Abstract | ||
---|---|---|
In this letter, a stable and orthonormal version of the OJA algorithm (SOOJA) is investigated for principal and minor subspace extraction and tracking. The new algorithm presented here guarantees the orthonormality of the weight matrix at each iteration through a novel orthonormalization method. Moreover, it obtains both a high numerical stability and a low computational complexity. The superiority of the proposed algorithm to some existing subspace tracking algorithms is demonstrated using a classical example. Simulation results confirm the veracity of the subspace tracking algorithm advocated. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/LSP.2011.2108999 | IEEE Signal Process. Lett. |
Keywords | Field | DocType |
subspace tracking algorithm,oja algorithm,weight matrix,orthonormalization method,numerical stability,orthonormal oja algorithm,tracking,singular value decomposition,subspace tracking,subspace extraction,algorithm design,matrices,computational complexity,data mining,signal processing,indexing terms,algorithm design and analysis | Singular value decomposition,Mathematical optimization,Algorithm design,Orthonormality,Subspace topology,Oja's rule,Algorithm,Orthonormal basis,Numerical stability,Mathematics,Computational complexity theory | Journal |
Volume | Issue | ISSN |
18 | 4 | 1070-9908 |
Citations | PageRank | References |
2 | 0.37 | 12 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rong Wang | 1 | 10 | 1.16 |
Minli Yao | 2 | 222 | 17.30 |
Daoming Zhang | 3 | 33 | 3.46 |
Hongxing Zou | 4 | 139 | 13.17 |