2018
DOI: 10.1109/lsp.2018.2847559
|View full text |Cite
|
Sign up to set email alerts
|

Bayesian Information Criterion for Signed Measurements With Application to Sinusoidal Signals

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
15
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
6
1

Relationship

2
5

Authors

Journals

citations
Cited by 21 publications
(15 citation statements)
references
References 21 publications
0
15
0
Order By: Relevance
“…To determine the number of sinusoids, i.e., the model order K, from signed measurements, we will use the one-bit Bayesian information criterion (1bBIC) with 1bMMRELAX. Suppose that β K is the vector of parameter estimates obtained by the 1bMMRELAX algorithm for an assumed model order K; then the 1bBIC cost function is given by [54]:…”
Section: Determining the Number Of Sinusoidsmentioning
confidence: 99%
See 1 more Smart Citation
“…To determine the number of sinusoids, i.e., the model order K, from signed measurements, we will use the one-bit Bayesian information criterion (1bBIC) with 1bMMRELAX. Suppose that β K is the vector of parameter estimates obtained by the 1bMMRELAX algorithm for an assumed model order K; then the 1bBIC cost function is given by [54]:…”
Section: Determining the Number Of Sinusoidsmentioning
confidence: 99%
“…3) For the case that the number of sinusoids, i.e., the model order, is unknown, we explain how the proposed algorithm can be used with the one-bit Bayesian information criterion (1bBIC) [54] to simultaneously estimate the sinusoidal parameters and determine the number of sinusoids.…”
Section: Introductionmentioning
confidence: 99%
“…For the case that the number of RFI sources, i.e., the true model order K, is unknown, we consider extending the single-PRI based one-bit Bayesian information criterion (1bBIC) in [21] to the multiple-PRI based cases so that the extended 1bBIC can be used with the extended 1bMMRELAX to determine the RFI model order. Suppose that β K is parameter vector estimated by the extended 1bMMRELAX algorithm for an assumed model order K, where 1 ≤ K ≤ K max .…”
Section: Bbicmentioning
confidence: 99%
“…Under mild conditions (see, e.g., [21], [34] and the references therein), the matrix Ĵ(Y, β) has the following asymptotic relationship with the Fisher information matrix (FIM) J for the parameter vector β [21]:…”
Section: Appendix a Derivation Of 1bbic For Multiple-pri Based Signed...mentioning
confidence: 99%
See 1 more Smart Citation