2014 IEEE 8th Sensor Array and Multichannel Signal Processing Workshop (SAM) 2014
DOI: 10.1109/sam.2014.6882359
|View full text |Cite
|
Sign up to set email alerts
|

Gaussian processes regressors for complex proper signals in digital communications

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
9
0

Year Published

2015
2015
2019
2019

Publication Types

Select...
3
2

Relationship

1
4

Authors

Journals

citations
Cited by 7 publications
(9 citation statements)
references
References 8 publications
0
9
0
Order By: Relevance
“…4) Proper case with k rj (x , x) = 0: This scenario arises when K jr is skew-symmetric. The kernel functions in (24) and (26) could be used in this case. However, the first one involves some quite particular similarity properties with exponential growth for some pair of points.…”
Section: B Convolution Approachmentioning
confidence: 99%
See 2 more Smart Citations
“…4) Proper case with k rj (x , x) = 0: This scenario arises when K jr is skew-symmetric. The kernel functions in (24) and (26) could be used in this case. However, the first one involves some quite particular similarity properties with exponential growth for some pair of points.…”
Section: B Convolution Approachmentioning
confidence: 99%
“…The covariance matrix of the GPR plays the role of the kernel. In [24] we developed complex-valued GPR for proper systems. A proper complex random signal is uncorrelated with its complex conjugate [25], and hence the pseudo-covariance cancels.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…for id ∈ {rr, ii, ri}, where A id n is the noise variance and the magnitudes Arr, Aii, Ari are parametrised according to (11). The periodic kernel has been readily validated in long-term forecasting of periodic signals [17].…”
Section: A Complex Gaussian Process Model For Climate Datamentioning
confidence: 99%
“…filters [8,9,10], combine the output of complex-valued neurons and kernels in a widely-linear fashion to yield accurate estimates, yet they fail to provide a probabilistic description of the processes, this is a consistent requirement when assuming a specific statistical setting (second order) for the signals at hand. This issue has been partially solved using Gaussian processes (GP) [11], although only for circular signals. In this sense, a probabilistic model for complex signals suitable for both circular and noncircular cases is still lacking in the open literature.…”
Section: Introductionmentioning
confidence: 99%