In the domain of Web Services, it is not uncommon to find redundant services that provide functionalities to the clients. Services with the same functionality can be clustered into a group of redundant services. Respectively, if a service offers different functionalities, it belongs to more than one group. Having various Web Services that are able to handle the client's request suggests the necessity of a mechanism that selects the most appropriate Web Service at a given moment of time. <p>This thesis presents an approach, Virtual Web Services Layer, for dynamic service selection based on virtualization on the server side. It helps managing redundant services in a transparent manner as well as allows adding services to the system at run-time. In addition, the layer assures a level of security since the consumers do not have direct access to the Web Services. <p>Several selection techniques are applied to increase the performance of the system in terms of load-balancing, dependability, or execution time. The results of the experiments show which selection techniques are appropriate when different QoS criteria of the services are known and how the correctness of this information influences on the decision-making process.

In the domain of Web Services, it is not uncommon to find redundant services that provide functionalities to the clients. Services with the same functionality can be clustered into a group of redundant services. Respectively, if a service offers different functionalities, it belongs to more than one group. Having various Web Services that are able to handle the client's request suggests the necessity of a mechanism that selects the most appropriate Web Service at a given moment of time. <p>This thesis presents an approach, Virtual Web Services Layer, for dynamic service selection based on virtualization on the server side. It helps managing redundant services in a transparent manner as well as allows adding services to the system at run-time. In addition, the layer assures a level of security since the consumers do not have direct access to the Web Services. <p>Several selection techniques are applied to increase the performance of the system in terms of load-balancing, dependability, or execution time. The results of the experiments show which selection techniques are appropriate when different QoS criteria of the services are known and how the correctness of this information influences on the decision-making process.

Submitted by Regis Albuquerque (regis.albuquerque1@gmail.com) on 2018-06-20T21:40:28Z No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) dissertacao_regis_corrigida_final.pdf: 2557634 bytes, checksum: b48eb7c37fd9dd633c4489a7f0f041a4 (MD5) / Approved for entry into archive by Secretaria PPGI (secretariappgi@icomp.ufam.edu.br) on 2018-06-20T21:52:37Z (GMT) No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) dissertacao_regis_corrigida_final.pdf: 2557634 bytes, checksum: b48eb7c37fd9dd633c4489a7f0f041a4 (MD5) / Approved for entry into archive by Divisão de Documentação/BC Biblioteca Central (ddbc@ufam.edu.br) on 2018-06-21T13:29:00Z (GMT) No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) dissertacao_regis_corrigida_final.pdf: 2557634 bytes, checksum: b48eb7c37fd9dd633c4489a7f0f041a4 (MD5) / Made available in DSpace on 2018-06-21T13:29:01Z (GMT). No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) dissertacao_regis_corrigida_final.pdf: 2557634 bytes, checksum: b48eb7c37fd9dd633c4489a7f0f041a4 (MD5) Previous issue date: 2018-06-08 / FAPEAM - Fundação de Amparo à Pesquisa do Estado do Amazonas / Many machine learning applications have to deal with classification problems in dynamic environments. This type of environment may be affected by concept drift, which may reduce the accuracy of classification systems significantly. In this context, methods using ensemble of classifiers are interesting due to the fact that ensembles of classifiers allow the design of strategies for drift detection and reaction more accurate and robust to changes. A classification system based on ensemble of classifiers may be divided into three main phases: classifier generation; single classifier or subset of classifier selection; and classifier fusion. The selection phase may be performed as a dynamic process. In this case, for each unknown sample, the individual classifier or classifier ensemble most likely to be correct is chosen to assign a label to the sample. In this work, it is proposed a method for concept drift detection and reaction based on dynamic classifier ensemble selection. The proposed method choses the expert classifier ensemble according to diversity and accuracy values. Focusing on evaluating the impact of dynamic ensemble selection guided by diversity and accuracy in terms of concept drift detection and reaction, four series of experiments were carried in this work using both synthetic and real datasets. In addition, since the proposed method is broken down into four phases: pool of ensemble classifiers generation; dynamic ensemble selection; drift detection; and drift reaction, different versions of the proposed method were investigated by varying the parameters of each phase. The results show that, in general, all these different versions attain very similar accuracy values. Besides, when compared to two baselines: (1) DDM - single classifier-based; and (2) Leveraging Bagging - classifier ensemble-based, our method outperforms both baselines since it achieved higher accuracy, lower detection delay and false detection rates, and it did not present missing detection. However, both baselines present lower time complexity. Therefore, this work shows that dynamic classifier ensemble selection guided by diversity and accuracy helps to improve detection precision and the general accuracy of classification systems employed in problems with concept drift. / Muitas aplicações de aprendizado de máquina estão relacionadas com problemas de classificação em ambientes dinâmicos. Mudança de conceito figura nesse tipo de ambiente e pode prejudicar muito a acurácia de sistemas de classificação. Nesse contexto, a utilização de comitês de classificadores é interessante porque possibilita a implementação de processos de detecção e de reação à mudança mais acurados e robustos. Sistemas de classificação que utilizam comitês podem possuir três grandes fases: geração; seleção; e integração de classificadores. A etapa de seleção pode ser feita de forma dinâmica, isto é, para cada instância desconhecida, o classificador ou comitê de classificadores com maior probabilidade de acerto é escolhido para atribuir uma classe à essa instância. Neste trabalho, é proposto um método para detecção e reação à mudança de conceito que utiliza seleção dinâmica de comitês de classificadores. O método proposto escolhe o comitê especialista com base nos valores de diversidade e de acurácia de cada comitê candidato. A fim de avaliar o impacto do uso de seleção dinâmica guiada por diversidade e acurácia nas tarefas de detecção e reação a mudança de conceito, foram realizadas quatro séries de experimentos com bases sintéticas e reais. Além disso, como o método proposto é dividido em quatro fases: geração da população de comitês; seleção dinâmica do comitê especialista; detecção de mudanças; e reação à mudança, diferentes versões desse método foram investigadas em função da definição de parâmetros de cada fase. Os resultados dos experimentos mostraram que, de maneira geral, as versões estudadas são bem equivalentes em termos de acurácia média final. Adicionalmente, quando comparado a dois baselines: (1) DDM - que utiliza um único classificador; e (2) Leveraging Bagging - que utiliza um comitê de classificadores, o método proposto alcançou melhores taxas de acurácia, menores taxas de atraso de detecção, não deixou de detectar as mudanças conhecidas nas bases e produziu reduzidas taxas de falsa detecção, apesar de apresentar maior complexidade computacional. Portanto, o trabalho mostra que o uso de seleção dinâmica guiada por diversidade e acurácia melhora a precisão de detecção, bem como a acurácia geral de sistemas de classificação utilizados em problemas que apresentam mudança de conceitos.

Made available in DSpace on 2014-12-17T15:47:46Z (GMT). No. of bitstreams: 1 AndreGDA.pdf: 982503 bytes, checksum: 1c9c31b9670edd5ef9e3e725bb8f680b (MD5) Previous issue date: 2008-02-12 / &#65279;This work presents a proposal of a multi-middleware environment to develop distributed applications, which abstracts different underlying middleware platforms. This work describes: (i) the reference architecture designed for the environment, (ii) an implementation which aims to validate the specified architecture integrating CORBA and EJB, (iii) a case study illustrating the use of the environment, (iv) a performance analysis. The proposed environment allows interoperability on middleware platforms, allowing the reuse of components of different kinds of middleware platforms in a transparency away to the developer and without major losses in performance. Also in the implementation we developed an Eclipse plugin which allows developers gain greater productivity at developing distributed applications using the proposed environment / &#65279;Este trabalho apresenta a proposta de um ambiente multi-middleware para desenvolvimento de aplica??es distribu?das, o qual abstrai diferentes plataformas de middleware subjacentes. O trabalho descreve: (i) a arquitetura de refer?ncia especificada para o ambiente, (ii) uma implementa??o que valida tal arquitetura integrando CORBA e EJB, (iii) um estudo de caso ilustrando o uso do ambiente, (iv) a an?lise de desempenho. O ambiente proposto permite alcan?ar interoperabilidade de plataformas de middleware, promovendo o reuso de componentes de diferentes plataformas de forma transparente para o desenvolvedor e sem perdas expressivas em termos de desempenho. Na implementa??o desenvolvemos um plugin para IDE Eclipse que permite que os eventuais desenvolvedores obtenham maior produtividade ao desenvolver aplica??es usando o ambiente

Submitted by Fernando Souza (fernandoafsou@gmail.com) on 2017-08-15T13:33:40Z No. of bitstreams: 1 arquivototal.pdf: 1946583 bytes, checksum: 46b84a872476f284510477eeb33e3b91 (MD5) / Made available in DSpace on 2017-08-15T13:33:40Z (GMT). No. of bitstreams: 1 arquivototal.pdf: 1946583 bytes, checksum: 46b84a872476f284510477eeb33e3b91 (MD5) Previous issue date: 2016-08-30 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / Despite being a well-established technology, research inWireless Sensor Networks (WSNs) are facing challenges due to its intrinsic connection to the paradigms of Smart Cities and IoT (Internet of Things - IoT). Traditionally, WSNs are deployed to meet the needs of a single application and are composed of sensors with the same physical characteristics. However, when considering smart environments, where several objects can collect data, trigger actions and interact with each other in order to provide sophisticated services, it is easy to see the diversity of the applications that can perform requests in such environments. It is also possible that different types of equipment interact with each other, such as sensors with different physical characteristics, thus creating a Heterogeneous WSN (HWSN). For this reason, this work aims to contribute to the management of HWSNs in Smart Cities environments by proposing an approach for dynamic and on-demand selection of sensors. This selection is performed by taking into account the physical characteristics of the sensors and the applications’ demands. This approach has been integrated into the POlicy-based Sensor SElection in Heterogeneous Wireless Sensor Network framework (POSSE-HWSN), which was implemented in order validate the proposal. Tests have shown that by using POSSE-HWSN it was possible to select the sensors with the most suitable hardware features to meet every application needs, thus improving the selection efficacy. / Apesar de ser uma tecnologia já consolidada, pesquisas em Redes de Sensores Sem Fio (RSSFs) vêm passando por desafios devido à sua intrínseca relação com os paradigmas de Cidades Inteligentes e Internet das Coisas (Internet of Things - IoT). Tradicionalmente, as RSSFs são implantadas e utilizadas para atender a uma única aplicação e são compostas de nós sensores com as mesmas características físicas. Contudo, ao se considerar ambientes inteligentes, onde vários objetos podem coletar dados, desencadear ações e interagir entre si de forma a prover serviços sofisticados, é fácil perceber a heterogeneidade dos tipos de aplicações que podem realizar requisições em tais ambientes. Além disso, é real a possibilidade de interação entre diferentes tipos de equipamentos, como por exemplo, sensores com diferentes características físicas, criando assim uma RSSF Heterogênea (RSSFH). Por este motivo, este trabalho objetiva contribuir para a gerência de RSSFHs em ambientes de Cidades Inteligentes ao propor uma abordagem para seleção dinâmica e sob-demanda de sensores, levando em consideração as características físicas dos sensores e as demandas das aplicações requisitantes. Esta abordagem foi utilizada no framework POlicy-based Sensor SElection in Heterogeneous Wireless Sensor Network (POSSE-HWSN), o qual foi implementado para validar a proposta. Testes realizados demonstram que através da utilização de POSSE-HWSN foi possível escolher os sensores com os recursos de hardware mais adequados para atender a cada aplicação, melhorando assim a eficácia da seleção.

Les travaux de cette thèse ont été initiés par des problèmes d’apprentissage de données radiomiques. La Radiomique est une discipline médicale qui vise l’analyse à grande échelle de données issues d’imageries médicales traditionnelles, pour aider au diagnostic et au traitement des cancers. L’hypothèse principale de cette discipline est qu’en extrayant une grande quantité d’informations des images, on peut caractériser de bien meilleure façon que l’œil humain les spécificités de cette pathologie. Pour y parvenir, les données radiomiques sont généralement constituées de plusieurs types d’images et/ou de plusieurs types de caractéristiques (images, cliniques, génomiques). Cette thèse aborde ce problème sous l’angle de l’apprentissage automatique et a pour objectif de proposer une solution générique, adaptée à tous problèmes d’apprentissage du même type. Nous identifions ainsi en Radiomique deux problématiques d’apprentissage: (i) l’apprentissage de données en grande dimension et avec peu d’instances (high dimension, low sample size, a.k.a.HDLSS) et (ii) l’apprentissage multi-vues. Les solutions proposées dans ce manuscrit exploitent des représentations de dissimilarités obtenues à l’aide des Forêts Aléatoires. L’utilisation d’une représentation par dissimilarité permet de contourner les difficultés inhérentes à l’apprentissage en grande dimension et facilite l’analyse conjointe des descriptions multiples (les vues). Les contributions de cette thèse portent sur l’utilisation de la mesure de dissimilarité embarquée dans les méthodes de Forêts Aléatoires pour l’apprentissage multi-vue de données HDLSS. En particulier, nous présentons trois résultats: (i) la démonstration et l’analyse de l’efficacité de cette mesure pour l’apprentissage multi-vue de données HDLSS; (ii) une nouvelle méthode pour mesurer les dissimilarités à partir de Forêts Aléatoires, plus adaptée à ce type de problème d’apprentissage; et (iii) une nouvelle façon d’exploiter l’hétérogénèité des vues, à l’aide d’un mécanisme de combinaison dynamique. Ces résultats ont été obtenus sur des données radiomiques mais aussi sur des problèmes multi-vue classiques. / The work of this thesis was initiated by a Radiomic learning problem. Radiomics is a medical discipline that aims at the large-scale analysis of data from traditional medical imaging to assist in the diagnosis and treatment of cancer. The main hypothesis of this discipline is that by extracting a large amount of information from the images, we can characterize the specificities of this pathology in a much better way than the human eye. To achieve this, Radiomics data are generally based on several types of images and/or several types of features (from images, clinical, genomic). This thesis approaches this problem from the perspective of Machine Learning (ML) and aims to propose a generic solution, adapted to any similar learning problem. To do this, we identify two types of ML problems behind Radiomics: (i) learning from high dimension, low sample size (HDLSS) and (ii) multiview learning. The solutions proposed in this manuscript exploit dissimilarity representations obtained using the Random Forest method. The use of dissimilarity representations makes it possible to overcome the well-known difficulties of learning high dimensional data, and to facilitate the joint analysis of the multiple descriptions, i.e. the views.The contributions of this thesis focus on the use of the dissimilarity easurement embedded in the Random Forest method for HDLSS multi-view learning. In particular, we present three main results: (i) the demonstration and analysis of the effectiveness of this measure for HDLSS multi-view learning; (ii) a new method for measuring dissimilarities from Random Forests, better adapted to this type of learning problem; and (iii) a new way to exploit the heterogeneity of views, using a dynamic combination mechanism. These results have been obtained on radiomic data but also on classical multi-view learning problems.

A crescente mobilidade de pessoas e recursos materiais exige um esforço constante na exploração das capacidades oferecidas pelas diferentes tecnologias disponíveis, que convergem para o fornecimento de informações e serviços em qualquer lugar com movimento, a qualquer tempo, e por meio de qualquer dispositivo, objetivos da rede mundial de cooperação e comunicação, conhecida como Internet. Em resposta a essa crescente demanda, a atual Internet está evoluindo do modelo de compartilhamento de informações para o modelo de contribuição e em um futuro próximo, para o modelo de colaboração entre provedores e consumidores, denominada de Internet do Futuro. Embora a atual Internet seja extraordinariamente bem sucedida, como um meio ubíquo de comunicação, sua atual arquitetura impõe limites para o provisionamento de serviços em ambientes heterogêneos e convergentes, demandando novas soluções que superem os desafios tecnológicos necessários ao estabelecimento da Internet do Futuro. Estas novas soluções basear-se-ão nos princípios da computação orientada a serviços, formando os componentes de um novo arcabouço de serviços para a Internet do Futuro, denominada de Internet de Serviços. Na Internet de Serviços, redes de comunicação móveis, convergentes e heterogêneas serão criadas sob demanda, disponibilizando um elevado número de serviços, funcionalmente similares, porém distintos sob o ponto de vista não funcional, dificultando a seleção dos serviços que melhor atendem o nível qualidade de serviço acordado entre provedores e consumidores. Este trabalho propõe uma nova solução para o problema de seleção de serviços, combinando algoritmos, usualmente empregados para prospecção de dados, para selecionar serviços de forma dinâmica e interativa, com base em atributos não funcionais, visando suprir as necessidades de mobilidade e colaboração em ambientes convergentes e heterogêneos, como a Internet de Serviços. Desta forma, este trabalho contribui para o projeto de pesquisa da Internet de Serviços, um dos pilares fundamentais para a elaboração da nova arquitetura orientada a serviços, que servirá de arcabouço à construção da Internet do Futuro, possibilitando inúmeras aplicações como Serviços Baseados em Localização e Computação em Nuvem. / The increasing mobility of people and resources demands additional efforts in exploring new capacities, offered by different technologies, which allows the supply of information and services in any place, any time and through any device, objective of the worldwide collaboration and communication web, known as Internet. Face to this increasing demand, current Internet is evolving from sharing to contribution model and in the near future, to collaboration model between providers and consumers. Although the current Internet has been extraordinarily successful, as a ubiquitous and universal means for communication, its architecture imposes limits for services deployment in heterogeneous and convergent environments, demanding new solutions to overcome the technological issues for Internet of Future achievement. These new solutions will be based on service oriented computing principles, providing the components of the new service framework for Internet of Future, called Internet of Services. In Internet of Services, convergent and heterogeneous mobile communication networks will be created on demand, providing a huge numbers of services, similar from functional point of view, but very different from the nonfunctional point of view, creating challenges for service selection which fits the service level agreement between providers and consumers. This work proposes a new solution for service selection process, combining algorithms commonly used for data mining, to perform dynamic and interactive service selection, fulfilling the mobility and collaborative requirements in a convergent and heterogeneous environment, such as Internet of Services. Therefore, this work contributes to Internet of Services research project, one of fundamental pillars to build the service oriented architecture, which will be used as framework for Internet of Future building, allowing many applications such as Location Based Services and Cloud Computing.

A crescente mobilidade de pessoas e recursos materiais exige um esforço constante na exploração das capacidades oferecidas pelas diferentes tecnologias disponíveis, que convergem para o fornecimento de informações e serviços em qualquer lugar com movimento, a qualquer tempo, e por meio de qualquer dispositivo, objetivos da rede mundial de cooperação e comunicação, conhecida como Internet. Em resposta a essa crescente demanda, a atual Internet está evoluindo do modelo de compartilhamento de informações para o modelo de contribuição e em um futuro próximo, para o modelo de colaboração entre provedores e consumidores, denominada de Internet do Futuro. Embora a atual Internet seja extraordinariamente bem sucedida, como um meio ubíquo de comunicação, sua atual arquitetura impõe limites para o provisionamento de serviços em ambientes heterogêneos e convergentes, demandando novas soluções que superem os desafios tecnológicos necessários ao estabelecimento da Internet do Futuro. Estas novas soluções basear-se-ão nos princípios da computação orientada a serviços, formando os componentes de um novo arcabouço de serviços para a Internet do Futuro, denominada de Internet de Serviços. Na Internet de Serviços, redes de comunicação móveis, convergentes e heterogêneas serão criadas sob demanda, disponibilizando um elevado número de serviços, funcionalmente similares, porém distintos sob o ponto de vista não funcional, dificultando a seleção dos serviços que melhor atendem o nível qualidade de serviço acordado entre provedores e consumidores. Este trabalho propõe uma nova solução para o problema de seleção de serviços, combinando algoritmos, usualmente empregados para prospecção de dados, para selecionar serviços de forma dinâmica e interativa, com base em atributos não funcionais, visando suprir as necessidades de mobilidade e colaboração em ambientes convergentes e heterogêneos, como a Internet de Serviços. Desta forma, este trabalho contribui para o projeto de pesquisa da Internet de Serviços, um dos pilares fundamentais para a elaboração da nova arquitetura orientada a serviços, que servirá de arcabouço à construção da Internet do Futuro, possibilitando inúmeras aplicações como Serviços Baseados em Localização e Computação em Nuvem. / The increasing mobility of people and resources demands additional efforts in exploring new capacities, offered by different technologies, which allows the supply of information and services in any place, any time and through any device, objective of the worldwide collaboration and communication web, known as Internet. Face to this increasing demand, current Internet is evolving from sharing to contribution model and in the near future, to collaboration model between providers and consumers. Although the current Internet has been extraordinarily successful, as a ubiquitous and universal means for communication, its architecture imposes limits for services deployment in heterogeneous and convergent environments, demanding new solutions to overcome the technological issues for Internet of Future achievement. These new solutions will be based on service oriented computing principles, providing the components of the new service framework for Internet of Future, called Internet of Services. In Internet of Services, convergent and heterogeneous mobile communication networks will be created on demand, providing a huge numbers of services, similar from functional point of view, but very different from the nonfunctional point of view, creating challenges for service selection which fits the service level agreement between providers and consumers. This work proposes a new solution for service selection process, combining algorithms commonly used for data mining, to perform dynamic and interactive service selection, fulfilling the mobility and collaborative requirements in a convergent and heterogeneous environment, such as Internet of Services. Therefore, this work contributes to Internet of Services research project, one of fundamental pillars to build the service oriented architecture, which will be used as framework for Internet of Future building, allowing many applications such as Location Based Services and Cloud Computing.

In neural implants and biohybrid research systems, the integration of electrode recording and stimulation front-ends with pre-processing circuitry promises a drastic increase in real-time capabilities [1,6]. In our proposed neural recording system, constant sampling with a bandwidth of 9.8kHz yields 6.73μV input-referred noise (IRN) at a power-per-channel of 0.34μW for the time-continuous ΔΣ−modulator, and 0.52μW for the digital filters and spike detectors. We introduce dynamic current/bandwidth selection at the ΔΣ and digital filter to reduce recording bandwidth at the absence of spikes (i.e. local field potentials). This is controlled by a two-level spike detection and adjusted by adaptive threshold estimation (ATE). Dynamic bandwidth selection reduces power by 53.7%, increasing the available channel count at a low heat dissipation. Adaptive back-gate voltage tuning (ABGVT) compensates for PVT variation in subthreshold circuits. This allows 1.8V input/output (IO) devices to operate at 0.4V supply voltage robustly. The proposed 64-channel neural recording system moreover includes a 16-channel adaptive compression engine (ACE) and an 8-channel on-chip current stimulator at 3.3V. The stimulator supports field-shaping approaches, promising increased selectivity in future research.