Navegando por Autor "MORALES, Gundisalvo Piratoba"

Agora exibindo 1 - 2 de 2

Acesso aberto (Open Access)
Classificação de estratos florestais utilizando redes neurais artificiais e dados de sensoriamento remoto
(Instituto de Pesquisas Ambientais em Bacias Hidrográficas, 2016-09) GONÇALVES, Wanderson Gonçalves e; RIBEIRO, Hebe Morganne Campos; SÁ, José Alberto Silva de; MORALES, Gundisalvo Piratoba; FERREIRA FILHO, Hélio Raymundo; ALMEIDA, Arthur da Costa
This study classified forest types using neural network data from a forest inventory provided by the "Florestal e da Biodiversidade do Estado do Pará" (IDEFLOR-BIO), and Bands 3, 4 and 5 of TM from the Landsat satellite. The information from the satellite images was extracted using QGIS software 2.8.1 Wien and was used as a database for training neural networks belonging to the software tools package MATLAB(r) R2011b. The neural networks were trained to classify two forest types: Rain Forest of Lowland Emerging Canopy (Dbe) and Rain Forest of Lowland Emerging Canopy plus Open with palm trees (Dbe + Abp) in the Mamuru Arapiuns glebes of Pará State, and were evaluated in terms of the indicators confusion matrix, overall accuracy, the Kappa coefficient, and the receiver operating characteristics chart (ROC). The best result of classification was obtained by the probabilistic neural network of radial basis function (RBF) newpnn, with an overall accuracy of 88%, and a Kappa coefficient of 76%, showing it to be a very good classifier, and demonstrating the potential of this methodology to provide ecosystem services, particularly in anthropogenic areas in the Amazon that adopt agricultural systems with low carbon emissions.
Acesso aberto (Open Access)
Influência da velocidade de circulação do leite na adesão de Pseudomonas aeruginosa sobre aço inoxidável
(2009-09) FIGUEIREDO, Hamilton Mendes de; ANDRADE, Nélio José de; OZELA, Eliana Ferreira; MORALES, Gundisalvo Piratoba
The influence of the flow milk circulation in the bacterial adhesion of Pseudomonas aeruginosa was evaluated by simulation tests through a circuit model of milk processing. The circuit is composed of a tubulation of stainless steel AISI 304, with 1.9 cm of diameter, 5.8 m of length and a tank of 25 L used as the reservoir of the product and sanitizer solutions. The reservoir was coupled to a centrifugal bomb of ½ HP to impel the food or sanitizer solutions for the system equipped with 90º and T cylindrical stainless steel specimens. The speed of circulation values were 0.5, 1.0 and 1.5 m.s–1, corresponding to turbulent flow with number of Reynolds 14.000, 28.000 and 42.000, respectively. When flow of 0.5 m.s–1 was used 10.7% the cells remained adhered, however at the speed values of 1.0 and 1.5 m.s–1 the adhesion percentages were 5.36 and 4.9%, respectively. These findings indicate a lower removal rate of adhered cells as flow decreases allowing higher number of bacteria to adhere to the production line, which can favor the biofilm formation.