DISSERTAÇÃO DE MESTRADO - PROGRAMA DE PÓS GRADUAÇÃO EM ENGENHARIA DE ELETRICIDADE

URI Permanente para esta coleçãohttps://tedebc-teste.ufma.br/handle/tede/280

Navegar

Agora exibindo 1 - 3 de 3

Um framework para suportar de forma semiautomática a atividade de desenvolvimento de software para mapreduce utilizando MDE
(Universidade Federal do Maranhão, 2017-11-22) SOUSA JUNIOR, Osvaldo Silva de; SILVA, Aristófanes Corrêa; 288745363-72; http://lattes.cnpq.br/2446301582459104; LOPES, Denivaldo Cícero Pavão; 61364371391; http://lattes.cnpq.br/7611180871627212; LOPES, Denivaldo Cícero Pavão; 613643713-91; http://lattes.cnpq.br/7611180871627212; SILVA, Aristófanes Corrêa; 288745363-72; http://lattes.cnpq.br/2446301582459104; DEL FABRO, Marcos Didonet; http://lattes.cnpq.br/4720333397291573; SANTOS NETO, Pedro de Alcântara dos; http://lattes.cnpq.br/3452982259415951; GUTIÉRREZ, María del Rosario Girardi; http://lattes.cnpq.br/5317074159250496
The need to analyze a large volume and variety of data to extract information has been increasing investments in Big Data. One example would be investments targeted at software engineering for Big Data platforms. These investments are recent and emerging, so several challenges and opportunities are found in the literature, but few approaches have been proposed to support them. In this work, a framework based on Model-Driven Engineering (MDE) and Weaving is proposed to support the software development activity in a semiautomatic way, using the MapReduce model of the Big Data platform. This framework was called F2BD and uses MDE to assist in controlling the complexity of software development through models; and uses Weaving to unify the view between different models. An activity process is proposed to guide the use of F2BD. In addition, a metamodel based on Action Language for Foundational UML (Alf) and a graphical notation called VisualAlf are proposed to complement UML, aiming to support the description of the actions modeled in the bodies (i.e. body field) of methods of diagram class UML. Metamodels for Platform-Description Model (PDM) based on MapReduce and metamodels for abstract Platform-Specific Model (PSM) based on Spark are provided. Transformation definitions of models written in Atlas Transformation Language (ATL) are proposed. The applicability of F2BD was demonstrated through the construction of a tool (TF2BD) and the feasibility of TF2BD was demonstrated through the construction of two illustrative examples and an experimental evaluation. TF2BD supports the tasks involved in software development activity, providing editors for manual manipulation of models and transformation definitions for automatic generation of PSM as well as full source code. This is possible because TF2BD was built based on the F2BD architecture. Thus, it is concluded that F2BD is feasible and can be used for the construction of other tools.
Meta-learning applications in digital image processing
(Universidade Federal do Maranhão, 2019-11-08) SEPULVEDA, Luis Fernando Marin; SILVA, Aristófanes Corrêa; 288745363-72; http://lattes.cnpq.br/2446301582459104; SILVA, Aristófanes Corrêa; 288745363-72; http://lattes.cnpq.br/2446301582459104; CONCI, Aura; https://orcid.org/0000-0003-0782-2501; http://lattes.cnpq.br/5601388085745497; LOPES, Denivaldo Cicero Pavao; http://lattes.cnpq.br/7611180871627212; ALMEIDA, João Dallyson Sousa de; http://lattes.cnpq.br/6047330108382641
In recent decades, advances in capture devices and increase of available digital image data have stimulated the creation of methodologies for data processing that produce various forms of valuable models, such as descriptors, classifiers, approximations and visualizations. These models are often developed in the field of machine learning, which is characterized by a large number of available algorithms, these algorithms often do not have guidelines to identify the most appropriate one based on specific data to which they will be applied and nature of problem under analysis. There is a knowledge that allows to relate the features of the algorithms and data that present a good performance to fulfill a specific task, known as Meta-Knowledge, which can include information on algorithms, evaluation metrics to calculate similarity of datasets or relation of tasks. Being Meta-Learning the study of methods based on principles that explore the Meta-Knowledge to obtain efficient models and solutions, adapting the processes of Machine Learning and Data Mining. The research carried out in this work analyzes the applications and advantages offered by Meta-Learning in field of digital image processing. To carry out this task, different types of images, characterizers, and feature analysis techniques are used; in addition, multiple Machine Learning techniques are applied. The results obtained show that methodology based on Meta-Learning is efficient when applied in processing of digital images for identification and storage of experience generated by developing methodologies for classification of different types of images, obtaining a high performance with respect to an evaluation metrics. This statement means that Meta-Learning allows recommending the most appropriate methodology to perform the processing of a specific type of image based on features of dataset under analysis and the type of specific task to be performed.
Metodologia computacional para a segmentação da próstata e classificação de lesões em imagens de ressonância magnética utilizando o modelo de Ising
(Universidade Federal do Maranhão, 2019-03-11) REIS, Artur Bernardo Silva; PAIVA, Anselmo Cardoso de; 375523843-87; http://lattes.cnpq.br/6446831084215512; SILVA, Aristófanes Corrêa; 288745363-72; http://lattes.cnpq.br/2446301582459104; SILVA, Aristófanes Corrêa; 288745363-72; http://lattes.cnpq.br/2446301582459104; PAIVA, Anselmo Cardoso de; 375523843-87; http://lattes.cnpq.br/6446831084215512; CONCI, Aura; http://lattes.cnpq.br/5601388085745497; PACIORNIK, Sidnei; http://lattes.cnpq.br/4692086634018379; CARVALHO FILHO, Antonio Oseas de; http://lattes.cnpq.br/7913655222849728
Prostate cancer is the second most prevalent type of cancer in the male population worldwide. The adoption of prostate imaging tests for the prevention, diagnosis, and treatment has grown. It is known that early detection increases the chances of an effective treatment, improving the prognosis of the disease. With this aim, computational tools have been proposed with the purpose of assisting the specialist in the interpretation of imaging tests, especially magnetic resonance imaging (MRI), providing the detection of lesions. The research of this doctoral work has as primary objective the proposition of an automatic methodology for the detection of lesions in the prostate. We divide the proposed methodology into two stages. In the first stage prostate segmentation is performed, for this purpose, the Ising model is used, models of probability, quality threshold and fusion of atlas labels. The second stage consists of the classification of abnormal tissues in the prostate. To this end, we extract lesion candidates through the Wolff algorithm, then texture characteristics are extracted using the Ising model, and finally, the vector machine is used to classify lesion or healthy tissue. The methodology was validated using three bases of T2-weighted MRI images. We used three bases for prostate segmentation. However, we used only one in prostate segmentation and lesion detection. The total number of images used in the validation of prostate segmentation was 108. The experimental results obtained here indicate an excellent perspective, considering that we obtained a mean Dice similarity coefficient (DSC) of 94.03 % in the step of. We validated The lesion detection stage on a set of 28 images with lesion markers. The methodology obtained a sensitivity of 95:92%, specificity of 93:89% and accuracy of 94:16%. These are promising since they were more significant than other methods compared.

Navegar

Navegando DISSERTAÇÃO DE MESTRADO - PROGRAMA DE PÓS GRADUAÇÃO EM ENGENHARIA DE ELETRICIDADE por Autor "288745363-72"