1982
DOI: 10.1109/tassp.1982.1163927
|View full text |Cite
|
Sign up to set email alerts
|

Singular value decomposition and improved frequency estimation using linear prediction

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
81
0

Year Published

1987
1987
2015
2015

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 210 publications
(81 citation statements)
references
References 14 publications
0
81
0
Order By: Relevance
“…Various researchers have suggested analytical methods to estimate model order [33,[42][43][44]. Akaike [42] has suggested a final prediction error method and a cost minimization method in which a cost is assigned for extra coefficients which do not reduce model order.…”
Section: Prony's Methodsmentioning
confidence: 99%
“…Various researchers have suggested analytical methods to estimate model order [33,[42][43][44]. Akaike [42] has suggested a final prediction error method and a cost minimization method in which a cost is assigned for extra coefficients which do not reduce model order.…”
Section: Prony's Methodsmentioning
confidence: 99%
“…Results are compared with the Koopman algorithm reported in [10] and a multisignal Prony method [20], based on the Kumaresan-Tuft approach [21] and the OMIB model in Fig. 12.…”
Section: Computational Effortmentioning
confidence: 99%
“…Frequency estimation of multiple complex sinusoids based on the SVD is described [9], [10]. The resultant estimates are used as the initial state variables in the NMSE, which have a good accuracy when frequency of each sinusoid is time-invariant.…”
Section: Initial Estimation For the Nmsementioning
confidence: 99%
“…Fortunately, the stability (convergence) of the NMSE is also theoretically clarified [8]. Also, the singular value decomposition (SVD) [9], [10] is effectively combined with the ECKF as the initial state estimation. In this paper, the NMSE is efficiently specialized to harmonic estimation so that its computational complexity is adequately reduced.…”
Section: Introductionmentioning
confidence: 99%