Submitted by Luis Ricardo Andrade da Silva (lrasilva@uefs.br) on 2017-11-28T22:15:22Z No. of bitstreams: 1 AILINE-corrigida e completa-enviada pgca.pdf: 18819458 bytes, checksum: 1356b2bb4c6c8fbf60dec709646715da (MD5) / Made available in DSpace on 2017-11-28T22:15:22Z (GMT). No. of bitstreams: 1 AILINE-corrigida e completa-enviada pgca.pdf: 18819458 bytes, checksum: 1356b2bb4c6c8fbf60dec709646715da (MD5) Previous issue date: 2017-08-24 / Advances in the acquisition technology of astronomical spectra resulted in an enormous amount of data. Not being more feasible to analyze them using classical approaches, the need for automatic methods arises. Then, in this research is presented, an Intelligent Algorithm for Identifying Spectral Lines, the AILINE (in Portuguese), which utilizes an artificial neural network to identify the emission lines in the optical spectra of galaxies. This method that in the tests carried out has achieved a accuracy higher than 95% is evaluated and faced with other automatic approaches and other machine learning algorithms. / Os avan?os na tecnologia de aquisi??o de espectros astron?micos resultaram em uma enorme quantidade de dados. N?o sendo mais vi?vel analis?-los usando abordagens cl?ssicas, surge a necessidade de m?todos autom?ticos. Ent?o, nesta pesquisa ? apresentado um Algoritmo Inteligente para Identifica??o de Linhas Espectrais, o AILINE, que utiliza uma Rede Neural Artificial para identificar as linhas em emiss?o nos espectros ?pticos de gal?xias. Este m?todo que nos testes realizados alcan?ou uma acur?cia superior a 95%, ? avaliado e confrontado com outras abordagens autom?ticas e outros algoritmos de aprendizado de m?quina.