PROGRAMA DE PÓS GRADUAÇÃO EM ENGENHARIA DE ELETRICIDADE - PPGEE

URI Permanente desta comunidadehttps://tedebc-teste.ufma.br/handle/tede/279

Navegar

Agora exibindo 1 - 20 de 43

UM MÉTODO PARA ELICITAÇÃO E MODELAGEM DE REQUISITOS BASEADO EM OBJETIVOS
(Universidade Federal do Maranhão, 2002-03-27) CARVALHO, Márcia Cristina Ferro; ABDELOUAHAB, Zair; CPF:61438154372; http://lattes.cnpq.br/3277510464047127
This work proposes an integration of the approach CREWS L ecritoire based on scenarios with the approach of use cases described by Regnell & al and the Method GBRAM. In this case, the work of Regnell is extended with the notion of Requirement Chunk (RC), strategies for discovering objectives through the relationships AND, OR, and refinement between RCs, as well as extending the model with a physical level where the internal actions of the system are described. On the other side, the approach CREWS L ecritoire is extended with coupling of objective and use case where the scenarios are obtained by applying a strategy of refining use cases, and also with an integration of normal and exceptional scenarios in one synthetic model of use with one unique vision for each actor. The Method GBRAM is extended with the alternative contract dependency, composicional contract dependency, inclusive and exclusive contract dependency, as well it introduzed the use case technique, described by Regnell et al and extended with the notion of scenarios for caracterize exceptionals, variationals and normal situations. With the integration of threes methods, the new method which benefit from the advantages of the approaches of CREWS-L ecritoire, use cases.and goals. The new method proposes a coupling between objective and Use Cases in a top-down decomposition of different levels of abstraction. The method combines the two concepts into a Requirement Chunk (RC). An RC is a pair of related with AND, OR and refinement. These three types of relations between RCs lead to a hierarchic organisation of RCs in three levels of abstractions: functional, behaviour, and physical.
ALOCAÇÃO ÓTIMA DE CAPACITORES EM SISTEMAS DE DISTRIBUIÇÃO RADIAL, UTILIZANDO-SE ESTRATÉGIAS EVOLUTIVAS
(Universidade Federal do Maranhão, 2002-05-29) Petinelli, Airton Egydio; SAAVEDRA MENDEZ, Osvaldo Ronald; CPF:10813804892; http://lattes.cnpq.br/6400934417933768
Static reactive power sources, such as shunt capacitors, have been commonly used to provide reactive compensation in distribution systems, minimizing losses and keeping voltage levels within operational limits. Heuristic algorithms for capacitor placement have been proposed in several works. However, the majority of these approaches converge to a local solution. This dissertation presents a hierarchical evolution strategy-based approach for solving the optimal reactive sources placement in radial distribution systems. The approach is based on the (m+l)-EE paradigm, improved by mutations control and by two types of mutations: the classical Gaussian mutation and the Cauchy-based mutation. Discrete standard capacitor values with non-linear cost are considered. Constraints such as the maximum number of parallel banks and installations cost are included. Validation tests have been performed using a real industrial feeder.
Filtragem robusta de trajetórias de veículos espaciais.
(Universidade Federal do Maranhão, 2002-12-13) Abreu, José Alano Péres de; COSTA FILHO, José Tarcisio; CPF:21155178300
In this work, a new methodology of filtering data of paths of space vehicles is proposed H2 and H∞ saw state estimates and discreet. In that new methodology, it is obtained, initially, the solution of the problem of filtering of data of paths of space vehicles saw state estimate through the equations of the filter of Kalman for Predicted Estimators and Filtered Estimators. The problem is solved through the mathematical development of the equations of the filter of Kalman that has as main function, to find a state estimate that minimizes the least-squares error. The equations mathematics are used for the development of the algorithm of the filter of Kalman. The algorithm of filtering of Kalman has two basic functions: prediction and correction. In the prediction phase the initial estimates and updating of the time of sampling are given, while, in the correction phase they are updated the measures. It is applied, also, the new methodology proposed in the project of filtering of data of path of space vehicles H∞ saw state estimate through equations of robust filter. The robust filtering has as function to esteem a linear combination that minimizes the norm, that has the interpretation of the existence of earnings of maximum energy of the entrance for the exit. In addition, it is obtained a new algorithm for filtering of data of paths of space vehicles, now through state estimate. All the project procedures are cultured through some applied examples to systems of tracking of space vehicles. The results are compared and discussed.
SISTEMA ESPECIALISTA PARA IDENTIFICAÇÃO DE FALHAS E TOMADA DE DECISÃO
(Universidade Federal do Maranhão, 2003-04-15) Moura, José Pinheiro de; Labidi, Sofiane; CPF:61878782300; http://lattes.cnpq.br/3474810859116416; FONSECA NETO, João Viana da; CPF:2199749048; http://lattes.cnpq.br/0029055473709795
In this work is presented the development and implementation of an Expert System to detect faults and decision making over the faults of mineral belt conveyors. This system applies artificial intelligence techniques to help the operator s decision making during the production process. It uses the CommonKADS reference methodology for knowledge acquisition and modeling. In this approach is also emphasized the difficulties in getting accurate and qualitative information, to support the decision making, and provide the users with highly trustable mechanisms able to analyze, select and drive to them the right information, meeting the demanded requisites for optimum performance during the operation of the belt conveyor.
WORKFLAGE: uma ferramenta de definição e criação de Workflow baseado em agentes de software para WEICOT
(Universidade Federal do Maranhão, 2003-11-26) Fialho, Hugo Sampaio; LABIDI, Sofiane; CPF:61878782300; http://lattes.cnpq.br/3474810859116416
The Workflow Management Systems (WfMS) have been used in many organizations with the objective of reducing, improve and control the workflow in their internal process. Current WfMS are, usually, designed to the administration of loosely structured businesses process, where the logical flow of the tasks totally predefined. However, not all business processess are like this. With the coming of the new communication technologies among the 6 organizations, the business environment becoming more and more dynamic demanding more complex processes. Considering this scenario, existent WfMS have some disadvantages and limitations and need improvements and modifications. Many researchers have been exploring the power of software agent's technology to provide solutions for current WfMS. There are several approaches, some are improvements with agents, another are based on agents. In this work we present the WorkFlage as a tool for the development Workflow Management Systems based on to technologies of Software Agents for the model proposed by the project WEICOT. The work is organized in 9 chapters where we cover from the technology of Workflow, going through a summary of the agents' technology, the state of the art in workflow based on agents, to case stud y of materials purchase where we demonstrate the application of the WorkFlage tool. At the end of this work we will make some final considerations where we propose improvements and suggestions for future works.
MINIMIZAÇÃO DO CUSTO DO SERVIÇO DE POTÊNCIA REATIVA FORNECIDA PELOS GERADORES LEVANDO EM CONTA A RESERVA DE POTÊNCIA
(Universidade Federal do Maranhão, 2005-03-04) Rodríguez, Yuri Percy Molina; SAAVEDRA MENDEZ, Osvaldo Ronald; CPF:10813804892; http://lattes.cnpq.br/6400934417933768
In the operation of the power transmission system the problems of voltage/reactive power can occur at any time due the contingencies and/or alterations in the demand. Therefore, reactive services are necessary to perform the control in relatively small time periods to improve the operation state and avoid the degradation of the security and the reliability of the system.The ancillary service of reactive power can be contracted by the System Independent Operator of agents connected to the Electrical system, such as generators, capacitor/reator banks, static VAR compensators static, compensators synchronous, among others.The present work proposes a methodology for minimizing the price of the reactive power service considering the coupling between this ancillary service and the power reserve service and the power market as well. For evaluation of the performance, it is considering the method of payment for reserve allocated for service of reserve power, and tests to evaluate its impact in the cost of the reactive power by using the IEEE 14-buses and IEEE 30-buses test systems, are performed. Discussions and relevant conclusions are also reported.
Estudo da Utilização de Mecanismos de QoS em Redes com Enlaces de Banda Estreita
(Universidade Federal do Maranhão, 2005-03-14) MELO, José Coelho de; ABDELOUAHAB, Zair; CPF:61438154372; http://lattes.cnpq.br/3277510464047127
This work presents several ways of using mechanisms of Quality of Service (QoS) in networks hardwired for links of short band. It is demonstrated that the use of mechanisms of QoS brings profits of performance for priority applications and rationality in the use of band resources. The work is developed in a test platform of Previdência Social. Implementations of the PHBs EF, Afs and BE are tested. The work has evaluated the capacities to offer guaranteed band, traffic priority, conditioning of traffic and the impact of the competition between traffic classes. The experiments are mounted using the architecture of differentiated services (DiffServ) of platform Cisco, that is the standard in the network of the Previdência Social and are manipulated the mechanisms of classification, control of congestion, policing and conformation of traffic. The results give subsidy for implementation of some models of QoS in IP networks, mainly for those that serve short band.
Análise da Confiabilidade em Redes de Distribuição Radiais: Reconfiguração e Alocação de Geração Distribuída
(Universidade Federal do Maranhão, 2006-03-10) Coelho Neto, Agnelo; SILVA, Maria da Guia da; CPF:09837418400; http://lattes.cnpq.br/5175196133230969
The distribution utilities must satisfy two concurrent objectives during planning process of the electric network: minimization of the investment cost and the satisfaction of reliability targets. An alternative to satisfy these objectives is to include low cost alternatives in the planning process. One of these alternatives is the reconfiguration of the distribution network. The reconfiguration of the distribution network can reduce the loss and balance the loads in the system only with opening and closing of switches without additional investment cost. In addition to reconfiguration, another alternative of low cost is the Distributed Generation (DG) allocation. This alternative became feasible due to the recent technological advances in the building of turbines that reduced significantly the costs of energy generation. In this way, the DG is a attractive option to satisfy the demand growth and minimize the costs associated with: building of new substations, feeder reconductoring and transformer upgrading. Consequently, is opportune to develop methodologies that include the reconfiguration and the DG in the planning of the distribution network. This dissertation presents the development of two methodologies for the planning of distribution networks: reconfiguration and optimal allocation of DG. The first part of the dissertation presents the development of the methodology for the network reconfiguration. Usually, the reconfiguration is carried out with the following objectives: minimization of the electric losses, voltage profile correction and load balancing between feeders. In this dissertation, in addition to these objectives, reliability constraints have been included in the reconfiguration methodology. This methodology is based on the combination of the following techniques: power flow algorithm, based on the Power Summation Method, to estimate the state of the network; analytic techniques to estimate the reliability indices and Tabu Search to identify the optimal topology. The second part of the research work presents the development of the methodology for the allocation of DG. This methodology has as objective to attend a forecasted demand level without violating operational constraints of the network (feeders loading and voltage drops) and minimizing the interruption costs through the DG allocation. These objectives are satisfied minimizing the cost/worth ratio between the installation/operation costs of DG and the costs associated with: interruptions, noncommercialized, energy purchases and electric losses. The minimization of the cost/worth ratio described above has been carried out by combining the following techniques: analytic approaches to estimate the impact of DG in the reliability indices, load flow algorithm to estimate the losses and violations in the operational constraints and genetic algorithms to maximize the cost worth ratio. The impact of the DG in the reliability indices has been considered including network constraints (voltage drop and feeder loading) in the predictive reliability model. The models and techniques proposed in this dissertation for the reconfiguration and DG allocation have been validated and applied in two large scale substations belonging to distribution network of the Electricity Utility of Maranhão - CEMAR. The results obtained with the algorithm of reconfiguration demonstrated that the proposed methodology was capable of reducing the losses in the feeders without deteriorating the reliability. Furthermore, the application of the methodology of DG allocation in the test system resulted in a cost/worth ratio lower than one.
Classificação de Lesões em Mamografias Digitais Utilizando Análise de Componentes Independentes e Perceptron Multicamadas
(Universidade Federal do Maranhão, 2006-03-24) Campos, Lucio Flavio de Albuquerque; BARROS FILHO, Allan Kardec Duailibe; CPF:34022589353; http://lattes.cnpq.br/0492330410079141
We propose a method for discrimination and classification of mammograms with benign, malignant and normal tissues using independent component analysis and neural networks. The method was tested for a mammogram set from MIAS database, and multilayer perceptron. The method obtained a success rate of 97.83% , with 97.5% of specificity and 98% of sensitivity.
Comunicação Segura e Confiável para Sistemas Multiagentes Adaptando Especificações XML
(Universidade Federal do Maranhão, 2006-12-01) OLIVEIRA, Emerson José Santos; ABDELOUAHAB, Zair; CPF:61438154372; http://lattes.cnpq.br/3277510464047127
Multi-agent systems are evolving to enterprise applications and they are more used in open environments, such as the Internet. Many issues should be considered with this evolution, like security and reliability of communication. In this work, we propose a solution for secure communication and a solution for a reliable communication; both solutions are for multi-agent systems. These solutions adapt XML technologies and consist of several XML Specifications and RDF standard. For secure communication, we adapt the XML-DSig specification to provide integrity and digital signature; the XMLEnc specification is used to provide confidentiality through encryption, and the XKMS specification is used to provide PKI support. For reliable communication, we adapt the WS-RM specification that guarantees the message delivery. The RDF standard enables agents for exchanging messages using XML syntax. In this work, the tests with prototypes of the proposed solutions and comparisons with other solutions are also presented.
PROPOST: UMA FERRAMENTA BASEADA EM CONHECIMENTO PARA GESTÃO DE PORTIFÓLIO DE PROJETOS.
(Universidade Federal do Maranhão, 2007-02-12) VIEIRA, Eduardo Newton Oliveira; GIRARDI, Rosario; 590.437.170-53; http://lattes.cnpq.br/5317074159250496; GIRARDI GUTIÉRREZ, Maria Del Rosario; http://lattes.cnpq.br/5317074159250496; ABDELOUAHAB, Zair; COSTA, Evandro de Barros; http://lattes.cnpq.br/5760364940162939
This work introduces PROPOST (Project Portfolio Support Tool), a knowledgebased software tool for supporting Project Portfolio Management – an increasing management model nowadays. This tool focuses on a project definition process, and was modeled using the MAAEM methodology and the ONTORMAS ontology-driven tool, as well as by reusing the ONTOINFO and ONTOWUM ontologies, which describe software product families for the development of Information Retrieval and Filtering applications, respectively. PROPOST looks for providing resource optimization by supporting reuse of existing information systems as well as avoiding duplicity on project definition for the composition on the organization’s software portfolio. The tool was created not only as a contribution for solving a current problem related to redundancy on portfolio definition, as well as support for several activities related to portfolio management (select, prioritization and evaluation). The development of PROPOST provides references on how ontology-based development can help in the software development process. It also contributes as a case study for evaluating the MAAEM methodology and the ONTORMAS ontology used in modeling process, having provided several hints for their improvement.
MECANISMO DE AUXÍLIO AO PROFESSOR PARA O AMBIENTE NETCLASS DE ENSINO-APRENDIZAGEM.
(Universidade Federal do Maranhão, 2007-06-18) BRANDÃO NETO, PEDRO; MARTINS, Ademir; LABIDI, Sofiane; 618.787.823-04; http://lattes.cnpq.br/3474810859116416
Distance Education environments, nowadays, provide means for learner evaluation. This task, still, requires effort of the teacher. So, the learner accompaniment in distance teaching-learning environments, obtained through the observation of the learner activities, it presents referring problems to the lack of mechanisms that offer an effective support to the teacher in the orientation for the learner. These existent mechanisms only present results to the teacher without to do any inference, like this, self teacher needs to analyze those results manually in search of subsidies to do a precise orientation, showing the possible causes and addressing the learner for the correct road. However, to dower a mechanism with inference capacity is necessary to capture the knowledge of as the teacher fulfills the leaner accompaniment for, later, to transfer this knowledge for a knowledge base with inference capacity. The necessary knowledge for the teacher to realize the learner accompaniment in a teaching-learning environment is the evaluation criterions that are defined by course pedagogic coordination or teacher of the teaching institution. However, those evaluation criterions are generic and not standardized hindering, therefore, the consent of the same; was realized a theoretical rising for the definition of the evaluation criterions in the NetClass environment. This research generated the knowledge on the development of a model denominated Learner Accompaniment Support Mechanism based on techniques of Artificial Intelligence, which is applied to the NetClass environment of teaching-learning.
Circuito de Condicionamento de Sinais Analógicos Programável para Sistemas Integrados
(Universidade Federal do Maranhão, 2007-09-05) Belfort, Diomadson Rodrigues; CATUNDA, Sebastian Yuri Cavalcanti; CPF:76867668453; http://lattes.cnpq.br/0873496251879638
In digital measurement systems, signal conditioning circuits have the main functionality of adjusting analog signals for digital conversion. For maximizing the application of a measurement circuit or system, yet considering its integration in a single chip, these circuits must be programmable, in order to serve to different kinds of sensors with diverse output signal characteristics. The main functions of the signal conditioning circuit, in this case, are the amplification and dc level shift of the analog signal. In this master s thesis, an architecture of a signal conditioning integrated circuit with programmable gain and dc level shift, optimized in number of discrete components, using the switched capacitor technique is proposed. The proposed architecture allows the circuit use in differential and single-ended modes, with unipolar and bipolar signals. The design of an integrated circuit is carried out for implementing the proposed architecture using 0.35 mm TSMC CMOS technology, available in the ASIC design kit (ADK) of the Mentor Graphics, IC Nanometer software package.
Conservação de energia elétrica: um enfoque em consumidores residenciais
(Universidade Federal do Maranhão, 2008-04-25) Silva, Paulo Roberto Mendes da; PESSANHA, José Eduardo Onoda; CPF:80603190782; http://lattes.cnpq.br/8268655137736254
This work investigates the most used forms of electric energy conservation, especially in Brazil, without neglecting the power quality aspect, emphasizing residential loads. Among the investigated issues, the technological is a very important one since it comprises the application of efficient equipment. However, it is not forgotten the human actions, with great application in the residential point of view. Power quality practical studies involving lightning residential loads are also presented. These studies were carried out with a lab prototype capable of simulating power quality problems, such as momentary and long-term voltage sags. Electrical parameters were monitored trough a power quality analyzer equipment - DRANETZ 4300. The results show that the consumer may not acquire a product (compact efficiency light in this case) according to the manufacturer specifications, being very far from the label specifications. The main objective was, therefore, to study the efficiency energy concepts actions and energy savings, associating them to the cost reduction related to electrical energy and the continuous improvement in cost management taking into account the power quality aspect.
MODELAGEM E IMPLEMENTAÇÃO DE UM SISTEMA MULTIAGENTE PARA SELEÇÃO DE FALHAS E TOMADA DE DECISÃO EM VIRADORES DE VAGÕES.
(Universidade Federal do Maranhão, 2009-02-09) FARIAS, Osevaldo da Silva; LABIDI, Sofiane; 618.787.823; http://lattes.cnpq.br/3474810859116416; FONSECA NETO, João Viana da
This work leads to the modeling and implementation of a multi-agent application of faults selection and decision making for VALE’s rotary railcar dumpers. The work explore development approaches and knowledge-based achtectures aiming to SADDEM build, a multi-agent system applyed to decision making in ore unload cells. The particularities of cognitives agents structures are based on Jess inference engine in order to link decisions and maintain plans recommendations made by the system. The ontology is developed throught elicitation of information and knowledge during interviews and VV311-K01 car positioner set operating activities. The artifacts produced during the development clycle phases employs PASSI methodology technics, Artificial Intelligence and support engineering to software development using JADE framework. The real time module is linked to the software of supervision and monitoring of the unloading cell productions of VALE.
MADAE-PRO: UM PROCESSO BASEADO NO CONHECIMENTO PARA ENGENHARIA DE DOMÍNIO E DE APLICAÇÕES MULTIAGENTE.
(Universidade Federal do Maranhão, 2009-02-17) COSTA, Adriana Leite; GIRARDI, Rosario; 590.437.170-53; http://lattes.cnpq.br/5317074159250496
The interest in the agent-oriented paradigm development has increased in recent years. This is due mainly to the increasing complexity of current software that requires new characteristics as autonomy behavior. In the agent-oriented paradigm, the software has no longer a strictly predictable behavior, has from the control over their own behavior and can make decisions based on observations the environment and inferences upon its knowledge base. A set of meth and process have been already proposed for agent-oriented software engineering. Domain Engineering is a process for the development of a reusable application family in a particular domain problem, and Application Engineering, the one for the construction of a specific application in a family based on the reuse of software artifacts in the application family previously produced in the Domain Engineering process. MADAE-Pro is an ontology-driven process for multi-agent domain and application engineering which promotes the construction and reuse of agent-oriented applications families. The process is specified in a formal representation language, thus avoiding ambiguous interpretations. Another differential of MADAE-Pro is the reuse of software support in all levels of abstraction, from the requirements to the deployment.
DEFINIÇÃO DE UMA ARQUITETURA P2P BASEADA EM REPUTAÇÃO E ORIENTADA A SERVIÇOS
(Universidade Federal do Maranhão, 2009-05-04) RAMOS, Flávio Marcílio Paiva; ABDELOUAHAB, Zair; CPF:61438154372; http://lattes.cnpq.br/3277510464047127
Nowadays, peer-to-peer networks are very popular mainly, when we wish to search or share a considerable amount of information and resources among various participants. One of the main difficulties of this technology is how to avoid that those participants maintain, at the same time, a considerable number of shared resources and to guarantee that those resources are not corrupted or polluted content. Another problem commonly found in P2P networks is the lack of interoperability among existing P2P solutions especially because the inconsistencies of metadata and operation interfaces used in node communication. This work describes P2PWSRep, a reputation management protocol that identifies non-cooperative nodes or that can hinder network performance by sharing corrupted, infected or non-existent files. P2PWSRep infrastructure was based on web services in order to tackle interoperability problems and to facilitate its extensibility, making it feasible to be accessed by several other P2P applications. The P2PWSRep protocol employs a distributed reputation computation using an exponentially weighted average that takes into account the current and previous node reputation and which is tuned by an adjustment parameter in order to obtain the final reputation, thus considering the node s behavior. The P2PWSRep protocol is validated by means of simulation and our results show that it is able to point out the more trustable nodes in the network as well as to insulate those which are not reliable or cooperative. Besides, the protocol does not unnecessarily impacts on the network load P2PWS.
SISTEMA MULTIAGENTE PARA MONITORAMENTO AMBIENTAL DO COMPLEXO PORTUÁRIO DA ILHA DE SÃO LUÍS-MARANHÃO
(Universidade Federal do Maranhão, 2009-11-04) Farias, Luciana Fortes; LABIDI, Sofiane; CPF:61878782300; http://lattes.cnpq.br/3474810859116416
This work is discussed the conceptual model of a multi-agent system for environmental monitoring with the use of biomarkers of aquatic organisms present in the port complex of São Luís-Maranhão-Brasil, second most important in the country in cargo handling. Located in the São Marcos Bay, this complex have an estuarine ecosystems which have suffered attacks in the current process of economic development, caused by intense port handling, dumping of ballast water and washing the vessels, overfishing, introduction of exotic species in the middle pollution in urban and industrial effluents, subject to severe environmental impacts that should be monitored. Methodologically, the modeling of the monitoring solution, we used the existing environmental conditions and aquatic life caught in two different sites of the port complex, the first in a potentially contaminated area and the second in a contamination-free (control), proposing the creation of a network of sensors in these locations. Invest conceded data by Carvalho-Neta (2007) whose research includes to catch fish in these perimeters, then submitting them for laboratory analysis to measure the enzyme activity of glutathione S-transferase (GST) and Catalase (CAT), the result was processed and recorded in bio-ontology . The core of the solution of Multi-agent system is based on the results derived from the biochemical analysis of GST, inspiring the modeling software agent that simulates the behavior of this enzyme. The solution also includes an application running on mobile devices that makes the collection of environmental variables in the selected points, validates them and makes the inference of those who could not be collected. Multi-agent System for Environmental Monitoring of the Port Complex of the Island of São Luís-Maranhão- Brasil, therefore, is made up of the bio-ontology, sensor networking, mobile application collection and inference of data from environmental conditions, software agents to simulate biochemical analysis, calculation of GST activity and other staff related to the maintenance and security of the SMA.
COMPOSIÇÃO DINÂMICA DE SERVIÇOS WEB SEMÂNTICOS UTILIZANDO ABORDAGENS DA ENGENHARIA DIRIGIDA POR MODELOS
(Universidade Federal do Maranhão, 2011-07-29) BEZERRA, Eduardo Devidson Costa; Lopes, Denivaldo Cícero Pavão; CPF:61364371391; http://lattes.cnpq.br/7611180871627212; ABDELOUAHAB, Zair; CPF:61438154372; http://lattes.cnpq.br/3277510464047127
The use of the Internet as a way to publish new applications and deliver new functionalities has consolidated the use of web services technology. Once web services technology enables a high degree of autonomy and interoperability, it provides a basic infrastructure for the development and composition of new services, which has benefited the business process management providing the agility required by enterprises to meet the need of rapidly changing business environment. Recently, new paradigms are being developed to deal with the increasing complexity in the development, maintenance and evolution of software systems. Among the new paradigms, Model Driven Engineering (MDE) and the Ontology stands out as the most promising for handling complex software systems. This work presents an approach to perform the dynamic composition of web services using techniques of match models (metamodels) that represent services. Models representing services must include semantic and structural aspects of the web service achieved through approaches to ontologies. Thus, we conjecture to establish matchings and measure the degree of similarity between models and investing in research about Ontologies and MDE in order to generate a tool that can assist in a Dynamic Composition of Web Services. A case study is presented to illustrate this approach.
EXTRAÇÃO CEGA DE SINAIS COM ESTRUTURAS TEMPORAIS UTILIZANDO ESPAÇOS DE HILBERT REPRODUZIDOS POR KERNEIS
(Universidade Federal do Maranhão, 2012-02-10) Santana Júnior, Ewaldo éder Carvalho; BARROS FILHO, Allan Kardec Duailibe; CPF:34022589353; http://lattes.cnpq.br/0492330410079141
This work derives and evaluates a nonlinear method for Blind Source Extraction (BSE) in a Reproducing Kernel Hilbert Space (RKHS) framework. For extracting the desired signal from a mixture a priori information about the autocorrelation function of that signal translated in a linear transformation of the Gram matrix of the nonlinearly transformed data to the Hilbert space. Our method proved to be more robust than methods presented in the literature of BSE with respect to ambiguities in the available a priori information of the signal to be extracted. The approach here introduced can also be seen as a generalization of Kernel Principal Component Analysis to analyze autocorrelation matrices at specific time lags. Henceforth, the method here presented is a kernelization of Dependent Component Analysis, it will be called Kernel Dependent Component Analysis (KDCA). Also in this dissertation it will be show a Information-Theoretic Learning perspective of the analysis, this will study the transformations in the extracted signals probability density functions while linear operations calculated in the RKHS.

Navegar

Navegando PROGRAMA DE PÓS GRADUAÇÃO EM ENGENHARIA DE ELETRICIDADE - PPGEE por Data de Publicação