Ciência da Computação

URI Permanente desta comunidade

https://repositorio.fei.edu.br/handle/FEI/342

Navegar

Agora exibindo 1 - 20 de 151

3DOOR:
(2022-12-09) Sousa, Caio Rios ; Ferreira, Guilherme Nunes Melo ; Lima, Lucas Alves de ; Pereira, Victor Manoel de Lima
A reconstrução 3D de ambientes, sejam eles internos ou externos, é uma realidade e tem se tornado cada vez mais utilizada. Porém, atualmente, é difícil encontrar técnicas que tenham a capacidade de fazer uma reconstrução 3D de fachadas utilizando imagens antigas, seja por falta de conteúdo disponível, como base de dados, ou por pouca eficácia de algoritmos na reconstrução de cenas com arquiteturas antigas. Sendo assim, o principal objetivo deste trabalho é fazer a reconstrução 3D de fachadas antigas baseando-se em poucas ou até mesmo uma única imagem, passando por técnicas para processamento da imagem que possibilitam, assim, a execução do processo de reconstrução 3D da fachada. Para alcançar esse objetivo foram utilizados alguns métodos, partindo desde o tratamento de imagens de entrada com a aplicação da equalização de histograma em conjunto com a remoção de elementos que possam obstruir a fachada, para que ela se adéque às condições ideais e assim possibilite que o resultado esperado seja alcançado, até a aplicação de métodos para geração das malhas 3D da fachada desejada e para a aplicação da imagem como textura no modelo criado. O pipeline proposto apresentou resultados consistentes considerando os desafios impostos na reconstrução 3D de fachadas antigas partindo de uma única perspectiva.
A Bio-Inspired Methodology for Digital Imaging Forensic Detection
(2019-09-05) SANTOS, G. L.; OLIVEIRA, G. R.; PRADO, F. F.; SERIKAKU, R.; SANTOS, R. M.; LOPES, G.; RODRIGUES, P. S.
© 2019 IEEE.The increasing number of digital media users, as well as the development of multimedia platforms, such as smartphones and tablets, has also increased the number of users who professionally and fraudulently manipulate all types of digital media. This paper proposes a methodology based on an image processing pipeline to detect mainly copy-move type frauds, which are intended to hide or enlarge visual information. Our proposal has been tested in a Copy-Move Forgery database and the results were equal or better in performance than the state-of-art methods.
A Bio-Inspired Strategy for 3D Surface Reconstruction of Unstructured Scenes Applied to Medical Images
(2019-09-05) BOUZON, M.; ALBERTINI, G.; VIANA, G.; MEDEIROS, G.; Paulo Rodrigues
© 2019 IEEE.The use of 3D reconstruction, along with immersive technologies, is a technique used in several areas of research and development. Currently, the most common strategy for performing this type of reconstruction is using a stereoscopic camera model. The problem worsens when the challenge involves unstructured scenes, which are scenes that have an ill-defined cognitive architecture. The present work proposes a methodology for 3D reconstruction of unstructured surfaces using monocular cameras. Thus, modern AI techniques, Computer Vision and Computer Graphics techniques have been applied to solve this problem. The experiments performed in this work can be concluded that the proposed method can reconstruct structured scenes with a hit rate between 63% and 68%, depending on the number of thresholds used in the segmentation, thus being superior to the classical method, where the extraction of points is done over the original image without any pre-processing.
A bipartite graph approach to retrieve similar 3D models with different resolution and types of cardiomyopathies
(2022-05-01) Leila Bergamasco; LIMA, K.R.P.S.; ROCHITTE, C. E.; NUNES, F. L. S.
Three-dimensional (3D) model retrieval uses content-based image retrieval (CBIR) techniques to search for the most similar 3D objects in a dataset, usually considering their geometry and organization in a feature vector. Feature vectors from different objects were compared to establish their similarities. Although this type of comparison typically uses metric distances, such metrics present limitations when the vector lengths are different. Signal-based descriptors are a promising approach for extracting features from 3D objects, but they generate feature vectors with different lengths. Thus, new methods for measuring the similarity are required. This study proposes an approach to 3D model retrieval as a network flow problem using bipartite graphs. The approach was applied to support the diagnosis of cardiomyopathies, considering 3D objects reconstructed from cardiac images of the left ventricle. We achieved an AUC value of 0.93 under the best retrieval scenario. The results also indicate that modeling a 3D model retrieval technique as a network flow problem using graphs can provide a promising manner to compare 3D objects with different shapes and sizes. This strategy, coupled with personal patient data, achieves better results than methods using classical comparison approaches.
A large-scale analysis of the use of session in a mobile application
(2016-10-04) MARCZAL, D.; Plinio Thomaz Aquino Junior
© 2016 ACM.Due to the recent proliferation of mobile applications, it has become essential to obtain a better understanding of how people use their devices and applications. The session usage contains the user behavior therefore, the present study aims to analyze which are the most representative session groups in the context of an application that is part of a taxi request platform by the means of an experiment performed in the application made available at application stores and used by real users, performing daily tasks.
A new approach based on computer vision and non-linear Kalman filtering to monitor the nebulization quality of oil flames
(2013-09-15) FLEURY, A. T.; TRIGO, F. C.; MARTINS, F. P. R.
The nebulization quality of oil flames, an important characteristic exhibited by combustion processes of petroleum refinery furnaces, is mostly affected by variations on the values ofthe vapor flow rate (VFR). Expressive visual changes in the flame patterns and decay of the combustion efficiency are observed when the process is tuned by diminishing the VFR. Such behavior is supported by experimental evidence showing that too low values of VFR and solid particulate material rate increase are strongly correlate d. Given the economical importance of keeping this parameter under control, a laborator ial vertical furnace was devised with the purpose of carrying out experiments to prototype acomputer vision system capable of estimati ng VFR values through the examination of test charact eristic vectors based on geometric properties of the grey level histogram of instantaneous flame images. Firstly, atraining set composed of feature vectors from all the images collected during experiments with a priori known VFR values are properly organized and analgorithm is applied to this data in order to generate a fuzzy measurement vector whose components represent membership degrees to the 'high nebulization quality'fuzzy set. Fuzzy classification vectors from images with unknown a priori VFR values are, then, assumed tobe state-vectors inarandom-walk model, and a non-linear Tikhonov regularized Kalman filter is applied to estimate the state and the corresponding nebulization quality. The successful validation of the output data, even based onsmall training data sets, indicates that the proposed approach could beapplied to synthesize a real-time algorithm for evaluating the nebulization quality of combustion processes in petroleum refinery furnaces that use oil flamesasthe heating source. © 2013 Elsevier Ltd. All rights reserved.
A novel deployment of smart Cold Chain system using 2G-RFID-Sys temperature monitoring in medicine Cold Chain based on Internet of Things
(2017-11-27) MONTELEONE, S.; Mauro Sampaio; Rodrigo Maia
© 2017 IEEE.Temperature monitoring of medicines is essential for product quality and patient safety. Product quality is influenced by temperature perturbations and time delays in interventions. Thanks to Internet of Things (IoT) considerable progress has been made in recent years in the improvement of temperature monitoring devices. However, temperature monitoring in medicine Cold Chain remains challenging. In this paper it is presented a conceptual model aiming at overcoming challenges of medicine Cold Chain related to temperature monitoring. The major particularity of our model is that it considers the complete Cold Chain according to two perspectives of pharmaceutical and healthcare industries in a single study. Besides this model can be applied also in vaccine Cold Chain and in temperature-controlled logistics of laboratory medicine. Our conceptual model supports the development of a smart Cold Chain system for temperature monitoring based on IoT. Our smart Cold Chain system can be used to improve Cold Chain responsiveness by studying weaknesses and deciding what Cold Chain characteristics to improve.
A q-extension of sigmoid functions and the application for enhancement of ultrasound images
(2019) Rodrigues P.S.; Wachs-Lopes G.; Santos R.M.; Coltri E.; Giraldi G.A.
© 2019 by the authors.This paper proposes the q-sigmoid functions, which are variations of the sigmoid expressions and an analysis of their application to the process of enhancing regions of interest in digital images. These new functions are based on the non-extensive Tsallis statistics, arising in the field of statistical mechanics through the use of q-exponential functions. The potential of q-sigmoids for image processing is demonstrated in tasks of region enhancement in ultrasound images which are highly affected by speckle noise. Before demonstrating the results in real images, we study the asymptotic behavior of these functions and the effect of the obtained expressions when processing synthetic images. In both experiments, the q-sigmoids overcame the original sigmoid functions, as well as two other well-known methods for the enhancement of regions of interest: slicing and histogram equalization. These results show that q-sigmoids can be used as a preprocessing step in pipelines including segmentation as demonstrated for the Otsu algorithm and deep learning approaches for further feature extractions and analyses.
A reference process to design information systems for sustainable design based on LCA, PSS, social and economic aspects
(2010) SANTAMA, F. S.; BARBERATO, C.; SARAIVA, A. M.
© IFIP International Federation for Information Processing 2010.The purpose of Sustainable Design, SD, is to satisfy customer needs while reducing environmental impacts. The main challenge is to integrate Life Cycle Assessment, Product Service Systems, social and economic aspects while considering the tensions and trade-offs of each activity in depth. SD requires data from many sources in addition to many software tools to perform each analysis. In order to provide information systems for SD, the adoption of a Service-Oriented Architecture, SOA, is appropriate because of its integration requirements. SOA best practices recommend the design of a reference process prior to architectural definitions, so as to identify the complexities and provide a comprehensive solution to the problem. A reference process is presented here as the first step for building information systems for SD. In addition, the reference process presents a list of activities to be performed during the design stage and is very helpful as a guide for SD beginners.
A study of a firefly meta-heuristics for multithreshold image segmentation
(2014-10-14) ERDMANN, H.; LOPES, L. A.; Guilherme Lopes; RIBEIRO, M. P.; Paulo Rodrigues
© 2014 Taylor & Francis Group, London.Thresholding-based image segmentation algorithms are usually developed for a specific set of images because the objective of these algorithms is strongly related to their applications. The binarization of the image is generally preferred over multi-segmentation, mainly because it’s simple and easy to implement. However, in this paper we demonstrate that a scene separation with three threshold levels can be more effective and closer to a manually performed segmentation. Also, we show that similar results can be achieved through a firefly-based meta-heuristic. Finally, we suggest a similarity measure that can be used for the comparison between the distances of the automatic and manual segmentation.
Adaptive interface combined to interface patterns in human factors
(2018-01-05) TAKAHASHI, N. M.; Plinio Thomaz Aquino Junior
© Springer International Publishing AG 2018.Adaptive interface is an artifact with the objective to learn the user interactions and improve the system experience, and the adaptive system is a system that can adapt itself according with the user’s goals and preferences. Patterns can be defined as solution to recurring problems in a specific context. The interface pattern are patterns that help to organize the interface, such as structure and behavior, in order to generate more understandable and usable interface. The Interface Patterns in Personas Layers (IPPL) are interface patterns that contain a structure organized in layers that are built and classified according with personas. The goal of this paper is to present a structure of interface patterns based on IPPL that allows future projects of adaptive interface and human-robot interaction to consider the automatic changes of the iterative process based on a set of patterns.
Agile web development with scrum: A user experience based approach using linguistic metamodel
(2018-07-15) AGUILLAR, D. A. M.; Plinio Thomaz Aquino Junior
© 2018, Springer International Publishing AG, part of Springer Nature.In this work it is proposed an approach based on user experience design for the agile development of web-based software, using the language metamodel. The main motivation was the observation of evidences, in market studies and papers from other researchers, of proportional differences between the usage of agile methods versus methods based on user experience design. This research proposes an approach for the development of web applications using SCRUM, based on UX design, offering the metamodel as a tool to tackle communication problems during this process. The experiments were done in academic and industrial contexts in order to validate and check viability/applicability of the proposed approach: In the academic context, workshops were made for the practical application of the developed approach and information regarding the experiment was collected by means of questionnaires. It was demonstrated that the proposed approach may be viable and may be applied in contexts where it is possible to adopt all stablished recommendations and principles so that the integration between SCRUM and UX happens. It was also used as a facilitating tool, for the integration process, the linguistic metamodel to permeate all existing communication processes, reducing communicational noise related to omission, generalization and distortion of information.
AGRO5G :
(2022-06-13) BRUNO DUCATI VAZQUEZ; LUCAS SOUZA VALVERDE; MARCELO SHINJI SHINZATO
O agronegócio é o setor responsável pelo saldo positivo da balança comercial de exportação e contribui com a geração de expressivo percentual de empregos no Brasil. Nesse contexto, uma das áreas chave para um bom desempenho agropecuário é a operação de irrigação, pois uma agricultura irrigada permite a criação de lavouras em regiões onde a escassez de água é predominante e são proporcionados diversos benefícios no uso dessa técnica como o aumento da produtividade, alta qualidade dos produtos, possibilidade de uma entressafra (mais de uma safra por ano), melhor rentabilidade e redução de riscos de perda nos períodos de estiagem. Entretanto, muitos fazendeiros utilizam técnicas que não garantem que a plantação esteja sendo irrigada uniformemente. Além disso, a forma como a irrigação é feita pode contribuir para um uso excessivo de água, assim, não utilizando de forma eficiente esse recurso natural e aumentando as despesas operacionais. Os problemas relacionados à irrigação eficiente de lavouras podem ser resolvidos por meio do uso de técnicas de inteligência Artificial e de redes de alta velocidade, como a emergente rede 5G. Com a utilização da rede 5G no agronegócio pode ajudar no aprimoramento do monitoramento de diversas condições de campo, da detecção antecipada da necessidade de irrigação e da pulverização de defensivos ou fertilizantes através de uma rede de sensores wireless. Assim, neste trabalho foi proposto uma plataforma unificada de gerenciamento das operações de agronegócio por meio da conectividade 5G. Em específico, neste projeto, como um primeiro caso de uso, nos focamos na melhora do sistema de irrigação de modo que a produção de uma fazenda seja aumentada e a água seja utilizada de forma eficiente.
ALGORITMOS BIO-INSPIRADOS APLICADOS À ANÁLISE GRÁFICA EM DAY TRADE DE STOCK MARKET
(2021-06-18) LUCA LENZARINI SILVA; MICHEL KRAHENBUHL BERNILS
A predição de tendência no mercado financeiro desempenha um importante papel na busca pelo lucro maximizado em investimentos. Analistas utilizam indicadores de análise téc- nica para efetuarem estudos do comportamento do mercado, o que gera enorme volume de dados diariamente. Porém, devido à intensa volatilidade e não-linearidade de valores, a pre- dição de preços de produtos financeiros se torna um dos maiores desafios para os investidores efetuarem manualmente. Por outro lado, a previsão probabilística desses ativos, ainda é um problema computacional relevante e sem solução definitiva. Sendo assim, o presente trabalho apresenta uma metodologia para predição de valores de ativos financeiros utilizando eventos probabilísticos com pesos de importância que são calculados por meio de algoritmos bioinspi- rados. Os experimento mostram que a metodologia proposta obteve uma média de curva ROC de 0,893 na predição de valores de ativos utilizando variaveis macroecônomicas, tais como va- riação do dólar e taxa SELIC. Dentre os algoritmos bioinspirados utilizados, o que mostrou melhores resultados foi o algoritmo Bat, alcançando uma média de 0,744 em termos de área sobre a curva ROC, para as variáveis macroeconômicas, mostrando que o método proposto é promissor.
ANÁLISE DE SENTIMENTOS BASEADA EM INFORMAÇÕES FACIAIS DURANTE AULA VIRTUAL
(2021-06-17) ALEXANDRE CARDOSO FEITOSA; ANDRE LUIZ BARONI; EDUARDO BAPTISTA DOS SANTOS; FILIPI GUIMARÃES SILVA; LUCAS MACHADO SERAIN
As aulas virtuais estão cada vez mais comuns na vida dos estudantes, especialmente durante a quarentena causada pela pandemia da doença COVID-19, em que grande parte das instituições educacionais adotaram esse sistema de ensino. Um dos principais desafios desta modalidade de educação é resolver o distanciamento entre aluno e professor, que impossibilita a percepção do docente sobre os sentimentos dos estudantes em um contexto no qual as expres- sões faciais dos alunos entregam informações não-verbais importantes frente ao que é abordado em sala. Embora existam diferentes sistemas para a avaliação da expressão facial, poucos tra- balhos entre os levantados foram criados objetivando um ambiente de ensino a distância e, por este motivo, não solucionam a ausência da expressão facial do aluno. O presente trabalho apre- senta duas metodologias para lidar com esse problema: uma baseada no Facial Action Coding System (FACS) e outra baseada em redes neurais convolucionais. Aplicando estas técnicas, foi possível unir a área de visão computacional com a área de aprendizado de máquina, quantifi- cando o sentimento do aluno enquanto visualiza uma determinada videoaula com até 79,97% de acurácia em determinadas emoções. A partir desta quantificação, o sistema foi capaz de gerar um relatório que apresenta os sentimentos predominantes em determinados intervalos de tempo.
Analysis of the PSO Parameters for a Robots Positioning System in SSL
(2019-07-08) LAUREANO, M. A. P.; Flavio Tonidandel
© 2019, Springer Nature Switzerland AG.The changes in the Small Size League rules have brought greater possibilities of playing. With the increased complexity of soccer matches, the positioning of the robots has become important as a defense and attack mechanism. The learning of opposing team game playing has been shown to be effective, but an SSL soccer match indicates the need for solutions that analyze the strategy of the opposing team during the game and make any necessary adaptations. This paper proposes the use of the Particle Swarm Optimization (PSO) algorithm as an option to determine the positioning during the match. A prototype has been developed to validate the configuration parameters. Experiments in a simulator, analysis of game logs and results in a real matches have demonstrated the feasibility of applying the PSO algorithm to find the robots positions.
Analyzing natural human language from the point of view of dynamic of a complex network
(2016) Wachs-Lopes G.A.; Rodrigues P.S.
© 2015 Elsevier Ltd.With increasing amount of information, mainly due to the explosive growth of Internet, the demand for applications of automatic text analysis has also grown. One of the tools that has increased in importance in the understanding of problems related to this area are complex networks. This tool merges graph theory and statistical methods for modeling important problems. In several research fields, complex networks are studied from the various points of view, such as: topology of networks, extraction of physical features and statistics, specific applications, comparison of metrics and study of physical phenomena. Linguistic is one area that has received great attention, particularly due to its close relationship with issues arising from the emergence of large text databases. Thus, many studies have emerged for modeling of complex networks in this area, increasing the demand for efficient algorithms for feature extraction, network dynamic observation and comparison of behavior for different types of languages. Some works for specific languages such as English, Chinese, French, Spanish, Russian and Arabic, have discussed the semantic aspects of these languages. On the other hand, as an important feature of a network we can highlight the computation of average clustering coefficient. This measure has a physical impact on the network topology studies and consequently on the conclusions about the semantics of a language. However its computational time is of O(n3), making its computing prohibitive for large current databases. This paper presents as main contribution a modeling of two complex networks: the first one, in English, is constructed from a specific medical database; the second, in Portuguese, from a journalistic manually annotated database. Our paper then presents the study of the dynamics of these two networks. We show their small-world behavior and the influence of hubs, suggesting that these databases have a high degree of Modularity, indicating specific contexts of words. Also, a method for efficient clustering coefficient computation is presented, and can be applied to large current databases. Other features such as fraction of reciprocal connections and average connection density are also calculated and discussed for both networks.
Anti-patterns apoiando a documentação dos problemas de usabilidade
(2008) MASIERO, A. A.; LOPES, G.; GONÇALVES, M. H.; AQUINO JUNIOR, Plinio Thomaz
Este artigo descreve uma metodologia para documentação de barreiras encontradas em interfaces. A partir de uma avaliação realizada em qualquer interface é possível documentar estas barreiras utilizando o conceito de anti-patterns, gerando uma base de conhecimento para evitar re-trabalhos futuros e auxiliar no design de interfaces
Aplicação de sensores e modelo geomorfológico para monitoração de áreas de riscos de acidentes naturais
(2016) OLIVATTI, Y. M.; PEREIRA, A. K. A.; MAIA, Rodrigo
Com o crescimento populacional em grandes polos urbanos a ocupação de áreas com risco de desastres naturais cresce constantemente, tornando o trabalho para evacuação, em momentos emergenciais, cada vez mais complexo. Atualmente, um dos dispositivos de comunicação mais difundidos são os celulares. Este trabalho propõe, utilizando modelos matemáticos, identificar a possibilidade de uma situação de risco ocorrer e acionar, por meio de um aplicativo móvel, após a decisão de um especialista responsável pelo monitoramento, a população que se encontra na área de risco e indicar uma área segura para evacuação. Espera-se, com o modelo utilizado, identificar poten¬ciais ocorrências de desastres naturais e que estas informações possam ser suficientes para salvar a população local
APLICAÇÃO GAMIFICADA PARA COLETA DE EMOÇÕES E CRIAÇÃO DE PERSONAS DE ALUNOS
(2021-12-17) LETICIA ALGUSTO PENHA; JOAO VICTOR FERSURA MOREIRA; JULIO CESAR SCHLINDWEIN DA SILVA
Desde seu primórdio, a humanidade sempre buscou resolver os problemas que possuiam com criatividade e inovação. Isso continua sendo uma verdade até nos dias atuais, em que ainda é possível melhorar a situação de vários problemas existentes no mundo, como a educação, que será o foco desse trabalho. Baseado em uma série de estudos sobre clusterização, educação e tecnologia, gamificação e personas, decidiu-se criar um aplicativo que ajude o docente a conhecer seus alunos mais profundamente e em menos tempo. Com os questionários que a turma de um professor responder, a aplicação atribuirá a cada aluno uma persona e também gerará relatórios estatísticos. Assim, ao analisar essas informações, o lecionador poderá encontrar novas maneiras de melhorar a qualidade de suas aulas na perspectiva de seus alunos até satisfazer toda a classe. A metodologia adotada foi dividida em 4 seções, cada uma representando uma parte do ciclo de funcionamento do produto final: coleta de dados, processamento de dados, geração de relatórios e manutenção dos usuários. Os resultados apontaram que o sistema de agrupamento de alunos por personas funcionou como planejado. Espera-se que o presente trabalho possa melhorar o estado da educação e servir de inspiração para que mais contribuições desse tipo sejam feitas no futuro.

Navegar

Navegando Ciência da Computação por Título

Resultados por página

Opções de Ordenação