Classification of Jacoby stellar spectra data using data modeling

Holger M. Jaenisch; Miroslav D. Filipovic

doi:10.1117/12.451527

Classification of Jacoby stellar spectra data using data modeling

Holger M. Jaenisch
, Miroslav D. Filipovic

School of Science

Research output: Contribution to journal › Conference article › peer-review

5 Citations (Scopus)

Abstract

This paper presents the results of creating a Data Model by using neural equation networks of high order polynomials to achieve 100% correct classification of the Jacoby stellar spectra. The Jacoby set is a challenging group of 161 spectra spanning the full range of temperature, sub-temperature and luminosity groupings of standard star types. To achieve full learning, the development of a cascaded decision architecture linking an extensive network of polynomial decision equations was required. The two dominant features were extracted, and complex decision maps generated. Also, the sensitivity of the equation architecture to misclassification due to measurement noise was analyzed.

Original language	English
Pages (from-to)	296-307
Number of pages	12
Journal	Proceedings of SPIE: The International Society for Optical Engineering
Volume	4816
DOIs	https://doi.org/10.1117/12.451527
Publication status	Published - 2002
Event	Imaging Spectrometry VII - Seattle, WA, United States Duration: 8 Jul 2002 → 10 Jul 2002

Keywords

Astronomy
Data modeling
Decision Architecture
Neural network
Stellar spectra classification

Access to Document

10.1117/12.451527

Cite this

@article{c5b540368e40434db67a9df928174a8b,

title = "Classification of Jacoby stellar spectra data using data modeling",

abstract = "This paper presents the results of creating a Data Model by using neural equation networks of high order polynomials to achieve 100\% correct classification of the Jacoby stellar spectra. The Jacoby set is a challenging group of 161 spectra spanning the full range of temperature, sub-temperature and luminosity groupings of standard star types. To achieve full learning, the development of a cascaded decision architecture linking an extensive network of polynomial decision equations was required. The two dominant features were extracted, and complex decision maps generated. Also, the sensitivity of the equation architecture to misclassification due to measurement noise was analyzed.",

keywords = "Astronomy, Data modeling, Decision Architecture, Neural network, Stellar spectra classification",

author = "Jaenisch, \{Holger M.\} and Filipovic, \{Miroslav D.\}",

year = "2002",

doi = "10.1117/12.451527",

language = "English",

volume = "4816",

pages = "296--307",

journal = "Proceedings of SPIE: The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "Imaging Spectrometry VII ; Conference date: 08-07-2002 Through 10-07-2002",

}

TY - JOUR

T1 - Classification of Jacoby stellar spectra data using data modeling

AU - Jaenisch, Holger M.

AU - Filipovic, Miroslav D.

PY - 2002

Y1 - 2002

N2 - This paper presents the results of creating a Data Model by using neural equation networks of high order polynomials to achieve 100% correct classification of the Jacoby stellar spectra. The Jacoby set is a challenging group of 161 spectra spanning the full range of temperature, sub-temperature and luminosity groupings of standard star types. To achieve full learning, the development of a cascaded decision architecture linking an extensive network of polynomial decision equations was required. The two dominant features were extracted, and complex decision maps generated. Also, the sensitivity of the equation architecture to misclassification due to measurement noise was analyzed.

AB - This paper presents the results of creating a Data Model by using neural equation networks of high order polynomials to achieve 100% correct classification of the Jacoby stellar spectra. The Jacoby set is a challenging group of 161 spectra spanning the full range of temperature, sub-temperature and luminosity groupings of standard star types. To achieve full learning, the development of a cascaded decision architecture linking an extensive network of polynomial decision equations was required. The two dominant features were extracted, and complex decision maps generated. Also, the sensitivity of the equation architecture to misclassification due to measurement noise was analyzed.

KW - Astronomy

KW - Data modeling

KW - Decision Architecture

KW - Neural network

KW - Stellar spectra classification

UR - https://www.scopus.com/pages/publications/0036986949

U2 - 10.1117/12.451527

DO - 10.1117/12.451527

M3 - Conference article

AN - SCOPUS:0036986949

SN - 0277-786X

VL - 4816

SP - 296

EP - 307

JO - Proceedings of SPIE: The International Society for Optical Engineering

JF - Proceedings of SPIE: The International Society for Optical Engineering

T2 - Imaging Spectrometry VII

Y2 - 8 July 2002 through 10 July 2002

ER -

Classification of Jacoby stellar spectra data using data modeling

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this