Adaptive filter theory
Square Hankel SVD subspace tracking algorithms
Signal Processing
Linear Prediction Theory: A Mathematical Basis for Adaptive Systems
Linear Prediction Theory: A Mathematical Basis for Adaptive Systems
Projection approximation subspace tracking
IEEE Transactions on Signal Processing
Bi-iterative least-square method for subspace tracking
IEEE Transactions on Signal Processing - Part II
Bi-iteration SVD subspace tracking algorithms
IEEE Transactions on Signal Processing
Equirotational stack parameterization in subspace estimation andtracking
IEEE Transactions on Signal Processing
Fast recursive subspace adaptive ESPRIT algorithms
IEEE Transactions on Signal Processing
Bi-iteration recursive instrumental variable subspace tracking andadaptive filtering
IEEE Transactions on Signal Processing
Bi-iteration multiple invariance subspace tracking and adaptiveESPRIT
IEEE Transactions on Signal Processing
Fast orthogonal iteration adaptive algorithms for the generalizedsymmetric eigenproblem
IEEE Transactions on Signal Processing
Total least squares phased averaging and 3-D ESPRIT for jointazimuth-elevation-carrier estimation
IEEE Transactions on Signal Processing
Fast approximated power iteration subspace tracking
IEEE Transactions on Signal Processing - Part I
IEEE Transactions on Signal Processing
The QS-householder sliding window Bi-SVD subspace tracker
IEEE Transactions on Signal Processing
Data stream anomaly detection through principal subspace tracking
Proceedings of the 2010 ACM Symposium on Applied Computing
Rethinking concepts of the dendritic cell algorithm for multiple data stream analysis
ICARIS'12 Proceedings of the 11th international conference on Artificial Immune Systems
| Hi-index | 0.09 |
We introduce a new sequential algorithm for tracking the principal subspace and, optionally, the r dominant eigenvalues and associated eigenvectors of an exponentially updated covariance matrix of dimension NxN, where Nr. The method is based on an updated orthonormal-square (QS) decomposition using the row-Householder reduction. This new subspace tracker reaches a dominant complexity of only 3Nr multiplications per time update for tracking the principal subspace, which is the lower bound in dominant complexity for an algorithm of this kind. The new method is completely reflection based. An updating of inverse matrices is not used.