Máquina de vetores-suporte intervalar

The Support Vector Machines (SVM) has attracted increasing attention in machine learning area, particularly on classification and patterns recognition. However, in some cases it is not easy to determinate accurately the class which given pattern belongs. This thesis involves the construction of a intervalar pattern classifier using SVM in association with intervalar theory, in order to model the separation of a pattern set between distinct classes with precision, aiming to obtain an optimized separation capable to treat imprecisions contained in the initial data and generated during the computational processing. The SVM is a linear machine. In order to allow it to solve real-world problems (usually nonlinear problems), it is necessary to treat the pattern set, know as input set, transforming from nonlinear nature to linear problem. The kernel machines are responsible to do this mapping. To create the intervalar extension of SVM, both for linear and nonlinear problems, it was necessary define intervalar kernel and the Mercer s theorem (which caracterize a kernel function) to intervalar function

Comparação entre metodologias de extração de HPAs em água utilizando um planejamento fatorial com quantificação no CG/EM

PAHs (Polycyclic Aromatic Hydrocarbons) are a group of organic substances which receive considerable attention because of the carcinogenic and mutagenic properties of some of them. It is therefore important to determine the PAHs in different environmental matrices. Several studies have shown the use of gas chromatography coupled to mass spectrometry as a technique for quantification of PAHs by presenting excellent detection limits. This study aimed to develop an analytical methodology for the determination of 16 PAHs listed by the USEPA, test two methods for extraction of PAHs in water from a 23 factorial design, quantify them through the analytical technique coupled to gas chromatography mass spectrometry (GC/MS) using the method developed, and finally apply the results in chemometrics. The sample was synthesized and subjected to tests of the 23 factorial design, which has the factors: the type of extraction technique (ultrasound and digester), the ratio solvent / sample (1:1 and 1:3) and the type of solvent (dichloromethane / hexane and acetone / dichloromethane). The responses of eight combinations of the factorial design were obtained from the quantification by external calibration in GC/MS. The quantification method was developed from an optimized adaptation of the USEPA Method 8270. We used the full scan mode as a way of acquiring the mass spectra of 16 PAHs. The time in which the samples were subjected to ultrasound was fixed at 10 min and held an investigation to establish the conditions of power and time in the digester. We had the best response in the investigation of the digester power of 100 watts and the time of six minutes. The factorial design of liquid-liquid extraction showed that the most representative factors were: the use of the digester as extraction technique, the ratio solvent / sample 1:1 and the use of a 1:1 mixture of dichloromethane / hexane as a solvent more suitable. These results showed that the 1:1 mixture of dichloromethane / hexane is an excellent mixture to recover the extraction of PAHs an aqueous sample using the microwave digester. The optimization of the method of separation, identification and quantification of PAHs in the GC/MS was valid for 16 PAHs present in each chromatogram of the samples

Identificação e comparação entre controle preditivo com modelo não linear e PI sintonizados com PSO em sistema de separação gravitacional de águia-óleo

The separation methods are reduced applications as a result of the operational costs, the low output and the long time to separate the uids. But, these treatment methods are important because of the need for extraction of unwanted contaminants in the oil production. The water and the concentration of oil in water should be minimal (around 40 to 20 ppm) in order to take it to the sea. Because of the need of primary treatment, the objective of this project is to study and implement algorithms for identification of polynomial NARX (Nonlinear Auto-Regressive with Exogenous Input) models in closed loop, implement a structural identification, and compare strategies using PI control and updated on-line NARX predictive models on a combination of three-phase separator in series with three hydro cyclones batteries. The main goal of this project is to: obtain an optimized process of phase separation that will regulate the system, even in the presence of oil gushes; Show that it is possible to get optimized tunings for controllers analyzing the mesh as a whole, and evaluate and compare the strategies of PI and predictive control applied to the process. To accomplish these goals a simulator was used to represent the three phase separator and hydro cyclones. Algorithms were developed for system identification (NARX) using RLS(Recursive Least Square), along with methods for structure models detection. Predictive Control Algorithms were also implemented with NARX model updated on-line, and optimization algorithms using PSO (Particle Swarm Optimization). This project ends with a comparison of results obtained from the use of PI and predictive controllers (both with optimal state through the algorithm of cloud particles) in the simulated system. Thus, concluding that the performed optimizations make the system less sensitive to external perturbations and when optimized, the two controllers show similar results with the assessment of predictive control somewhat less sensitive to disturbances