Bacharelado em Ciência da Computação (Sede)
URI permanente desta comunidadehttps://arandu.ufrpe.br/handle/123456789/6
Siglas das Coleções:
APP - Artigo Publicado em Periódico
TAE - Trabalho Apresentado em Evento
TCC - Trabalho de Conclusão de Curso
Navegar
10 resultados
Resultados da Pesquisa
Item Comparative Analysis of Data Augmentation Techniques in Hand Gesture Recognition(2025-03-18) Souza, Diego Rafael Ferreira de; Macario Filho, Valmir; http://lattes.cnpq.br/4346898674852080; http://lattes.cnpq.br/0925751641833600Hand gesture recognition has gained significant attention due to its widespread applications in human-computer interaction, virtual reality, and assistive technologies. However, the scarcity of large, labeled datasets poses challenges such as overfitting and limited model generalization. To address this, we systematically evaluate 13 classical and six state-of-the-art (SOTA) data augmentation techniques for hand gesture recognition, conducting experiments on HGR1, OUHANDS, LIBRASUEFS, and EgoHands using the HGR-Net CNN architecture. Our results show that contrast-based augmentations (e.g., Solarize, Invert) improved accuracy by up to 21.16%, while mixing-based methods (e.g., MixUp, CutMix) often reduced performance, likely due to excessive distortion of gesture structures. Additionally, combining the best-performing augmentations was critical for maximizing accuracy across all datasets. However, these combinations did not always produce additive improvements, underscoring the importance of dataset-specific augmentation strategies for achieving optimal model performance.Item Modelos de recomendação sensível ao contexto em ambientes de comunicação aumentativa alternativa: naive bayes, redes neurais e aprendizagem federada(2025-03-19) Nascimento, Fabio Augusto Souza do; Nascimento, André Câmara Alves do; http://lattes.cnpq.br/0622594061462533; http://lattes.cnpq.br/2170186670973508A inteligência artificial (IA) está presente em diversos setores da sociedade, promovendo constantes avanços tecnológicos e sociais. Um dos subconjuntos da IA é a aprendizagem de máquina (AM), que possibilita aos computadores aprenderem e evoluírem com base em dados. O conhecimento obtido por meio desse processo auxilia em diferentes áreas, desde a análise e interpretação de informações até a usabilidade de aplicativos. Compreender o funcionamento e as possibilidades dessa ferramenta pode ser um ativo valioso. Entre as múltiplas aplicações possíveis, a AM desempenha um papel importante na comunicação aumentativa e alternativa (CAA), auxiliando indivíduos que apresentam dificuldades nessas interações por meio de aplicativos. Essas aplicações estão em constante evolução e, com as inovações tecnológicas, possibilitam o desenvolvimento de sistemas capazes de compreender o ambiente em que uma pessoa está inserida e oferecer recomendações personalizadas aos usuários. Este trabalho investiga o uso dos Sistemas de Recomendação Sensível ao Contexto (SRSC) em aplicações da CAA, considerando as características individuais dos usuários com base em seus dados e contexto. São utilizados modelos de IA, tais como Naïve Bayes (NB), Redes Neurais Artificiais (RNA) e Aprendizagem Federada (AF), para comparar diferentes abordagens e avaliar sua capacidade de fornecer resultados relevantes. A partir dos experimentos realizados, foi possível verificar que modelos personalizados demonstram melhor desempenho em relação a abordagens globais, oferecendo recomendações mais relevantes aos usuários finais. Nesse sentido, a personalização e o uso de variáveis contextuais podem melhorar significativamente a experiência de pessoas que dependem de CAA, aumentando a agilidade e a assertividade da comunicação.Item Comparison of recommendation algorithms for user groups: a food-based case study(2023-04-24) Vasconcelos, Caio Giovanni Pereira; Silva, Douglas Véras e; http://lattes.cnpq.br/2969243668455081; http://lattes.cnpq.br/4775036700843482Item Uma metodologia para a avaliação de desempenho e custos do treinamento de redes neurais em ambientes de nuvem(2024-03-07) Moura Filho, Cláudio Márcio de Araújo; Sousa, Érica Teixeira Gomes de; http://lattes.cnpq.br/9899077867723655; http://lattes.cnpq.br/8143173691280119Deep neural networks are solutions to problems involving pattern recognition and several works try to find ways to optimize the performance of these networks. This optimization requires suitable hardware to be implemented, hardware that can be very expensive for small and medium-sized organizations. The objective of this work is to propose a methodology to evaluate the performance and cost of training neural networks, considering the factors that most impact training time and evaluate the total financial cost of the environment for this task. In this sense, it was observed that factors such as the size of the input image and the network architecture have a great impact on the training time metric and consequently on the total cost.Item Rastreamento de pedestres 3D multi-câmera usando redes neurais de grafos(2022-05-27) Andrade, Isabella Stefanny Fernandes de; Lima, João Paulo Silva do Monte; http://lattes.cnpq.br/1916245590298485; http://lattes.cnpq.br/5529506615862118Tracking the position of pedestrians over time through camera images is a rising computer vision research topic. In multi-camera settings, the researches are even more recent. Many solutions use supervised neural networks to solve this problem, which can require a lot of effort to annotate the data in addition to a lot of time spent to train the network. The goals of this work are: develop variations of pedestrian tracking algorithms, being desirable to avoid the need to have annotated data; and compare the results obtained through accuracy metrics. Therefore, this work proposes an approach for tracking pedestrians in 3D space in multi-camera environments using the Message Passing Neural Network framework inspired by graphs. We evaluated the solution using the WILDTRACK dataset and a generalizable detection method, reaching 77.1% of MOTA when training with data obtained by a generalizable tracking algorithm. The algorithm can track at a 40 frames per second rate.Item Estudo de viabilidade de sistemas de detecção de armamentos em tempo real em linhas de ônibus urbanos(2021-12-09) Lima Junior, Cícero Pereira de; Silva, Douglas Véras e; http://lattes.cnpq.br/2969243668455081; http://lattes.cnpq.br/9901763283774954Surveillance systems are fundamental on preventing armed robberys on public busses. However, to be operated in real-time theses systems demand an unrealistic amount of people. The usage of computer vision and deep learning technics raises as a way to automate parts or even the whole surveillance process, from the weapons detection to the alarm triggering. For this process to be accomplished efficiently, allowing authorities to take more effective actions, the system needs to be able to handle a growing security cameras demand. Thus, this work analyses a bus line weapon detection system viabillity. Through simulation, this work evaluated the perfomance of YOLO algorithm, in its fourth version, on a client-server model under a growing security camera demand. The server is composed of a Tesla V80 GPU with a 12GB memory, Intel Xeon dual core processor, 61GB RAM memory and 200GB disk space. Finally, from the gathered results, its observable that the application presents a detection time increase after having introduced 16 virtual users (cameras), also the average response time cannot be considered as real-time, on bus security context.Item Aprendizado profundo com capacidade computacional reduzida: uma aplicação à quebra de CAPTCHAs(2018-08-16) Melo, Diogo Felipe Félix de; Sampaio, Pablo Azevedo; http://lattes.cnpq.br/8865836949700771; http://lattes.cnpq.br/2213650736070295During the last decade, Deep Neural Networks has been shown to be a powerfull machine learn technique. Generally, to obtain relevant results, these techniques require high computacional power and large volumes of data, which can be a limiting factor on some cases. Neverthless, a careful project of trainig and archtecture may help to reduce these requirements. In the this work we present a comparative approach to the application of deep neural networks to text based CAPTCHAs as a way to cope with these limitations. We studied models that are capable of learn to segment and identify the text content of images, only based on examples. By experimentation of different hiper-parameters and architectures, we were capable to obtain a final model with 96.06% of token prediction accuracy in approximately 3 hours of training in a simple personal computer.Item Um currículo de aprendizado por reforço para o cenário “Run to Score with Keeper” do Google Research Football Environment(2019-12-10) Silva, Jonatan Washington Pereira da; Sampaio, Pablo Azevedo; Macário Filho, Valmir; http://lattes.cnpq.br/4346898674852080; http://lattes.cnpq.br/8865836949700771; http://lattes.cnpq.br/6846637095187550Reinforcement learning is a group of techniques that allow an agent to interact with a particular environment. Agents observe the state of the environment and perform an action, the action is evaluated through a reward obtained. The agent objective is to maximize this reward. Various issues such as three-dimensional locomotion and electronic games have been addressed by reinforcement learning (KURACH et al., 2019). The Trainament of agents for a soccer game usually has sparse rewards, what slows learning (MATIISEN et al., 2019). One technique that can solve this obstacle is the curriculum learning proposed in (BENGIO et al., 2009). This technique use simplest tasks of the main task and the increase difficult level with the time. In This work we present two curriculum, identified as 5-15-30-50 e 3-10-20-67, for the scenario Run To Score With Keeper of Football Academy. We have shown that curriculums on average achieved better results compared to training only in the main scenario, without curriculum. Curriculum 3-10-20-67 achieved a better result even considering the pattern deviation.Item Classificação de documentos de identificação com redes neurais convolucionais(2019-01-18) Rocha, Alessandro Nazário da; Sampaio, Pablo Azevedo; http://lattes.cnpq.br/8865836949700771; http://lattes.cnpq.br/2466292990350036Deep Learning has played an important role in data processing, with one of its main techniques being convolutional neural networks, which has the power to automatically learn features included in images in their layers. However, these deep artificial neural networks need a significant amount of images, for the proposed problem, already separated into categories to perform the training and validations of models that are not always available. In this context, in this work was constructed a dataset with images of Brazilian identification document of National Registry (RG) and National Qualification Card (CNH) separating them into some categories and, since they are documents with sensitive information, add a significant amount of images to obtain good results, it was a step that took time. For this reason, care was taken to preserve this sensitive information. This work presents some architectures of deep artificial neural networks to classify the images for different categories. Experiments were performed using a graphics processing unit (GPU) and using only the central processing unit (CPU). Results above 99% were obtained in some scenarios that were tested in the course of the work for the different proposed architectures.Item Proposta de um meta-modelo para avaliação de robutez de redes de computadores com base na combinação de métricas topológicas(2017) Barros, Gustavo Henrique Pinto Soares de; Araújo, Danilo Ricardo Barbosa de; http://lattes.cnpq.br/2708354422178489; http://lattes.cnpq.br/1155438495823549A growing demand for resilience and robustness in the field of computer networks rises from the great diversity of its aplications. The modern sistems display an increasing critical nature, and the occurrence of perturbations may cause significant losses either human, monetary or environmental. Optical fiber acts on the current systems as the main mean of transportation. Among its variety of applications, which are heavily dependant on its infrastructure, some of them are the internet, cable television and high transmission rates systems. The non-homogeneous and complex topology nature of these networks determine their increasing avaluation cost. For these reasons, optical networks are the study object of this research. Quantifying the robustness of networks is usually accomplished by nodes and links failure simulations, on which the monetary and temporal cost scales proportionally to the network size. This research analyzes the possibility of obtaining values of robustness metrics in complex networks which would originally be obtained from simulations through an alternative regression method. This method has as inputs the values of simple metrics which are obtained through applications other than simulations and uses artificial neural networks to forecast simulation results in a smaller period. The results are obtained through a comparison between the proposed model output and the node and link failure simulation output. They indicate that the proposed model presents a satisfactory error margin, between 10−³ and 10−9, thus the simulation values were reached successfully through regression on a smaller time period.