Aprendizado de máquina baseado em tensores e suas aplicacções para floresta de caminhos ótimos

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Aplicação de modelos gráficos probabilísticos computacionais em economia

O objetivo deste trabalho é testar a aplicação de um modelo gráfico probabilístico, denominado genericamente de Redes Bayesianas, para desenvolver modelos computacionais que possam ser utilizados para auxiliar a compreensão de problemas e/ou na previsão de variáveis de natureza econômica. Com este propósito, escolheu-se um problema amplamente abordado na literatura e comparou-se os resultados teóricos e experimentais já consolidados com os obtidos utilizando a técnica proposta. Para tanto,foi construído um modelo para a classificação da tendência do "risco país" para o Brasil a partir de uma base de dados composta por variáveis macroeconômicas e financeiras. Como medida do risco adotou-se o EMBI+ (Emerging Markets Bond Index Plus), por ser um indicador amplamente utilizado pelo mercado.

Deep learning architecture for gesture recognition

Pós-graduação em Engenharia Mecânica - FEG

Seleção de características utilizando algoritmos evolucionistas e suas aplicações em reconhecimento de padrões

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Implementação do algoritmo de Newman para identificação de comunidades em placas gráficas

Communities are present on physical, chemical and biological systems and their identification is fundamental for the comprehension of the behavior of these systems. Recently, available data related to complex networks have grown exponentially, demanding more computational power. The Graphical Processing Unit (GPU) is a cost effective alternative suitable for this purpose. We investigate the convenience of this for network science by proposing a GPU based implementation of Newman community detection algorithm. We showed that the processing time of matrix multiplications of GPUs grow slower than CPUs in relation to the matrix size. It was proven, thus, that GPU processing power is a viable solution for community dentification simulation that demand high computational power. Our implementation was tested on an integrated biological network for the bacterium Escherichia coli

Sistema de recomendação de produtos online baseado em palavras-chave

This project aims to explore the many methods used for the development of recommendation systems to user ’ s items and apply the content - based recommendation method on a prototype system whose purpose is to recommend books to users. This paper exposes the most popular methods for creating systems capable of providing items (products) according to user preferences, such as collaborat ive filtering and content - based. It also point different techniques that can be applied to calculate the similarity between two entities, for items or users, as the Pearson ’s method, calculating the cosine of vectors and more recently, a proposal to use a Bayesian system under a Dirichlet distribution. In addition, this work has the purpose to go through various points on the design of an online application, or a website, dealing not only oriented algorithms issues, but also the definition of development to ols and techniques to improve the user’s experience. The tools used for the development of the page are listed, and a topic about web design is also discussed in order to emphasize the importance of the layout of the application. At the end, some examples of recommender systems are presented for curiosity , learning and research purposes

Utilização da instrumentação virtual em Labview para criação da interface gráfica do amplificador lock-in utilizado em estudos fisiológicos a partir da comunicação via porta serial

This work presents the development of a graphical interface to the Lock-in Amplifier, which is used in physiological studies on the motility of the gastrointestinal tract in rats and signal processing. With a simple and low cost instrumentation, the resources offered by the virtual interface of LabVIEW software allows the creation of commands similar to the actual instrument that, through communication via standard serial port, transmits data between a PC and peripheral device performing specific and particular needs in the amplifier. Created for the lock-in amplifier model SR830 Stanford Research Systems, the remote manipulation gives the user greater accessibility in the process of configuration and calibration. And, since the software is installed, there is the advantage of eliminating the need of purchase new devices to upgrade the system. The commands created were made to perform six basic modifications that are used in routine of the Biomagnetism Laboratory. The instrumentation developed has the following controls: Amplitude, Frequency, Time Constant, slope low pass filter, sensitivity and offset

Interface para classificação de dados por máquinas de vetores de suporte

In this project the Pattern Recognition Problem is approached with the Support Vector Machines (SVM) technique, a binary method of classification that provides the best solution separating the data in the better way with a hiperplan and an extension of the input space dimension, as a Machine Learning solution. The system aims to classify two classes of pixels chosen by the user in the interface in the interest selection phase and in the background selection phase, generating all the data to be used in the LibSVM library, a library that implements the SVM, illustrating the library operation in a casual way. The data provided by the interface is organized in three types, RGB (Red, Green and Blue color system), texture (calculated) or RGB + texture. At last the project showed successful results, where the classification of the image pixels was showed as been from one of the two classes, from the interest selection area or from the background selection area. The simplest user view of results classification is the RGB type of data arrange, because it’s the most concrete way of data acquisition

Detecção de impressões digitais fraudulentas utilizando padrões mapeados localmente em multiescala

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Segmentação interativa de imagens utilizando competição e cooperação entre partículas

Pós-graduação em Ciência da Computação - IBILCE

Classificação de atividade eletromiográfia facial de indivíduos saudáveis e com hanseníese por meio de máquina de vetores de suporte

A number of studies in the areas of Biomedical Engineering and Health Sciences have employed machine learning tools to develop methods capable of identifying patterns in different sets of data. Despite its extinction in many countries of the developed world, Hansen’s disease is still a disease that affects a huge part of the population in countries such as India and Brazil. In this context, this research proposes to develop a method that makes it possible to understand in the future how Hansen’s disease affects facial muscles. By using surface electromyography, a system was adapted so as to capture the signals from the largest possible number of facial muscles. We have first looked upon the literature to learn about the way researchers around the globe have been working with diseases that affect the peripheral neural system and how electromyography has acted to contribute to the understanding of these diseases. From these data, a protocol was proposed to collect facial surface electromyographic (sEMG) signals so that these signals presented a high signal to noise ratio. After collecting the signals, we looked for a method that would enable the visualization of this information in a way to make it possible to guarantee that the method used presented satisfactory results. After identifying the method's efficiency, we tried to understand which information could be extracted from the electromyographic signal representing the collected data. Once studies demonstrating which information could contribute to a better understanding of this pathology were not to be found in literature, parameters of amplitude, frequency and entropy were extracted from the signal and a feature selection was made in order to look for the features that better distinguish a healthy individual from a pathological one. After, we tried to identify the classifier that best discriminates distinct individuals from different groups, and also the set of parameters of this classifier that would bring the best outcome. It was identified that the protocol proposed in this study and the adaptation with disposable electrodes available in market proved their effectiveness and capability of being used in different studies whose intention is to collect data from facial electromyography. The feature selection algorithm also showed that not all of the features extracted from the signal are significant for data classification, with some more relevant than others. The classifier Support Vector Machine (SVM) proved itself efficient when the adequate Kernel function was used with the muscle from which information was to be extracted. Each investigated muscle presented different results when the classifier used linear, radial and polynomial kernel functions. Even though we have focused on Hansen’s disease, the method applied here can be used to study facial electromyography in other pathologies.

Classificação de atividade eletromiográfia facial de indivíduos saudáveis e com hanseníase por meio de máquina de vetores de suporte

A number of studies in the areas of Biomedical Engineering and Health Sciences have employed machine learning tools to develop methods capable of identifying patterns in different sets of data. Despite its extinction in many countries of the developed world, Hansen’s disease is still a disease that affects a huge part of the population in countries such as India and Brazil. In this context, this research proposes to develop a method that makes it possible to understand in the future how Hansen’s disease affects facial muscles. By using surface electromyography, a system was adapted so as to capture the signals from the largest possible number of facial muscles. We have first looked upon the literature to learn about the way researchers around the globe have been working with diseases that affect the peripheral neural system and how electromyography has acted to contribute to the understanding of these diseases. From these data, a protocol was proposed to collect facial surface electromyographic (sEMG) signals so that these signals presented a high signal to noise ratio. After collecting the signals, we looked for a method that would enable the visualization of this information in a way to make it possible to guarantee that the method used presented satisfactory results. After identifying the method's efficiency, we tried to understand which information could be extracted from the electromyographic signal representing the collected data. Once studies demonstrating which information could contribute to a better understanding of this pathology were not to be found in literature, parameters of amplitude, frequency and entropy were extracted from the signal and a feature selection was made in order to look for the features that better distinguish a healthy individual from a pathological one. After, we tried to identify the classifier that best discriminates distinct individuals from different groups, and also the set of parameters of this classifier that would bring the best outcome. It was identified that the protocol proposed in this study and the adaptation with disposable electrodes available in market proved their effectiveness and capability of being used in different studies whose intention is to collect data from facial electromyography. The feature selection algorithm also showed that not all of the features extracted from the signal are significant for data classification, with some more relevant than others. The classifier Support Vector Machine (SVM) proved itself efficient when the adequate Kernel function was used with the muscle from which information was to be extracted. Each investigated muscle presented different results when the classifier used linear, radial and polynomial kernel functions. Even though we have focused on Hansen’s disease, the method applied here can be used to study facial electromyography in other pathologies.

A contribution to semantic description of images and videos: an application of soft biometrics

Humans have a high ability to extract visual data information acquired by sight. Trought a learning process, which starts at birth and continues throughout life, image interpretation becomes almost instinctively. At a glance, one can easily describe a scene with reasonable precision, naming its main components. Usually, this is done by extracting low-level features such as edges, shapes and textures, and associanting them to high level meanings. In this way, a semantic description of the scene is done. An example of this, is the human capacity to recognize and describe other people physical and behavioral characteristics, or biometrics. Soft-biometrics also represents inherent characteristics of human body and behaviour, but do not allow unique person identification. Computer vision area aims to develop methods capable of performing visual interpretation with performance similar to humans. This thesis aims to propose computer vison methods which allows high level information extraction from images in the form of soft biometrics. This problem is approached in two ways, unsupervised and supervised learning methods. The first seeks to group images via an automatic feature extraction learning , using both convolution techniques, evolutionary computing and clustering. In this approach employed images contains faces and people. Second approach employs convolutional neural networks, which have the ability to operate on raw images, learning both feature extraction and classification processes. Here, images are classified according to gender and clothes, divided into upper and lower parts of human body. First approach, when tested with different image datasets obtained an accuracy of approximately 80% for faces and non-faces and 70% for people and non-person. The second tested using images and videos, obtained an accuracy of about 70% for gender, 80% to the upper clothes and 90% to lower clothes. The results of these case studies, show that proposed methods are promising, allowing the realization of automatic high level information image annotation. This opens possibilities for development of applications in diverse areas such as content-based image and video search and automatica video survaillance, reducing human effort in the task of manual annotation and monitoring.

O lugar do computador na mesa do arquiteto : uma mirada sobre os recursos informáticos no aprendizado do projeto arquitetônico

O trabalho tem como objetivo estudar as repercussões do emprego de recursos informáticos aplicados ao projeto arquitetônico e da sua interação com o usuário. A relação entre computação gráfica e projeto arquitetônico é um assunto já bastante discutido, seja como a aplicação do potencial matemático da ferramenta para a composição das formas, ou ainda, como experimentações no campo da realidade virtual. No entanto, sob o ponto de vista do projeto arquitetônico e da sua apropriação da ferramenta pouco se tem dito, é nesta lacuna que a dissertação pretende se inserir. Desenvolvo a questão em duas partes principais. A primeira tem o objetivo de situar o leitor no assunto proposto, procurando possíveis repostas para relação entre usuário/projeto/máquina. A segunda parte se concentra no projeto arquitetônico como forma de investigação, amparada em um estudo de caso, resultado da observação do atelier. Procuro tecer as relações entre o projeto dos alunos, como resposta às instruções dos professores, e o uso da computação gráfica na composição do projeto.

A inserção do uso do computador no processo de modelagem matemática contribuindo para o aprendizado de conhecimentos matemáticos

Nesta pesquisa investigamos de que forma a inserção do uso do computador e do portfólio no processo de Modelagem Matemática, contribui para a aprendizagem de conhecimentos matemáticos a partir das percepções de alunos do ensino médio. Na busca de respostas a esta problemática, traçou-se como objetivo principal uma investigação à inserção do uso do computador no processo de Modelagem Matemática, com auxilio do portfólio para o aprendizado deste processo. A abordagem da pesquisa foi qualitativa. Levantamos um referencial teórico focando em especial pesquisadores da área de Modelagem Matemática como: Biembengut e Hein (2007); Bassanezi (2006), Barbosa (2001, 2004, 2007); Borba e Penteado(2001); Ponte e Canavarro (1997) entre outros, e com alguns autores que abordam mais especificamente a inserção de tecnologias na educação como: Valente (1993); Almeida (2000), Belloni (2005) entre outros. No entrelaçamento das idéias relacionaram-se os elementos (computador, Modelagem e portfólio) para subsidiar um tratamento diferenciado do conhecimento matemático em busca de minimizar, por exemplo, os baixos índices no Sistema de Avaliação do Ensino Básico (SAEB) dos alunos do ensino médio do Estado do Pará em Matemática. Sendo assim, foi necessário rever a forma atual de transposição do ensino dessa disciplina. O histórico da Modelagem é descrito em algumas concepções, buscando pontos de aproximação com as novas tecnologias em especial o computador. A pesquisa de campo foi desenvolvida a partir do curso: Modelagem Matemática: Aprendendo Matemática com a utilização do Computador. Na pesquisa de campo os instrumentos utilizados foram: o portfólio e o questionário. O uso do portfólio na pesquisa foi inspirado a partir de uma idéia em Biembengut e Hein (2007) que dizem haver a necessidade de se criar um relatório no final do processo de Modelagem. No entanto verificou-se que o uso do portfólio extrapola sua utilidade como coleta de dados, já que se constitui também como instrumento de organização e constituição do processo de Modelagem da Matemática. Para a análise dos dados definiu-se categorias de análises do tipo emergentes a partir de Fiorentini e Lorenzato (2007). A pesquisa de campo foi desenvolvida no Laboratório de Informática da Escola Estadual de Ensino Médio Mário Barbosa na área correspondente a Região metropolitana de Belém no Estado do Pará, onde por meio da inserção do uso computador neste processo, potencializou-se a aprendizagem dos conhecimentos matemáticos pelos alunos do ensino médio. Nas atividades desenvolvidas, percebeu-se que o ambiente gerado pelo processo de Modelagem dentro do laboratório de informática, permitiu-se trabalhar de forma coletiva e colaborativa, onde os resultados foram significativos, principalmente, articulado ao uso do computador. Nesta pesquisa mostraremos que a Modelagem e o portfólio estabelecem uma relação de troca, possibilitando dessa forma a condução do processo de Modelagem Matemática de forma dinâmica, facilitando o aprendizado do conteúdo matemático.