Classificação de imagens de ambientes coralinos: uma abordagem empregando uma combinação de classificadores e máquina de vetor de suporte

The use of the maps obtained from remote sensing orbital images submitted to digital processing became fundamental to optimize conservation and monitoring actions of the coral reefs. However, the accuracy reached in the mapping of submerged areas is limited by variation of the water column that degrades the signal received by the orbital sensor and introduces errors in the final result of the classification. The limited capacity of the traditional methods based on conventional statistical techniques to solve the problems related to the inter-classes took the search of alternative strategies in the area of the Computational Intelligence. In this work an ensemble classifiers was built based on the combination of Support Vector Machines and Minimum Distance Classifier with the objective of classifying remotely sensed images of coral reefs ecosystem. The system is composed by three stages, through which the progressive refinement of the classification process happens. The patterns that received an ambiguous classification in a certain stage of the process were revalued in the subsequent stage. The prediction non ambiguous for all the data happened through the reduction or elimination of the false positive. The images were classified into five bottom-types: deep water; under-water corals; inter-tidal corals; algal and sandy bottom. The highest overall accuracy (89%) was obtained from SVM with polynomial kernel. The accuracy of the classified image was compared through the use of error matrix to the results obtained by the application of other classification methods based on a single classifier (neural network and the k-means algorithm). In the final, the comparison of results achieved demonstrated the potential of the ensemble classifiers as a tool of classification of images from submerged areas subject to the noise caused by atmospheric effects and the water column

Controle adaptativo robusto para um modelo desacoplado de um robô móvel

This thesis presents a new structure of robust adaptive controller applied to mobile robots (surface mobile robot) with nonholonomic constraints. It acts in the dynamics and kinematics of the robot, and it is split in two distinct parts. The first part controls the robot dynamics, using variable structure model reference adaptive controllers. The second part controls the robot kinematics, using a position controller, whose objective is to make the robot to reach any point in the cartesian plan. The kinematic controller is based only on information about the robot configuration. A decoupling method is adopted to transform the linear model of the mobile robot, a multiple-input multiple-output system, into two decoupled single-input single-output systems, thus reducing the complexity of designing the controller for the mobile robot. After that, a variable structure model reference adaptive controller is applied to each one of the resulting systems. One of such controllers will be responsible for the robot position and the other for the leading angle, using reference signals generated by the position controller. To validate the proposed structure, some simulated and experimental results using differential drive mobile robots of a robot soccer kit are presented. The simulator uses the main characteristics of real physical system as noise and non-linearities such as deadzone and saturation. The experimental results were obtained through an C++ program applied to the robot soccer kit of Microrobot team at the LACI/UFRN. The simulated and experimental results are presented and discussed at the end of the text

Identificação fuzzy-multimodelos para sistemas não lineares

This paper presents a new multi-model technique of dentification in ANFIS for nonlinear systems. In this technique, the structure used is of the fuzzy Takagi-Sugeno of which the consequences are local linear models that represent the system of different points of operation and the precursors are membership functions whose adjustments are realized by the learning phase of the neuro-fuzzy ANFIS technique. The models that represent the system at different points of the operation can be found with linearization techniques like, for example, the Least Squares method that is robust against sounds and of simple application. The fuzzy system is responsible for informing the proportion of each model that should be utilized, using the membership functions. The membership functions can be adjusted by ANFIS with the use of neural network algorithms, like the back propagation error type, in such a way that the models found for each area are correctly interpolated and define an action of each model for possible entries into the system. In multi-models, the definition of action of models is known as metrics and, since this paper is based on ANFIS, it shall be denominated in ANFIS metrics. This way, ANFIS metrics is utilized to interpolate various models, composing a system to be identified. Differing from the traditional ANFIS, the created technique necessarily represents the system in various well defined regions by unaltered models whose pondered activation as per the membership functions. The selection of regions for the application of the Least Squares method is realized manually from the graphic analysis of the system behavior or from the physical characteristics of the plant. This selection serves as a base to initiate the linear model defining technique and generating the initial configuration of the membership functions. The experiments are conducted in a teaching tank, with multiple sections, designed and created to show the characteristics of the technique. The results from this tank illustrate the performance reached by the technique in task of identifying, utilizing configurations of ANFIS, comparing the developed technique with various models of simple metrics and comparing with the NNARX technique, also adapted to identification

Mapeamento robótico 2,5-D com representação em grade de ocupação-elevação

This work introduces a new method for environment mapping with three-dimensional information from visual information for robotic accurate navigation. Many approaches of 3D mapping using occupancy grid typically requires high computacional effort to both build and store the map. We introduce an 2.5-D occupancy-elevation grid mapping, which is a discrete mapping approach, where each cell stores the occupancy probability, the height of the terrain at current place in the environment and the variance of this height. This 2.5-dimensional representation allows that a mobile robot to know whether a place in the environment is occupied by an obstacle and the height of this obstacle, thus, it can decide if is possible to traverse the obstacle. Sensorial informations necessary to construct the map is provided by a stereo vision system, which has been modeled with a robust probabilistic approach, considering the noise present in the stereo processing. The resulting maps favors the execution of tasks like decision making in the autonomous navigation, exploration, localization and path planning. Experiments carried out with a real mobile robots demonstrates that this proposed approach yields useful maps for robot autonomous navigation

Mapeamento com Sonar Usando Grade de Ocupação baseado em Modelagem Probabilística

In this work, we propose a probabilistic mapping method with the mapped environment represented through a modified occupancy grid. The main idea of the proposed method is to allow a mobile robot to construct in a systematic and incremental way the geometry of the underlying space, obtaining at the end a complete environment map. As a consequence, the robot can move in the environment in a safe way, based on a confidence value of data obtained from its perceptive system. The map is represented in a coherent way, according to its sensory data, being these noisy or not, that comes from exterior and proprioceptive sensors of the robot. Characteristic noise incorporated in the data from these sensors are treated by probabilistic modeling in such a way that their effects can be visible in the final result of the mapping process. The results of performed experiments indicate the viability of the methodology and its applicability in the area of autonomous mobile robotics, thus being an contribution to the field

Implantação de um sistema de detecção de vazamentos em oleodutos com tratamento de alarmes falsos

The pumping of fluids in pipelines is the most economic and safe form of transporting fluids. That explains why in Europe there was in 1999 about 30.000 Km [7] of pipelines of several diameters, transporting millíons of cubic meters of crude oil end refined products, belonging to COCAWE (assaciation of companies of petroleum of Europe for health, environment and safety, that joint several petroleum companies). In Brazil they are about 18.000 Km of pipelines transporting millions of cubic meters of liquids and gases. In 1999, nine accidents were registered to COCAWE. Among those accidents one brought a fatal victim. The oil loss was of 171 m3, equivalent to O,2 parts per million of the total of the transported volume. Same considering the facts mentioned the costs involved in ao accident can be high. An accident of great proportions can bríng loss of human lives, severe environmental darnages, loss of drained product, loss . for dismissed profit and damages to the image of the company high recovery cost. In consonance with that and in some cases for legal demands, the companies are, more and more, investing in systems of Leak detection in pipelines based on computer algorithm that operate in real time, seeking wíth that to minimize still more the drained volumes. This decreases the impacts at the environment and the costs. In general way, all the systems based on softWare present some type of false alarm. In general a commitment exists betWeen the sensibílity of the system and the number of false alarms. This work has as objective make a review of thé existent methods and to concentrate in the analysis of a specific system, that is, the system based on hydraulic noise, Pressure Point Analyzis (PPA). We will show which are the most important aspects that must be considered in the implementation of a Leak Detection System (LDS), from the initial phase of the analysis of risks passing by the project bases, design, choice of the necessary field instrumentation to several LDS, implementation and tests. We Will make na analysis of events (noises) originating from the flow system that can be generator of false alarms and we will present a computer algorithm that restricts those noises automatically

Sensores e interfaces com aplicações em motor mancal

Relevant researches have been growing on electric machine without mancal or bearing and that is generally named bearingless motor or specifically, mancal motor. In this paper it is made an introductory presentation about bearingless motor and its peripherical devices with focus on the design and implementation of sensors and interfaces needed to control rotor radial positioning and rotation of the machine. The signals from the machine are conditioned in analogic inputs of DSP TMS320F2812 and used in the control program. This work has a purpose to elaborate and build a system with sensors and interfaces suitable to the input and output of DSP TMS320F2812 to control a mancal motor, bearing in mind the modularity, simplicity of circuits, low number of power used, good noise imunity and good response frequency over 10 kHz. The system is tested at a modified ordinary induction motor of 3,7 kVA to be used with a bearingless motor with divided coil

Controle vetorial para velocidade de um motor de indução trifásico utilizando estimador filtro de Kalman

This paper describes the study, computer simulation and feasibility of implementation of vector control speed of an induction motor using for this purpose the Extended Kalman Filter as an estimator of rotor flux. The motivation for such work is the use of a control system that requires no sensors on the machine shaft, thus providing a considerable cost reduction of drives and their maintenance, increased reliability, robustness and noise immunity as compared to control systems with conventional sensors

Projeto e Implementação em Ambiente Foundation Fieldbus de Filtragem Estocástica Baseada em Análise de Componentes Independentes (M175)

This work considers the development of a filtering system composed of an intelligent algorithm, that separates information and noise coming from sensors interconnected by Foundation Fieldbus (FF) network. The algorithm implementation will be made through FF standard function blocks, with on-line training through OPC (OLE for Process Control), and embedded technology in a DSP (Digital Signal Processor) that interacts with the fieldbus devices. The technique ICA (Independent Component Analysis), that explores the possibility of separating mixed signals based on the fact that they are statistically independent, was chosen to this Blind Source Separation (BSS) process. The algorithm and its implementations will be Presented, as well as the results

Avaliação dos impactos ambientais gerados por uma industria cerâmica típica da Região do Seridó/RN

The present work deals with an evaluation of the environmental impacts arised from a typical ceramics industry located in the Seridó region of Rio Grande do Norte State. That region contains the largest State s producing basin of red ceramics. The district of Parelhas stands out as the largest producing nucleus. The studied company is located in the rural zone of Parelhas, it was selected as study object because it possesses a great part of the representative characteristics of the Region s ceramics park as a whole. Impacts produced at the implantation and operation phases of the Company had been evaluated, being this last phase subdivided in stages of the productive process. Among found adverse impacts, they are distinguished: losses in air quality, undesirable noises, microclimatic alterations, impoverishment of the ground, elimination of the vegetal covering, agricultural exodus, crisis in cattle agriculture and, superficial and underground water contamination, beyond risks ocupational diseases and industrial accidents. The Leopold s interactive matrix, that summarizes results of the work, was presented in form of 15 (fifteen) tables that display impacts classified in qualitative and quantitative way. Totally, 175 (one hundred and seventy-five) significant impacts produced by this Company had been identified, being 114 (one hundred and fourteen) negative, 38 (thirty-eight) positive and 23 (twenty-three) among mixed, indefinite and inert ones. In the work, before the evaluation of impacts properly said, it was constructed a diagnostic table of the ambient situation at a previous moment to implantation of the Company, elaborated on basis of inferences and historical researches. It was proposed still, mitigative steps for adverse impacts identified, as also elaborated a program to accompaniment and observing that the fulfilment of indicated mitigative steps guarantees. The final part of the work contemplates conclusions and suggestions that aim to influence positively the presented sight in terms of environmental management

Monitoramento em tempo real de processos fermentativos por espectroscopia no infravermelho próximo (NIRS)

A chemical process optimization and control is strongly correlated with the quantity of information can be obtained from the system. In biotechnological processes, where the transforming agent is a cell, many variables can interfere in the process, leading to changes in the microorganism metabolism and affecting the quantity and quality of final product. Therefore, the continuously monitoring of the variables that interfere in the bioprocess, is crucial to be able to act on certain variables of the system, keeping it under desirable operational conditions and control. In general, during a fermentation process, the analysis of important parameters such as substrate, product and cells concentration, is done off-line, requiring sampling, pretreatment and analytical procedures. Therefore, this steps require a significant run time and the use of high purity chemical reagents to be done. In order to implement a real time monitoring system for a benchtop bioreactor, these study was conducted in two steps: (i) The development of a software that presents a communication interface between bioreactor and computer based on data acquisition and process variables data recording, that are pH, temperature, dissolved oxygen, level, foam level, agitation frequency and the input setpoints of the operational parameters of the bioreactor control unit; (ii) The development of an analytical method using near-infrared spectroscopy (NIRS) in order to enable substrate, products and cells concentration monitoring during a fermentation process for ethanol production using the yeast Saccharomyces cerevisiae. Three fermentation runs were conducted (F1, F2 and F3) that were monitored by NIRS and subsequent sampling for analytical characterization. The data obtained were used for calibration and validation, where pre-treatments combined or not with smoothing filters were applied to spectrum data. The most satisfactory results were obtained when the calibration models were constructed from real samples of culture medium removed from the fermentation assays F1, F2 and F3, showing that the analytical method based on NIRS can be used as a fast and effective method to quantify cells, substrate and products concentration what enables the implementation of insitu real time monitoring of fermentation processes

Noções básicas de variabilidade da frequência cardíaca e sua aplicabilidade clínica

O sistema nervoso autônomo (SNA) desempenha um papel importante na regulação dos processos fisiológicos do organismo humano tanto em condições normais quanto patológicas. Dentre as técnicas utilizadas para sua avaliação, a variabilidade da frequência cardíaca (VFC) tem emergido como uma medida simples e não-invasiva dos impulsos autonômicos, representando um dos mais promissores marcadores quantitativos do balanço autonômico. A VFC descreve as oscilações no intervalo entre batimentos cardíacos consecutivos (intervalos R-R), assim como oscilações entre frequências cardíacas instantâneas consecutivas. Trata-se de uma medida que pode ser utilizada para avaliar a modulação do SNA sob condições fisiológicas, tais como em situações de vigília e sono, diferentes posições do corpo, treinamento físico, e também em condições patológicas. Mudanças nos padrões da VFC fornecem um indicador sensível e antecipado de comprometimentos na saúde. Uma alta variabilidade na frequência cardíaca é sinal de boa adaptação, caracterizando um indivíduo saudável, com mecanismos autonômicos eficientes, enquanto que, baixa variabilidade é frequentemente um indicador de adaptação anormal e insuficiente do SNA, implicando a presença de mau funcionamento fisiológico no indivíduo. Diante da sua importância como um marcador que reflete a atividade do SNA sobre o nódulo sinusal e como uma ferramenta clínica para avaliar e identificar comprometimentos na saúde, este artigo revisa aspectos conceituais da VFC, dispositivos de mensuração, métodos de filtragem, índices utilizados para análise da VFC, limitações de utilização e aplicações clínicas da VFC.

Análise dos traçados de ondas da agregação plaquetária em pacientes com doenças cardiovasculares em uso do ácido acetil salicílico comparados a doadores de sangue

A agregação plaquetária avalia a função das plaquetas através de diferentes vias de ativação plaquetária in vitro, fornecendo traçados de ondas equivalentes à propriedade física dessa agregação. Sabendo-se que a aspirina acetila irrever­sivelmente a enzima cicloxigenase prevenindo a geração de tromboxana A2, potente ativador da agregação plaquetária, esta droga tem sido analisada há mais de trinta anos na clínica médica em pacientes com doenças cardiovasculares como uma potente droga antitrombótica. Foram nossos objetivos obter traçados de ondas correspondentes às fases da agregação plaquetária para nossa padronização utilizando nosso grupo controle de doadores de sangue e compará-las com nosso grupo estudo, frente a diferentes agentes agonistas em diferentes concentrações: ADP 1µM e 3µM; AA, 0,5mM; ADR, 0,05 mg/mL, 0,025 mg/mL e 0,010 mg/mL. Os grupos analisados foram constituídos por 41 cardíacos e 40 doadores de sangue considerados controle. Dos cardíacos, 33 faziam uso regular do AAS na concentração de 200 mg/dia e oito na concentração de 100 mg/dia, sendo todos considerados hipertensos. A padronização da agregometria estava na dependência do encontro de traçados correspondentes a ondas de agregação, sendo esses obtidos em porcentagem no tempo de cinco minutos estandartizados pelo aparelho utilizado. Comparando os resultados entre os pacientes e o grupo controle, foi possível observar que, na presença dos agentes agregantes ADP 1µM e ADP 3 µM, ADR 0,05 mg/mL, 0,025mg/mL e 0,010 mg/mL, os pacientes apresentaram 1ª onda, mas não 2ª onda. Por sua vez, no caso do AA 0,5 mM não houve o encontro de traçados de ondas.

Análise estatística de padrões sísmicos: decomposição em multiescala

O processamento de registros sísmicos é uma tarefa muito importante dentro da Geofísica e que representa um desafio permanente na exploração de petróleo. Embora esses sinais forneçam uma imagem adequada da estrutura geológica do subsolo, eles são contaminados por ruídos e, o ground roll é a componente principal. Este fato exige um esforço grande para o desenvolvimento de metodologias para filtragem, Dentro desse contexto, este trabalho tem como objetivo apresentar um método de remoção do ruído ground roll fazendo uso de ferramentas da Física Estatística. No método, a Análise em Ondeletas é combinada com a Transformada de Karhunen-Loève para a remoção em uma região bem localizada. O processo de filtragem começa com a Decomposição em Multiescala. Essa técnica permite uma representação em tempo-escala fazendo uso das ondeletas discretas implementadas a filtros de reconstrução perfeita. O padrão sísmico original fica representado em multipadrões: um por escala. Assim, pode-se atenuar o ground roll como uma operação cirúrgica em cada escala, somente na região onde sua presença é forte, permitindo preservar o máximo de informações relevantes. A atenuação é realizada pela definição de um fator de atenuação Af. Sua escolha é feita pelo comportamento dos modos de energia da Transformada de Karhunen-Loève. O ponto correspondendo a um mínimo de energia do primeiro modo é identificado como um fator de atenuação ótimo

Fisioterapia respiratória em crianças com pneumonia: revisão sistemática

Introduction: Pneumonia is an inflammatory lung disease and it is the greatest cause of deaths in children younger than five years of age worldwide. Chest physiotherapy is widely used in the treatment of pneumonia because it can help to eliminate inflammatory exudates and tracheobronchial secretions, remove airway obstructions, reduce airway resistance, enhance gas exchange and reduce the work of breathing. Thus, chest physiotherapy may contribute to patient recovery as an adjuvant treatment even though its indication remains controversial. Objectives: To assess the effectiveness of chest physiotherapy in relation to time until clinical resolution in children (from birth up to 18 years old) of either gender with any type of pneumonia. Methods: We searched CENTRAL 2013, Issue 4; MEDLINE (1946 to May week 4, 2013); EMBASE (1974 to May 2013); CINAHL (1981 to May 2013); LILACS (1982 to May 2013); Web of Science (1950 to May 2013); and PEDro (1950 to May 2013). We consulted the ClinicalTrials.gov and the WHO ICTRP registers to identify planned, ongoing and unpublished trials. We consulted the reference lists of relevant articles found by the electronic searches for additional studies. We included randomised controlled trials (RCTs) that compared chest physiotherapy of any type with no chest physiotherapy in children with pneumonia. Two review authors independently selected the studies to be included in the review, assessed trial quality and extracted data. Results: Three RCTs involving 255 inpatient children are included in the review. They addressed conventional chest physiotherapy, positive expiratory pressure and continuous positive airway pressure. The following outcomes were measured: duration of hospital stay, time to clinical resolution (observing the following parameters: fever, chest indrawing, nasal flaring, tachypnoea and peripheral oxygen saturation levels), change in adventitious sounds, change in chest X-ray and duration of cough in days. Two of the included studies found a significant improvement in respiratory rate and oxygen saturation whereas the other included study failed to show that standardised respiratory physiotherapy and positive expiratory pressure decrease the time to clinical resolution and the duration of hospital stay. No adverse effects related to the interventions were xvi described. Due to the different characteristics of the trials, such as the duration of treatment, levels of severity, types of pneumonia and the techniques used in children with pneumonia, as well as differences in their statistical presentation, we were not able to pool data. Two included studies had an overall low risk of bias whereas one included study had an overall unclear risk of bias. Conclusion: Our review does not provide conclusive evidence to justify the use of chest physiotherapy in children with pneumonia due to a lack of data. The number of included studies is small and they differed in their statistical presentation