Author_Institution :
Telecom Paris, France
fDate :
5/1/2000 12:00:00 AM
Abstract :
In this letter, we propose an orthogonalized version of the Oja algorithm (OOja) that can be used for the estimation of minor and principal subspaces of a vector sequence. The new algorithm offers, as compared to Oja, such advantages as orthogonality of the weight matrix, which is ensured at each iteration, numerical stability, and a quite similar computational complexity.
Keywords :
computational complexity; covariance matrices; iterative methods; numerical stability; principal component analysis; signal processing; vectors; Householder transform; computational complexity; covariance matrix; iteration; minor subspace estimation; numerical stability; orthogonal Oja algorithm; principal subspace estimation; vector sequence; weight matrix orthogonality; Computational complexity; Covariance matrix; Data mining; Equations; Information analysis; Information processing; Matrices; Numerical stability; Principal component analysis; Telecommunications;
Journal_Title :
Signal Processing Letters, IEEE
