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

Algoritmo Q-learning como estratégia de exploração e/ou explotação para metaheurísticas GRASP e algoritmo genético

Techniques of optimization known as metaheuristics have achieved success in the resolution of many problems classified as NP-Hard. These methods use non deterministic approaches that reach very good solutions which, however, don t guarantee the determination of the global optimum. Beyond the inherent difficulties related to the complexity that characterizes the optimization problems, the metaheuristics still face the dilemma of xploration/exploitation, which consists of choosing between a greedy search and a wider exploration of the solution space. A way to guide such algorithms during the searching of better solutions is supplying them with more knowledge of the problem through the use of a intelligent agent, able to recognize promising regions and also identify when they should diversify the direction of the search. This way, this work proposes the use of Reinforcement Learning technique - Q-learning Algorithm - as exploration/exploitation strategy for the metaheuristics GRASP (Greedy Randomized Adaptive Search Procedure) and Genetic Algorithm. The GRASP metaheuristic uses Q-learning instead of the traditional greedy-random algorithm in the construction phase. This replacement has the purpose of improving the quality of the initial solutions that are used in the local search phase of the GRASP, and also provides for the metaheuristic an adaptive memory mechanism that allows the reuse of good previous decisions and also avoids the repetition of bad decisions. In the Genetic Algorithm, the Q-learning algorithm was used to generate an initial population of high fitness, and after a determined number of generations, where the rate of diversity of the population is less than a certain limit L, it also was applied to supply one of the parents to be used in the genetic crossover operator. Another significant change in the hybrid genetic algorithm is the proposal of a mutually interactive cooperation process between the genetic operators and the Q-learning algorithm. In this interactive/cooperative process, the Q-learning algorithm receives an additional update in the matrix of Q-values based on the current best solution of the Genetic Algorithm. The computational experiments presented in this thesis compares the results obtained with the implementation of traditional versions of GRASP metaheuristic and Genetic Algorithm, with those obtained using the proposed hybrid methods. Both algorithms had been applied successfully to the symmetrical Traveling Salesman Problem, which was modeled as a Markov decision process

Aprendizado por Reforço com Valores deInfluência em Sistemas Multi-Agente

We propose a new paradigm for collective learning in multi-agent systems (MAS) as a solution to the problem in which several agents acting over the same environment must learn how to perform tasks, simultaneously, based on feedbacks given by each one of the other agents. We introduce the proposed paradigm in the form of a reinforcement learning algorithm, nominating it as reinforcement learning with influence values. While learning by rewards, each agent evaluates the relation between the current state and/or action executed at this state (actual believe) together with the reward obtained after all agents that are interacting perform their actions. The reward is a result of the interference of others. The agent considers the opinions of all its colleagues in order to attempt to change the values of its states and/or actions. The idea is that the system, as a whole, must reach an equilibrium, where all agents get satisfied with the obtained results. This means that the values of the state/actions pairs match the reward obtained by each agent. This dynamical way of setting the values for states and/or actions makes this new reinforcement learning paradigm the first to include, naturally, the fact that the presence of other agents in the environment turns it a dynamical model. As a direct result, we implicitly include the internal state, the actions and the rewards obtained by all the other agents in the internal state of each agent. This makes our proposal the first complete solution to the conceptual problem that rises when applying reinforcement learning in multi-agent systems, which is caused by the difference existent between the environment and agent models. With basis on the proposed model, we create the IVQ-learning algorithm that is exhaustive tested in repetitive games with two, three and four agents and in stochastic games that need cooperation and in games that need collaboration. This algorithm shows to be a good option for obtaining solutions that guarantee convergence to the Nash optimum equilibrium in cooperative problems. Experiments performed clear shows that the proposed paradigm is theoretical and experimentally superior to the traditional approaches. Yet, with the creation of this new paradigm the set of reinforcement learning applications in MAS grows up. That is, besides the possibility of applying the algorithm in traditional learning problems in MAS, as for example coordination of tasks in multi-robot systems, it is possible to apply reinforcement learning in problems that are essentially collaborative

Um algoritmo para estimação de estado em alimentadores de distribuição de energia elétrica com base no método da soma de potências

Most algorithms for state estimation based on the classical model are just adequate for use in transmission networks. Few algorithms were developed specifically for distribution systems, probably because of the little amount of data available in real time. Most overhead feeders possess just current and voltage measurements at the middle voltage bus-bar at the substation. In this way, classical algorithms are of difficult implementation, even considering off-line acquired data as pseudo-measurements. However, the necessity of automating the operation of distribution networks, mainly in regard to the selectivity of protection systems, as well to implement possibilities of load transfer maneuvers, is changing the network planning policy. In this way, some equipments incorporating telemetry and command modules have been installed in order to improve operational features, and so increasing the amount of measurement data available in real-time in the System Operation Center (SOC). This encourages the development of a state estimator model, involving real-time information and pseudo-measurements of loads, that are built from typical power factors and utilization factors (demand factors) of distribution transformers. This work reports about the development of a new state estimation method, specific for radial distribution systems. The main algorithm of the method is based on the power summation load flow. The estimation is carried out piecewise, section by section of the feeder, going from the substation to the terminal nodes. For each section, a measurement model is built, resulting in a nonlinear overdetermined equations set, whose solution is achieved by the Gaussian normal equation. The estimated variables of a section are used as pseudo-measurements for the next section. In general, a measurement set for a generic section consists of pseudo-measurements of power flows and nodal voltages obtained from the previous section or measurements in real-time, if they exist -, besides pseudomeasurements of injected powers for the power summations, whose functions are the load flow equations, assuming that the network can be represented by its single-phase equivalent. The great advantage of the algorithm is its simplicity and low computational effort. Moreover, the algorithm is very efficient, in regard to the accuracy of the estimated values. Besides the power summation state estimator, this work shows how other algorithms could be adapted to provide state estimation of middle voltage substations and networks, namely Schweppes method and an algorithm based on current proportionality, that is usually adopted for network planning tasks. Both estimators were implemented not only as alternatives for the proposed method, but also looking for getting results that give support for its validation. Once in most cases no power measurement is performed at beginning of the feeder and this is required for implementing the power summation estimations method, a new algorithm for estimating the network variables at the middle voltage bus-bar was also developed

Análise comparativa do desempenho de um Controlador Fuzzy acoplado a um PID Neural sintonizado por um Algoritmo Genético com Controladores Inteligentes Convencionais

On this paper, it is made a comparative analysis among a controller fuzzy coupled to a PID neural adjusted by an AGwith several traditional control techniques, all of them applied in a system of tanks (I model of 2nd order non lineal). With the objective of making possible the techniques involved in the comparative analysis and to validate the control to be compared, simulations were accomplished of some control techniques (conventional PID adjusted by GA, Neural PID (PIDN) adjusted by GA, Fuzzy PI, two Fuzzy attached to a PID Neural adjusted by GA and Fuzzy MISO (3 inputs) attached to a PIDN adjusted by GA) to have some comparative effects with the considered controller. After doing, all the tests, some control structures were elected from all the tested techniques on the simulating stage (conventional PID adjusted by GA, Fuzzy PI, two Fuzzy attached to a PIDN adjusted by GA and Fuzzy MISO (3 inputs) attached to a PIDN adjusted by GA), to be implemented at the real system of tanks. These two kinds of operation, both the simulated and the real, were very important to achieve a solid basement in order to establish the comparisons and the possible validations show by the results

Implementação de um algoritmo para a análise de curtos-circuitos de alta impedância baseado no fluxo de carga soma de potências

This work has as main objective to show all the particularities regarding the Three-phase Power Summation Method, used for load flow calculation, in what it says respect to the influence of the magnetic coupling among the phases, as well as to the losses presented in all the existent transformers in the feeder to be analyzed. Besides, its application is detailed in the study of the short-circuits, that happen in the presence of high impedance values, which possess a problem, that is its difficult detection and consequent elimination on the part of common devices of protection. That happens due to the characteristic presented by the current of short¬ circuit, in being generally of the same order of greatness that the load currents. Results of simulations accomplished in several situations will be shown, objectifying a complete analysis of the behavior of the proposed method in several types of short-circuits. Confront of the results obtained by the method with results of another works will be presented to verify its effectiveness

Algoritmo SOM com estrutura hierárquica e dinâmica aplicado a compressão de imagens

ln this work the implementation of the SOM (Self Organizing Maps) algorithm or Kohonen neural network is presented in the form of hierarchical structures, applied to the compression of images. The main objective of this approach is to develop an Hierarchical SOM algorithm with static structure and another one with dynamic structure to generate codebooks (books of codes) in the process of the image Vector Quantization (VQ), reducing the time of processing and obtaining a good rate of compression of images with a minimum degradation of the quality in relation to the original image. Both self-organizing neural networks developed here, were denominated HSOM, for static case, and DHSOM, for the dynamic case. ln the first form, the hierarchical structure is previously defined and in the later this structure grows in an automatic way in agreement with heuristic rules that explore the data of the training group without use of external parameters. For the network, the heuristic mIes determine the dynamics of growth, the pruning of ramifications criteria, the flexibility and the size of children maps. The LBO (Linde-Buzo-Oray) algorithm or K-means, one ofthe more used algorithms to develop codebook for Vector Quantization, was used together with the algorithm of Kohonen in its basic form, that is, not hierarchical, as a reference to compare the performance of the algorithms here proposed. A performance analysis between the two hierarchical structures is also accomplished in this work. The efficiency of the proposed processing is verified by the reduction in the complexity computational compared to the traditional algorithms, as well as, through the quantitative analysis of the images reconstructed in function of the parameters: (PSNR) peak signal-to-noise ratio and (MSE) medium squared error

Proposta de algoritmo para detecção de vazamentos em oleodutos utilizando análise freqüencial de sinais de pressão

Pipeline leak detection is a matter of great interest for companies who transport petroleum and its derivatives, in face of rising exigencies of environmental policies in industrialized and industrializing countries. However, existing technologies are not yet fully consolidated and many studies have been accomplished in order to achieve better levels of sensitivity and reliability for pipeline leak detection in a wide range of flowing conditions. In this sense, this study presents the results obtained from frequency spectrum analysis of pressure signals from pipelines in several flowing conditions like normal flowing, leakages, pump switching, etc. The results show that is possible to distinguish between the frequency spectra of those different flowing conditions, allowing recognition and announce of liquid pipeline leakages from pressure monitoring. Based upon these results, a pipeline leak detection algorithm employing frequency analysis of pressure signals is proposed, along with a methodology for its tuning and calibration. The proposed algorithm and its tuning methodology are evaluated with data obtained from real leakages accomplished in pipelines transferring crude oil and water, in order to evaluate its sensitivity, reliability and applicability to different flowing conditions

Posicionamento e movimentação de um robô humanóide utilizando imagens de uma câmera móvel externa

This work proposes a method to localize a simple humanoid robot, without embedded sensors, using images taken from an extern camera and image processing techniques. Once the robot is localized relative to the camera, supposing we know the position of the camera relative to the world, we can compute the position of the robot relative to the world. To make the camera move in the work space, we will use another mobile robot with wheels, which has a precise locating system, and will place the camera on it. Once the humanoid is localized in the work space, we can take the necessary actions to move it. Simultaneously, we will move the camera robot, so it will take good images of the humanoid. The mainly contributions of this work are: the idea of using another mobile robot to aid the navigation of a humanoid robot without and advanced embedded electronics; chosing of the intrinsic and extrinsic calibration methods appropriated to the task, especially in the real time part; and the collaborative algorithm of simultaneous navigation of the robots

Automação da detecção de fraudes em sistemas de medição de energia elétrica utilizando lógica fuzzy em ambiente SCADA

This works presents a proposal to make automatic the identification of energy thefts in the meter systems through Fuzzy Logic and supervisory like SCADA. The solution we find by to collect datas from meters at customers units: voltage, current, power demand, angles conditions of phasors diagrams of voltages and currents, and taking these datas by fuzzy logic with expert knowledge into a fuzzy system. The parameters collected are computed by fuzzy logic, in engineering alghorithm, and the output shows to user if the customer researched may be consuming electrical energy without to pay for it, and these feedbacks have its own membership grades. The value of this solution is a need for reduce the losses that already sets more than twenty per cent. In such a way that it is an expert system that looks for decision make with assertivity, and it looks forward to find which problems there are on site and then it wont happen problems of relationship among the utility and the customer unit. The database of an electrical company was utilized and the datas from it were worked by the fuzzy proposal and algorithm developed and the result was confirmed

Separação cega de fontes lineares e não lineares usando algoritmo genético, redes neurais artificiais RBF e negentropia de Rényi como medida de independência

Conventional methods to solve the problem of blind source separation nonlinear, in general, using series of restrictions to obtain the solution, often leading to an imperfect separation of the original sources and high computational cost. In this paper, we propose an alternative measure of independence based on information theory and uses the tools of artificial intelligence to solve problems of blind source separation linear and nonlinear later. In the linear model applies genetic algorithms and Rényi of negentropy as a measure of independence to find a separation matrix from linear mixtures of signals using linear form of waves, audio and images. A comparison with two types of algorithms for Independent Component Analysis widespread in the literature. Subsequently, we use the same measure of independence, as the cost function in the genetic algorithm to recover source signals were mixed by nonlinear functions from an artificial neural network of radial base type. Genetic algorithms are powerful tools for global search, and therefore well suited for use in problems of blind source separation. Tests and analysis are through computer simulations

Otimização de Algoritmos Criptográficos para Redes de Sensores e Atuadores Sem-fio para Poços do Tipo Plunger Lift

Wireless sensors and actuators Networks specified by IEEE 802.15.4, are becoming increasingly being applied to instrumentation, as in instrumentation of oil wells with completion Plunger Lift type. Due to specific characteristics of the environment being installed, it s find the risk of compromising network security, and presenting several attack scenarios and the potential damage from them. It`s found the need for a more detailed security study of these networks, which calls for use of encryption algorithms, like AES-128 bits and RC6. So then it was implement the algorithms RC6 and AES-128, in an 8 bits microcontroller, and study its performance characteristics, critical for embedded applications. From these results it was developed a Hybrid Algorithm Cryptographic, ACH, which showed intermediate characteristics between the AES and RC6, more appropriate for use in applications with limitations of power consumption and memory. Also was present a comparative study of quality of security among the three algorithms, proving ACH cryptographic capability.

Maximização da penetração da geração distribuída através do algoritmo de otimização nuvem de partículas

This work develops a methodology for defining the maximum active power being injected into predefined nodes in the studied distribution networks, considering the possibility of multiple accesses of generating units. The definition of these maximum values is obtained from an optimization study, in which further losses should not exceed those of the base case, i.e., without the presence of distributed generation. The restrictions on the loading of the branches and voltages of the system are respected. To face the problem it is proposed an algorithm, which is based on the numerical method called particle swarm optimization, applied to the study of AC conventional load flow and optimal load flow for maximizing the penetration of distributed generation. Alternatively, the Newton-Raphson method was incorporated to resolution of the load flow. The computer program is performed with the SCILAB software. The proposed algorithm is tested with the data from the IEEE network with 14 nodes and from another network, this one from the Rio Grande do Norte State, at a high voltage (69 kV), with 25 nodes. The algorithm defines allowed values of nominal active power of distributed generation, in percentage terms relative to the demand of the network, from reference values

Uma contribuição à solução do problema dos k-servos usando aprendizagem por reforço

Neste trabalho é proposto um novo algoritmo online para o resolver o Problema dos k-Servos (PKS). O desempenho desta solução é comparado com o de outros algoritmos existentes na literatura, a saber, os algoritmos Harmonic e Work Function, que mostraram ser competitivos, tornando-os parâmetros de comparação significativos. Um algoritmo que apresente desempenho eficiente em relação aos mesmos tende a ser competitivo também, devendo, obviamente, se provar o referido fato. Tal prova, entretanto, foge aos objetivos do presente trabalho. O algoritmo apresentado para a solução do PKS é baseado em técnicas de aprendizagem por reforço. Para tanto, o problema foi modelado como um processo de decisão em múltiplas etapas, ao qual é aplicado o algoritmo Q-Learning, um dos métodos de solução mais populares para o estabelecimento de políticas ótimas neste tipo de problema de decisão. Entretanto, deve-se observar que a dimensão da estrutura de armazenamento utilizada pela aprendizagem por reforço para se obter a política ótima cresce em função do número de estados e de ações, que por sua vez é proporcional ao número n de nós e k de servos. Ao se analisar esse crescimento (matematicamente, ) percebe-se que o mesmo ocorre de maneira exponencial, limitando a aplicação do método a problemas de menor porte, onde o número de nós e de servos é reduzido. Este problema, denominado maldição da dimensionalidade, foi introduzido por Belmann e implica na impossibilidade de execução de um algoritmo para certas instâncias de um problema pelo esgotamento de recursos computacionais para obtenção de sua saída. De modo a evitar que a solução proposta, baseada exclusivamente na aprendizagem por reforço, seja restrita a aplicações de menor porte, propõe-se uma solução alternativa para problemas mais realistas, que envolvam um número maior de nós e de servos. Esta solução alternativa é hierarquizada e utiliza dois métodos de solução do PKS: a aprendizagem por reforço, aplicada a um número reduzido de nós obtidos a partir de um processo de agregação, e um método guloso, aplicado aos subconjuntos de nós resultantes do processo de agregação, onde o critério de escolha do agendamento dos servos é baseado na menor distância ao local de demanda

Estratégias baseadas em aprendizado para coordenação de uma frota de robôs em tarefas cooperativas

In multi-robot systems, both control architecture and work strategy represent a challenge for researchers. It is important to have a robust architecture that can be easily adapted to requirement changes. It is also important that work strategy allows robots to complete tasks efficiently, considering that robots interact directly in environments with humans. In this context, this work explores two approaches for robot soccer team coordination for cooperative tasks development. Both approaches are based on a combination of imitation learning and reinforcement learning. Thus, in the first approach was developed a control architecture, a fuzzy inference engine for recognizing situations in robot soccer games, a software for narration of robot soccer games based on the inference engine and the implementation of learning by imitation from observation and analysis of others robotic teams. Moreover, state abstraction was efficiently implemented in reinforcement learning applied to the robot soccer standard problem. Finally, reinforcement learning was implemented in a form where actions are explored only in some states (for example, states where an specialist robot system used them) differently to the traditional form, where actions have to be tested in all states. In the second approach reinforcement learning was implemented with function approximation, for which an algorithm called RBF-Sarsa($lambda$) was created. In both approaches batch reinforcement learning algorithms were implemented and imitation learning was used as a seed for reinforcement learning. Moreover, learning from robotic teams controlled by humans was explored. The proposal in this work had revealed efficient in the robot soccer standard problem and, when implemented in other robotics systems, they will allow that these robotics systems can efficiently and effectively develop assigned tasks. These approaches will give high adaptation capabilities to requirements and environment changes.