Análisis y clasificación de firmas espectrales utilizando técnicas de aprendizaje automático.

The study of spectral signatures makes it possible to identify different objects of earth and sky, present in digital images. The elements that are in it make it have a particular feature, it is analogous to a fingerprint. Researcher’s study its spectral signature, which is made up of the physical,...

ver descrição completa

Detalhes bibliográficos
Autor: ANA PATRICIA
Tipo de documento: dissertação
Estado:Versión aceptada para publicación
Data de publicação:2019
País:México
Recursos:Instituto Nacional de Astrofísica, Óptica y Electrónica
Repositório:Repositorio Institucional del INAOE
Idioma:espanhol
OAI Identifier:oai:inaoe.repositorioinstitucional.mx:1009/1677
Acesso em linha:http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/1677
Access Level:Acceso aberto
Palavra-chave:info:eu-repo/classification/Técnicas/Techniques
info:eu-repo/classification/Aprendizaje/Learning
info:eu-repo/classification/Automático/Automatic
info:eu-repo/classification/cti/1
info:eu-repo/classification/cti/25
info:eu-repo/classification/cti/2512
Descrição
Resumo:The study of spectral signatures makes it possible to identify different objects of earth and sky, present in digital images. The elements that are in it make it have a particular feature, it is analogous to a fingerprint. Researcher’s study its spectral signature, which is made up of the physical, chemical, biological and wavelength properties of electromagnetic energy. It has multiple applications in different areas, such as geoscience and astronomy. In geoscience, the spectra are captured by satellites, once the solar radiation has penetrated the atmosphere, each type of surface interacts with the radiation in a way that absorbs wavelengths and reflects different ones. In astronomy, the spectra of the stars are captured by sensors, the electromagnetic radiation that comes from the stars emits wavelengths of the spectrum and several absorption lines. In relation to the study of stellar spectra, the National Institute of Astrophysics, Optics, and Electronics has at its disposal the set of digitized images of the astronomical plates that were taken with Schmidt Camera of Tonantzintla, from 1944 to 1994, during this period observations, it sampled the entire center of the galaxy and one of its poles. The collection of digitized images has been used in other works; researchers have dedicated to the study of stellar spectra, visually and automatically. With respect to automatic methods, in the present thesis work, a set of data is proposed, obtained from algorithms of extraction and selection of feature which results in the spectral signature of each stellar object. In this way, classification of stellar spectra of the proposed data set was made, using machine learning. The objective is to classify the largest number of stellar spectra and increase the classes and subclasses reported in previous works. To finish with the proposed, the results are reported up to 90.32% accuracy, for the main classes and subclasses of spectral type.