A proposal to the supervision of processes in an industrial environment with heterogeneous systems

SOUZA, Rodrigo B. ; MEDEIROS, Adelardo A. D. ; NASCIMENTO, João Maria A. ; GOMES, Heitor P. ; MAITELLI, André L. A Proposal to the Supervision of Processes in an Industrial Environment with Heterogeneous Systems. In: INTERNATIONAL CONFERENCE OF THE IEEEOF THE INDUSTRUI ELECTRONICS SOCIETY,32., Paris, 2006, Paris. Anais... Paris: IECON, 2006

Aplicação de técnicas de aprendizado de máquina no reconhecimento de classes estruturais de proteínas

Nowadays, classifying proteins in structural classes, which concerns the inference of patterns in their 3D conformation, is one of the most important open problems in Molecular Biology. The main reason for this is that the function of a protein is intrinsically related to its spatial conformation. However, such conformations are very difficult to be obtained experimentally in laboratory. Thus, this problem has drawn the attention of many researchers in Bioinformatics. Considering the great difference between the number of protein sequences already known and the number of three-dimensional structures determined experimentally, the demand of automated techniques for structural classification of proteins is very high. In this context, computational tools, especially Machine Learning (ML) techniques, have become essential to deal with this problem. In this work, ML techniques are used in the recognition of protein structural classes: Decision Trees, k-Nearest Neighbor, Naive Bayes, Support Vector Machine and Neural Networks. These methods have been chosen because they represent different paradigms of learning and have been widely used in the Bioinfornmatics literature. Aiming to obtain an improvment in the performance of these techniques (individual classifiers), homogeneous (Bagging and Boosting) and heterogeneous (Voting, Stacking and StackingC) multiclassification systems are used. Moreover, since the protein database used in this work presents the problem of imbalanced classes, artificial techniques for class balance (Undersampling Random, Tomek Links, CNN, NCL and OSS) are used to minimize such a problem. In order to evaluate the ML methods, a cross-validation procedure is applied, where the accuracy of the classifiers is measured using the mean of classification error rate, on independent test sets. These means are compared, two by two, by the hypothesis test aiming to evaluate if there is, statistically, a significant difference between them. With respect to the results obtained with the individual classifiers, Support Vector Machine presented the best accuracy. In terms of the multi-classification systems (homogeneous and heterogeneous), they showed, in general, a superior or similar performance when compared to the one achieved by the individual classifiers used - especially Boosting with Decision Tree and the StackingC with Linear Regression as meta classifier. The Voting method, despite of its simplicity, has shown to be adequate for solving the problem presented in this work. The techniques for class balance, on the other hand, have not produced a significant improvement in the global classification error. Nevertheless, the use of such techniques did improve the classification error for the minority class. In this context, the NCL technique has shown to be more appropriated

Avaliação cinética e potencial do Nb2O5 obtido a partir de um complexo de nióbio para formação do oleato de metila através da reação de esterificação do ácido oleico

Among the heterogeneous catalysts materials made from niobium show up as an alternative to meet the demand of catalysts for biodiesel production. This study aims to evaluate the potential of a heterogeneous catalyst derived from a complex of niobium in the reaction of methyl esterification of oleic acid. The catalyst was synthesized after calcination at different temperatures of a niobium complex ((NH4)3[NbO(C2O4)3].H2O) generating a niobium oxide nanostructure with a different commercial niobium oxide used to synthesize the complex. The commercial niobium oxide, the complex niobium and niobium catalyst were characterized by thermogravimetry (TG and DTA), surface area analysis (BET), scanning electron microscopy (SEM) and X-ray diffraction (XRD), showing the catalyst has researched morphological and crystallographic indicating a catalytic potential higher than that of commercial niobium oxide characteristics. Factorial with central composite design point, with three factors (calcination temperature, molar ratio of alcohol/oleic acid and mass percentage of catalyst) was performed. Noting that the optimal experimental point was given by the complex calcination temperature of 600°C, a molar ratio alcohol/oleic acid of 3.007/1 and the catalyst mass percentage of 7.998%, with a conversion of 22.44% oleic acid in methyl oleate to 60 min of reaction. We performed a composite linear and quadratic regression to determine an optimal statistical point of the reaction, the temperature of calcination of the complex at 450°C, the molar ratio of alcohol/oleic acid 3.3408/1 and mass percentage of catalyst of 7.6833% . Kinetic modeling to estimate parameters for heterogeneous catalysis it set well the experimental results with a final conversion of 85.01% with 42.38% of catalyst and without catalyst at 240 min reaction was performed. Allowing to evaluate the catalyst catalytic studied has the potential to be used in biodiesel production