Aprendizado profundo para classificação de microorganismos

• Ano de defesa: 2018
• Autor(a) principal: Faria, Renan Carlos Prata de
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Rio de Janeiro; Brasil; Instituto Alberto Luiz Coimbra de Pós-Graduação e Pesquisa de Engenharia; Programa de Pós-Graduação em Engenharia de Sistemas e Computação; UFRJ
• Palavras-chave em Português: Machine Learning; Deep Learning; Microrganismos; Redes Neurais; CNPQ::ENGENHARIAS
• Link de acesso: http://hdl.handle.net/11422/13071

In this work we present a comparison among three machine learning (ML) methods applied to identify Chattonella based on microscopic images. We analyze KNearest Neighbors algorithm (KNN), Weightless Neural Network algorithm (WNN) and Convolutional Neural Network algorithm (CNN). The latter being the state of art to image classification. The goal of this work is to identify the best method to count different types of microorganisms in oceanic water samples, with the goal for detecting pollution. This comparison takes into account accuracy of the hit rate. The best result was reached by Convolutional Neural Network algorithm, as will be described in this work.