Library · IAA RAS

Papers

Principal Component Analysis and Applications

Transactions of IAA RAS, issue 22, 31–41 (2011)

Keywords: Extraterrestrial civilization, SETI, astrobiology, algorithm Lanczos

Abstract

Principal Component Analysis (PCA) is a powerful tool of factorial analysis. It can be used to classified objects, to reduce the size of a database and extract information from a noisy situation. This paper will briefly introduce the PCA and present applications related to astrobiology and SETI. It will also discuss how to use the algorithm Lanczos to compute eigenvalues of huge matrices (N=1,000,000)

Citation

Text

BibTeX

RIS

S. Dumas. Principal Component Analysis and Applications // Transactions of IAA RAS. — 2011. — Issue 22. — P. 31–41.

@article{dumas2011,
  abstract = {Principal Component Analysis (PCA) is a powerful tool of factorial analysis. It can be used to classified objects, to reduce the size of a database and extract information from a noisy situation. This paper will briefly introduce the PCA and present applications related to astrobiology and SETI. It will also discuss how to use the algorithm Lanczos to compute eigenvalues of huge matrices (N=1,000,000)},
  author = {S. Dumas},
  issue = {22},
  journal = {Transactions of IAA RAS},
  keyword = {Extraterrestrial civilization, SETI, astrobiology, algorithm Lanczos},
  pages = {31--41},
  title = {Principal Component Analysis and Applications},
  url = {http://iaaras.ru/en/library/paper/740/},
  year = {2011}
}

TY  - JOUR
TI  - Principal Component Analysis and Applications
AU  - Dumas, S.
PY  - 2011
T2  - Transactions of IAA RAS
IS  - 22
SP  - 31
AB  - Principal Component Analysis (PCA) is a powerful tool of factorial
analysis. It can be used to classified objects, to reduce the size of
a database and extract information from a noisy situation. This paper
will briefly introduce the PCA and present applications related to
astrobiology and SETI. It will also discuss how to use the algorithm
Lanczos to compute eigenvalues of huge matrices (N=1,000,000)
UR  - http://iaaras.ru/en/library/paper/740/
ER  -