Parameter optimization in the regularized kernel minimum noise fraction transformation

Allan Aasbjerg Nielsen; Jacob Schack Vestergaard

doi:10.1109/IGARSS.2012.6351561

Parameter optimization in the regularized kernel minimum noise fraction transformation

Allan Aasbjerg Nielsen (Invited author), Jacob Schack Vestergaard (Invited author)

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

1 Downloads (Pure)

Abstract

Based on the original, linear minimum noise fraction (MNF) transformation and kernel principal component analysis, a kernel version of the MNF transformation was recently introduced. Inspired by we here give a simple method for finding optimal parameters in a regularized version of kernel MNF analysis. We consider the model signal-to-noise ratio (SNR) as a function of the kernel parameters and the regularization parameter. In 2-4 steps of increasingly refined grid searches we find the parameters that maximize the model SNR. An example based on data from the DLR 3K camera system is given.

Original language	English
Title of host publication	IEEE International Geoscience and Remote Sensing Symposium proceedings
Publisher	IEEE
Publication date	2012
Pages	370-373
ISBN (Print)	978-1-4673-1160-1
ISBN (Electronic)	978-1-4673-1158-8
DOIs	https://doi.org/10.1109/IGARSS.2012.6351561
Publication status	Published - 2012
Event	2012 IEEE International Geoscience and Remote Sensing Symposium: Remote Sensing for a Dynamic Earth - Munich, Germany Duration: 22 Jul 2012 → 27 Jul 2012 https://ieeexplore.ieee.org/xpl/conhome/6334512/proceeding

Conference

Conference	2012 IEEE International Geoscience and Remote Sensing Symposium
Country/Territory	Germany
City	Munich
Period	22/07/2012 → 27/07/2012
Internet address	https://ieeexplore.ieee.org/xpl/conhome/6334512/proceeding

Series	IEEE International Geoscience and Remote Sensing Symposium
ISSN	2153-6996

Access to Document

10.1109/IGARSS.2012.6351561

OpenUrl availability

Full text

Cite this

@inproceedings{f3d0297fc3c7474a829197f8e3e97d52,

title = "Parameter optimization in the regularized kernel minimum noise fraction transformation",

abstract = "Based on the original, linear minimum noise fraction (MNF) transformation and kernel principal component analysis, a kernel version of the MNF transformation was recently introduced. Inspired by we here give a simple method for finding optimal parameters in a regularized version of kernel MNF analysis. We consider the model signal-to-noise ratio (SNR) as a function of the kernel parameters and the regularization parameter. In 2-4 steps of increasingly refined grid searches we find the parameters that maximize the model SNR. An example based on data from the DLR 3K camera system is given.",

author = "Nielsen, {Allan Aasbjerg} and Vestergaard, {Jacob Schack}",

year = "2012",

doi = "10.1109/IGARSS.2012.6351561",

language = "English",

isbn = "978-1-4673-1160-1",

series = "IEEE International Geoscience and Remote Sensing Symposium",

pages = "370--373",

booktitle = "IEEE International Geoscience and Remote Sensing Symposium proceedings",

publisher = "IEEE",

address = "United States",

note = "2012 IEEE International Geoscience and Remote Sensing Symposium : Remote Sensing for a Dynamic Earth, IGARSS 2012 ; Conference date: 22-07-2012 Through 27-07-2012",

url = "https://ieeexplore.ieee.org/xpl/conhome/6334512/proceeding",

}

Nielsen, AA & Vestergaard, JS 2012, Parameter optimization in the regularized kernel minimum noise fraction transformation. in IEEE International Geoscience and Remote Sensing Symposium proceedings. IEEE, IEEE International Geoscience and Remote Sensing Symposium, pp. 370-373, 2012 IEEE International Geoscience and Remote Sensing Symposium, Munich, Bavaria, Germany, 22/07/2012. https://doi.org/10.1109/IGARSS.2012.6351561

Parameter optimization in the regularized kernel minimum noise fraction transformation. / Nielsen, Allan Aasbjerg (Invited author); Vestergaard, Jacob Schack (Invited author).
IEEE International Geoscience and Remote Sensing Symposium proceedings. IEEE, 2012. p. 370-373 (IEEE International Geoscience and Remote Sensing Symposium).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Parameter optimization in the regularized kernel minimum noise fraction transformation

AU - Nielsen, Allan Aasbjerg

AU - Vestergaard, Jacob Schack

PY - 2012

Y1 - 2012

N2 - Based on the original, linear minimum noise fraction (MNF) transformation and kernel principal component analysis, a kernel version of the MNF transformation was recently introduced. Inspired by we here give a simple method for finding optimal parameters in a regularized version of kernel MNF analysis. We consider the model signal-to-noise ratio (SNR) as a function of the kernel parameters and the regularization parameter. In 2-4 steps of increasingly refined grid searches we find the parameters that maximize the model SNR. An example based on data from the DLR 3K camera system is given.

AB - Based on the original, linear minimum noise fraction (MNF) transformation and kernel principal component analysis, a kernel version of the MNF transformation was recently introduced. Inspired by we here give a simple method for finding optimal parameters in a regularized version of kernel MNF analysis. We consider the model signal-to-noise ratio (SNR) as a function of the kernel parameters and the regularization parameter. In 2-4 steps of increasingly refined grid searches we find the parameters that maximize the model SNR. An example based on data from the DLR 3K camera system is given.

U2 - 10.1109/IGARSS.2012.6351561

DO - 10.1109/IGARSS.2012.6351561

M3 - Article in proceedings

SN - 978-1-4673-1160-1

T3 - IEEE International Geoscience and Remote Sensing Symposium

SP - 370

EP - 373

BT - IEEE International Geoscience and Remote Sensing Symposium proceedings

PB - IEEE

T2 - 2012 IEEE International Geoscience and Remote Sensing Symposium

Y2 - 22 July 2012 through 27 July 2012

ER -

Parameter optimization in the regularized kernel minimum noise fraction transformation

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this