Reliability Checks on the Indo-US Stellar Spectral Library Using Artificial Neural Networks and Principal Component Analysis
| Autor: | Nawo Yamamoto, Manabu Yuasa, Ranjan Gupta, Harinder P. Singh |
|---|---|
| Rok vydání: | 2006 |
| Předmět: |
Physics
Artificial neural network business.industry Astrophysics (astro-ph) FOS: Physical sciences Astronomy and Astrophysics Pattern recognition Astrophysics Missing data Stellar classification methods: data analysis Spectral line Data set Stars Space and Planetary Science Principal component analysis Astrophysics::Solar and Stellar Astrophysics Artificial intelligence business stars: general catalogs Curse of dimensionality |
| Zdroj: | Publications of the Astronomical Society of Japan. 58:177-186 |
| ISSN: | 2053-051X 0004-6264 |
| DOI: | 10.1093/pasj/58.1.177 |
| Popis: | The Indo-US coud\'{e} feed stellar spectral library (CFLIB) made available to the astronomical community recently by Valdes et al. (2004) contains spectra of 1273 stars in the spectral region 3460 to 9464 \AA at a high resolution of 1 \AA FWHM and a wide range of spectral types. Cross-checking the reliability of this database is an important and desirable exercise since a number of stars in this database have no known spectral types and a considerable fraction of stars has not so complete coverage in the full wavelength region of 3460-9464 \AA resulting in gaps ranging from a few \AA to several tens of \AA. In this paper, we use an automated classification scheme based on Artificial Neural Networks (ANN) to classify all 1273 stars in the database. In addition, principal component analysis (PCA) is carried out to reduce the dimensionality of the data set before the spectra are classified by the ANN. Most importantly, we have successfully demonstrated employment of a variation of the PCA technique to restore the missing data in a sample of 300 stars out of the CFLIB. Comment: 17 pages, 8 figures PASJ Vol.58, No1 (it will be issued on February 25, 2006) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|