TY - JOUR
T1 - An improved sequential method for principal component analysis
AU - Wang, Ze
AU - Lee, Yin
AU - Fiori, Simone
AU - Leung, Chi-Sing
AU - Zhu, Yi-Sheng
PY - 2003/6
Y1 - 2003/6
N2 - In sequential principal component (PC) extraction, when increasing numbers of PCs are extracted the accumulated extraction error becomes dominant and makes a reliable extraction of the remaining PCs difficult. This paper presents an improved cascade recursive least squares method for PCs' extraction. The good features of the proposed approach are illustrated through simulation results, and include improved convergence speed and higher extraction accuracy. © 2002 Elsevier Science B.V. All rights reserved.
AB - In sequential principal component (PC) extraction, when increasing numbers of PCs are extracted the accumulated extraction error becomes dominant and makes a reliable extraction of the remaining PCs difficult. This paper presents an improved cascade recursive least squares method for PCs' extraction. The good features of the proposed approach are illustrated through simulation results, and include improved convergence speed and higher extraction accuracy. © 2002 Elsevier Science B.V. All rights reserved.
KW - Cascade recursive least squares (CRLS)
KW - Principal component analysis
KW - Vector orthogonalization by subspace deflation
UR - http://www.scopus.com/inward/record.url?scp=0037410764&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0037410764&origin=recordpage
U2 - 10.1016/S0167-8655(02)00381-1
DO - 10.1016/S0167-8655(02)00381-1
M3 - RGC 21 - Publication in refereed journal
SN - 0167-8655
VL - 24
SP - 1409
EP - 1415
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
IS - 9-10
ER -