EMC - Escola de Engenharia Elétrica, Mecânica e de Computação
URI Permanente desta comunidade
A Escola de Engenharia Elétrica, Mecânica e de Computação (EMC), da Universidade Federal de Goiás, oferece Graduação em: Engenharia Elétrica, Engenharia Mecânica e Engenharia da Computação. Além de Especialização em: Telecomunicações; Instalações Elétricas; e, Gestão de Negócios.
Navegar
Navegando EMC - Escola de Engenharia Elétrica, Mecânica e de Computação por curso "Engenharia da Computação (RG)"
Agora exibindo 1 - 4 de 4
Resultados por página
Opções de Ordenação
Item Desenvolvimento de sistema para gerenciar e auxiliar na tomada de decisão envolvendo consumo de energia elétrica(Universidade Federal de Goiás, 2019-07-05) Raulino, Rafael Ratacheski de Sousa; Castro, Marcelo Stehling de; Castro, Marcelo Stehling de; Oliveira, Gustavo Dias de; Pires, Sandrerley Ramosn recent years with the intense development of electronic devices to facilitate our day to day, electricity consumption has only increased, and along with this increase has also grown the environmental and economic impact caused by such consumption. Therefore, the concern to create measures for the understanding and control of impacts is increasingly present. It is proposed, with this work, the development of a system to monitor and assist in the control of the energy network of the Federal University of Goiás and its assets, providing an interface for appreciation and analysis of the data collected by the energy grid monitoring online systems, which allows to make the registration of assets, such as transformers, inverters, power plants, substations, along with the possibility of insertion of historical data of the consumption by reading the files of the invoices of the consumer units of the University, feeding the system database with the official data of the billing energy utility of past months.Item Projeto de cabeamento estruturado na infraestrutura de rede da escola de engenharia(Universidade Federal de Goiás, 2019-06-27) Costa, Alexandre da Silva; Castro, Tiago Santana de; Castro, Marcelo Stehling de; Castro, Marcelo Stehling de; Araújo, Sérgio Granato de; Oliveira, Gustavo Dias deThe present project started with an internship done by one of the authors in one of the buildings of the School of Engineering of the UFG (EMC-UFG) in 2018. Several problems were noticed during everyday tasks common to the network environment. The objective of this work is to present and develop practical solutions that improve the EMC-UFG Block A network environment based on Brazilian technical standards, thus enabling a standardization in existing cabling. First, the theoretical basis of network management is presented, followed by the presentation of various international and national standards on structured cabling. Then, the basic concepts of cabling infrastructure, active and passive components for the understanding of this project are exposed. It is necessary to demonstrate where the EMC-UFG network is inserted before proceeding with designation of the ideas proposed by this work. Finally, the results obtained are elucidated and can serve as a basis for future network expansion projects.Item Redes neurais auto - organizáveis na visualização da fala como recurso fonoaudiológico(Universidade Federal de Goiás, 2019-07-10) Silva, Ronaldo Gomes; Martins, Weber; Martins, Weber; Lemos, Rodrigo Pinto; Martins, Wellington SantosSpeech is an important element of socialization and development of the individual. However, millions of people do not develop it partially or completely. Verbal communication disorders usually appear as secondary anomalies due to other pathologies, such as hearing impairment. Although there is an expressive number of hearing impaired, the studies and use of computational resources in training and speech therapy for speech acquisition and improvement are still timid. In this context, the present work proposes the use of self-organizing neural networks as an aid in the speech-language training process of individuals with speech disorders, through visual feedback. The processes required for the development of the proposed system are described, as well as experiments with Kohonen's Self-Organizing Map, using Mel Frequency Cepstral Coefficients as descriptors of speech characteristics. Some configuration scenarios were defined for both the selforganizing map parameters and the cepstral coefficients, where the topological phonetic map of reduced scope was obtained, which produced a lower percentage of error and misconceptions, being 35.83% and 35.42%, respectively.Item Utilização de redes neurais recorrentes para predição de controle de estoque(Universidade Federal de Goiás, 2019-07-05) Faria Filho, Eduardo Rodrigues de; Guimarães, Gabriel Augusto de Vito D’Abbadia; Pires, Sandrerley Ramos; Pires, Sandrerley Ramos; Marques, Thyago Carvalho; Pinheiro Júnior, Carlos Galvãohe present work aims at studying the Recurrent Neural network (RNN) as a method for prediction of the amount of stock needed for the given period of maize deseeded. Being that the corn product marketed for a specific seller of agricultural products. Before that, it was made a study of the historical series of sales of the product in question and so confronted past periods for the prediction in future periods.