Mestrado em Ciência da Computação (INF)

URI Permanente para esta coleçãohttp://200.137.215.59/tede/handle/tde/225

Navegar

Agora exibindo 1 - 20 de 330

Energy-aware approaches to resource allocation in open radio access networks
(Universidade Federal de Goiás, 2026-02-09) Pires Junior, William Teixeira; Pinto, Leizer de Lima; https://lattes.cnpq.br/0611031507120144; Cardoso, Kleber Vieira; http://lattes.cnpq.br/0268732896111424; Cardoso, Kleber Vieira; http://lattes.cnpq.br/0268732896111424; Klautau Júnior, Aldebaro Barreto da Rocha; https://lattes.cnpq.br/1596629769697284; Longo, Humberto José; https://lattes.cnpq.br/0188685041571480
The evolution of mobile communication networks toward 5G and beyond seeks to meet the demands for high throughput, low latency, and energy efficiency. Open Radio Access Networks (O-RAN), with their disaggregated and virtualized architecture, provide flexibility and interoperability but also pose significant challenges in terms of energy consumption. This work addresses energy-aware resource allocation in O-RAN, focusing on Virtualized Network Function (VNF) placement and user equipment association. We propose a Mixed Integer Linear Programming model that jointly considers radio equipment, transport network, and VNF migration energy costs while supporting flexible functional split options and routing decisions, complemented by a heuristic for scalability. Using synthetic load and topology generators, we evaluate diverse scenarios and show that hierarchical topologies achieve up to 15% more centralization and reduce energy consumption by about 28% compared to current widely adopted topologies. Additionally, joint optimization of VNF placement and user equipment association enables significant energy savings by disabling entire base stations during moments of low load. A disjoint approach to the problem is able to solve larger instances of the problem and achieves solutions close to optimal while surpassing a maximum-Signal to Noise Ratio (SNR) solution. Despite the optimal solutions being unable to meet the stringent response time required in practical deployments, they present a robust baseline for the evaluation of both the network and non-optimal approaches to the problem.
Previsão de nascidos vivos nas regiões de saúde do Brasil através de modelos de aprendizado de máquina baseados em árvore
(Universidade Federal de Goiás, 2024-11-13) Nascimento, Douglas Vieira do; Galvão filho, Arlindo Rodrigues; http://lattes.cnpq.br/7744765287200890; Galvão Filho, Arlindo Rodrigues; http://lattes.cnpq.br/7744765287200890; Soares, Anderson da Silva; http://lattes.cnpq.br/1096941114079527; Sousa , Rafael Teixeira; http://lattes.cnpq.br/3819400092348829
Forecasting tree-based models are a type of predictive modeling technique that uses decision trees to make predictions about future values or events. These models are good choices due to their ability to model non-linear relationships, which is why they were applied to predicting live births with multiple covariates. The study uses data from the Brazilian Ministry of Health to train and evaluate forecasting models, following the guidelines of the Ministry’s expectations and needs for public policy planning. The study uses data from all 450 microregions in Brazil with records between the years 2000 and 2020. The objective is to train a tree-based model with all months between 2000 and 2018 to evaluate the performance of predicting the number of births over of the years 2019 and 2020. LightGBM, XGBoost and Catboost were evaluated and compared with AutoARIMA and simple linear regression. LightGBM performed slightly better than other evaluated models, achieving a MAPE of 0.0797, with a more consistent performance over the 24-month forecast horizon. The results show that tree-based models are reliable for handling multiple covariates and can be a useful tool for public policy planning. Keywords
Modelo arquitetural para monitoramento remoto de pacientes em cuidados paliativos domiciliares
(Universidade Federal de Goiás, 2025-10-23) Martins, Matheus Brito; Santos, Silvana de Lima Vieira dos; http://lattes.cnpq.br/2461784381351166; Carvalho, Sérgio Teixeira de; http://lattes.cnpq.br/2721053239592051; Carvalho, Sérgio Teixeira de; http://lattes.cnpq.br/2721053239592051; Santos, Silvana de Lima Vieira dos; http://lattes.cnpq.br/2461784381351166; Izidoro, Livia Cristina de Resende; http://lattes.cnpq.br/0102271932510852; Berretta, Luciana de Oliveira; http://lattes.cnpq.br/0987947348533817
he management of palliative care for home-based patients faces challenges in maintaining continuous monitoring of their symptoms after hospital discharge. Although palliative care aims to provide better quality of life for patients with life-threatening illnesses, the lack of remote monitoring tools hinders this process and results in delays in interventions for patients outside the hospital environment. The use of mobile monitoring technologies, such as mHealth applications, combined with data security measures based on blockchain, can support symptom monitoring for patients receiving palliative care at home. This approach enables real-time remote monitoring and contributes to the security and privacy of sensitive information collected during the period outside the hospital setting. The objective of this work is to propose a system model for monitoring home-based palliative care patients. The work uses mobile devices in an Android environment to collect information through questionnaires registered by healthcare professionals, combined with the use of blockchain to ensure data integrity and security. To achieve this objective, the research conducts a systematic literature review on technologies and methodologies employed in the mHealth field for home-based palliative care patients and develops a proposal based on the identified gaps. The research presents a conceptual model, the architecture, and the tools used for development, as well as the evaluation carried out by palliative care healthcare professionals at HC-UFG, who are responsible for monitoring the patients. The questionnaires administered to professionals indicated high acceptance of the system, with positive perceived usefulness and intention to use, satisfactory ease of use, and practical suggestions for the next steps. Deployment and testing with end users are planned as future stages, aiming to evolve the proposed model and expand support for home-based palliative care patients.
Otimização de portfólio de ativos do mercado financeiro brasileiro: integrando notícias e indicadores fundamentalistas com aprendizado por reforço profundo
(Universidade Federal de Goiás, 2025-09-16) Silva, Kéthlyn Campos; Fernandes, Deborah Silva Alves; http://lattes.cnpq.br/0380764911708235; Fernandes, Deborah Silva Alves; http://lattes.cnpq.br/0380764911708235; Soares , Fabrízzio Alphonsus Alves de Melo Nunes; http://lattes.cnpq.br/7206645857721831; Pires, Sandrerley Ramos; http://lattes.cnpq.br/0685245697561631
This study investigates the impact of incorporating fundamental and sentiment-based indicators, extracted from Portuguese news, into deep reinforcement learning (DRL) algorithms for portfolio optimization in the Brazilian financial market. The research involves collecting news articles, historical data, and financial indicators of assets, with sentiment and key entities extracted from the news using the Gemini Pro Large Language Model. To refine sentiment indicators, entity- and topic-based filtering techniques are applied to reduce informational noise. Statistical analyses using correlation coefficients show that entity-based filtering enhances the relationship between sentiment indicators and daily asset returns. Subsequently, sentiment and fundamental indicators are integrated into five DRL algorithms, tested across four distinct scenarios: (1) prices only, (2) prices and sentiment, (3) prices and fundamental indicators, and (4) all combined. A total of 44 samples were generated. Although the Kruskal-Wallis test did not reveal statistically significant differences between the scenarios, all DRL-based models outperformed baseline strategies such as Buy and Hold and the Ibovespa index in terms of Sharpe Ratio, indicating higher returns with better risk control. These findings suggest that the use of DRL algorithms can contribute to more effective risk management in portfolios composed of Brazilian financial market assets.
Raciocínio parcial em modelos de linguagem: busca e refinamento guiados por incerteza
(Universidade Federal de Goiás, 2025-12-18) Luz, Murilo Lopes da; Soares, Telma Woerle de Lima; http://lattes.cnpq.br/6296363436468330; Soares, Telma Woerle de Lima; Máximo, Marcos Ricardo Omena de Albuquerque; Vieira, Flavio Henrique Teles
Embargado
Explorando Rubricas Educacionais para Fomentar a Aprendizagem Regulada de Alunos em Cursos Iniciais de Programação
(Universidade Federal de Goiás, 2026-11-29) Lima, Maurício Rodrigues; Dias, Elisângela Silva; http://lattes.cnpq.br/0138908377103572; Ferreira, Deller James; http://lattes.cnpq.br/1646629818203057; Dias, Elisângela Silva; http://lattes.cnpq.br/0138908377103572; Berretta, Luciana de Oliveira; http://lattes.cnpq.br/0987947348533817; Cardoso, Evellin Cristine Souza; http://lattes.cnpq.br/3304385875966984; Rodrigues, Cássio Leonardo; http://lattes.cnpq.br/2590620617848677; Carvalho, Sérgio Teixeira de; http://lattes.cnpq.br/2721053239592051
Resumo
Dimensionamento adaptativo de microsserviços para aplicações de realidade virtual
(Universidade Federal de Goiás, 2025-10-23) Gonçalves, André Luiz de Jesus; Freitas, Leandro Alexandre; http://lattes.cnpq.br/7450982711522425; Oliveira Junior, Antonio Carlos de; http://lattes.cnpq.br/3148813459575445; Oliveira Junior, Antonio Carlos de; http://lattes.cnpq.br/3148813459575445; Freitas, Leandro Alexandre; http://lattes.cnpq.br/7450982711522425; Rodrigues, Vagner José do Sacramento; http://lattes.cnpq.br/4148896613580056
Embargado
Caracterização de funções de realidade aumentada usando computação de borda
(Universidade Federal de Goiás, 2025-06-02) Rodrigues, Karlla Bianca Chaves; Cardoso, Kleber Vieira; http://lattes.cnpq.br/0268732896111424; Corrêa, Sand Luz; http://lattes.cnpq.br/3386409577930822; Correa, Sand Luz; http://lattes.cnpq.br/3386409577930822; Both, Cristiano Bonato; http://lattes.cnpq.br/2658002010026792; Berretta, Luciana de Oliveira; http://lattes.cnpq.br/0987947348533817
The growing use of immersive applications—such as augmented reality, virtual reality, and mixed reality—has led to increasing demand for more efficient computational resources capable of real-time data processing. While cloud computing can meet these demands, it often introduces high latency, negatively affecting the user experience. Edge computing emerges as a promising alternative by bringing computational resources closer to enduser devices, reducing latency, enhancing immersion, and enabling the deployment of such applications on mobile devices. Understanding the functional components of these applications and their performance profiles is essential for efficient offloading between mobile devices and edge servers. This work aims to characterize two core tasks in mobile augmented reality applications: Simultaneous Localization and Mapping (SLAM) and object detection. To this end, the MR-Leo prototype was used, integrating ORB-SLAM2 and incorporating a new object detection functionality based on the YOLO architecture. The research evaluates the performance of these tasks under different hardware configurations, considering execution on both CPUs and GPUs. The results show that although SLAM is computationally intensive, it performs acceptably on CPU-based architectures. In contrast, object detection requires massive parallelism for satisfactory performance and is heavily dependent on GPU usage. Based on the task characterization, a statistical workload model was developed to support the creation of workload generators capable of emulating the behavior of augmented reality applications under different computational architectures and scenarios.
Estratégia de alocação dinâmica de recursos no Kubernetes para ambientes multi-inquilinos
(Universidade Federal de Goiás, 2025-10-15) Gabriel Eduardo de Bessa Maciel; Oliveira Junior, Antonio Carlos de; http://lattes.cnpq.br/3148813459575445; Oliveira Junior, Antonio Carlos de; http://lattes.cnpq.br/3148813459575445; Gomes, Raphael de Aquino; http://lattes.cnpq.br/4136576326278536; Santos, Carlos Eduardo da Silva; http://lattes.cnpq.br/5815707716439139; Freitas, Leandro Alexandre; http://lattes.cnpq.br/7450982711522425
The growing adoption of cloud-native applications has intensified the demand for efficient and secure multi-tenancy solutions in Kubernetes environments. However, dynamic resource allocation in shared environments presents significant challenges, requiring a balance between maximizing resource utilization and ensuring strict isolation between tenants. This study addresses these challenges by analyzing multi-tenant usage in Kubernetes, identifying its potential and limitations. Based on this analysis, we propose the Multi-Tenant Strategy for Kubernetes (EMK), which incorporates a Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS)-based algorithm for multi-criteria decision-making in dynamic resource allocation. This approach is integrated into a Kubernetes operator, enabling more efficient and automated tenant management while optimizing resource distribution in multi-tenant scenarios. The experimental evaluation was conducted in a Kubernetes cluster environment, considering different workload scenarios (light, moderate, and heavy). Performance indicators such as response time, allocation success rate, cluster flexibility, and adaptability were analyzed, all collected through Kubernetes’ native monitoring tools. The results demonstrated that the EMK reduces average latency and improves system stability under varying load conditions when compared to traditional allocation, highlighting greater efficiency and resilience in multi-tenant resource management.
SLArch: Arquitetura de Split Learning orientada a métricas de rede para desempenho de Redes Móveis B5G/6G
(Universidade Federal de Goiás, 2025-10-02) Reis, Cleyber Bezerra dos; Ribeiro, Maria do Rosário Campos; http://lattes.cnpq.br/1285706867893743; Oliveira Júnior, Antonio Carlos de; http://lattes.cnpq.br/3148813459575445; Oliveira Júnior, Antonio Carlos de; http://lattes.cnpq.br/3148813459575445; Ribeiro, Maria do Rosário Campos; http://lattes.cnpq.br/1285706867893743; Moreira Júnior, Waldir Aranha; http://lattes.cnpq.br/4552403112118292; Lopes, Victor Hugo Lázaro; http://lattes.cnpq.br/8690054906597785
Split Learning (SL) is a collaborative learning technique in which a neural network model is partitioned between client and server, enabling training without the need to share the original data. This study investigates the integration of SL with B5G/6G mobile networks using the ns-3 simulator and a convolutional neural network (CNN) trained on the MNIST dataset. We evaluated model-performance metrics, such as accuracy, as well as network indicators including packet loss, latency, throughput, and energy consumption. The results demonstrate that increasing transmit power reduces latency and improves model accuracy. The SL model exhibited performance variability with distance but maintained satisfactory accuracy (>80%) at distances up to 160 m in the highest-power scenario. These findings demonstrate the viability of SL as an enabling technology for next-generation mobile networks, optimising distributed training in communicationconstrained settings.
Aquisição Progressiva de Habilidades por meio de Curriculum Learning para Futebol de Robôs Multiagente
(Universidade Federal de Goiás, 2025-03-11) Guimarães, Werikcyano Lima; Soares, Telma Woerle de Lima; http://lattes.cnpq.br/6296363436468330; Soares, Telma Woerle de Lima; http://lattes.cnpq.br/6296363436468330; Salazar, Aldo André Diaz; http://lattes.cnpq.br/2265620121158672; Máximo, Marcos Ricardo Omena de Albuquerque; http://lattes.cnpq.br/1610878342077626
This work investigates the integration of Curriculum Learning with Self-play for rein- forcement learning in the context of SSL-EL robot soccer. The research addresses the challenge of developing efficient policies in complex multi-agent environments by proposing a structured methodology that decomposes learning into progressive stages. The implemented framework establishes adaptive criteria for transitioning between tasks, allowing agents to initially develop fundamental skills before facing complete competitive scenarios. The experimental results clearly demonstrate the superiority of the combined approach, with significantly higher win rates in competitive tournaments compared to traditional Full Self-play, as well as an expressive increase in the average goals per match. Additionally, a substantial reduction in total training time and greater stability in the learning process were observed, evidenced by metrics such as policy entropy, policy loss, and explained variance. The analyses confirm that Curriculum Learning provides a solid technical foundation that enhances the benefits of Self-play, resulting in agents with more sophisticated and efficient tactical capabilities.
Aprimoramento de dados para SFT em português brasileiro: um estudo com modelos de língua e avaliação com LLM-as- Judge
(Universidade Federal de Goiás, 2025-06-10) Rios, Walcy Santos Rezende; Galvão Filho, Arlindo Rodrigues; http://lattes.cnpq.br/7744765287200890; Galvão Filho, Arlindo Rodrigues; http://lattes.cnpq.br/7744765287200890; Oliveira , Sávio Salvarino Teles de; http://lattes.cnpq.br/1905829499839846; Soares, Telma Woerle de Lima; http://lattes.cnpq.br/6296363436468330
The scarcity of high-quality resources for Brazilian Portuguese (pt-br) hinders the development of effective language models adapted to the language's specificities. This work investigates the impact of synthetic enhancement of conversational data, using Large Language Models (LLMs), on the Supervised Fine-Tuning (SFT) of models from the Qwen2.5 family (0.5B, 1.5B, 3B). Based on the SmolTalk dataset, two versions were generated for ptbr: one by direct translation and another with responses synthetically enhanced and rewritten by the LLM Gemini 2.0 Flash. The Qwen2.5 models were trained on both datasets and comparatively evaluated using standardized objective benchmarks for Portuguese (ENEM, HATEBR, BLUEX, ASSIN2-RTE) and through qualitative evaluation of open-ended text generation (Alpaca-Eval-BR), using Claude 3.5 Haiku as LLM-as-Judge based on relevance, precision, comprehensiveness, usefulness, and coherence criteria. The results demonstrate a significant superiority of the models trained with synthetic data in the qualitative LLM-as- Judge evaluation across all metrics. In this evaluation, the normalized average F1-Score significantly increased with synthetic data: the 1.5B model achieved 44.45 (vs 14.05 for the translated, a ~216% gain) and the 3B model reached 57.21 (vs 16.79 for the translated, a ~241% gain). In contrast, on the objective benchmarks, the positive impact of synthetic enhancement was less pronounced, being more consistent only in the 3B parameter version. It is concluded that the LLM-assisted synthetic data enhancement strategy is effective in significantly raising the quality and performance of conversational language models for Brazilian Portuguese, representing a valuable approach to mitigate the scarcity of dedicated resources and advance the development of NLP technologies better adapted to the national context.synthetic data enhancement strategy is effective in significantly raising the quality and performance of conversational language models for Brazilian Portuguese, representing a valuable approach to mitigate the scarcity of dedicated resources and advance the development of NLP technologies better adapted to the national context.
Enhanced-ProBlock: adaptações em uma abordagem descentralizada, baseada em checagem humana e apoiada por blockchain para consenso ponderado na detecção de desinformação
(Universidade Federal de Goiás, 2025-05-26) Damacena, Pedro Henrique Campos; Borges, Vinicius da Cunha Martins; http://lattes.cnpq.br/6904676677900593; Lima; Borges, Vinicius da Cunha Martins; http://lattes.cnpq.br/6904676677900593; Lima, Eliomar Araújo de; http://lattes.cnpq.br/1362170231777201; Graciano Neto, Valdemar Vicente; http://lattes.cnpq.br/9864803557706493
Embargada.
Verificação semi-automática de fatos em português: enriquecimento de corpus via busca e extração de alegação
(Universidade Federal de Goiás, 2025-06-10) Gomes, Juliana Resplande Sant'Anna; Galvão Filho, Arlindo Rodrigues; http://lattes.cnpq.br/7744765287200890; Galvão Filho, Arlindo Rodrigues; http://lattes.cnpq.br/7744765287200890; Lima, Eliomar Araújo de; http://lattes.cnpq.br/1362170231777201; Soares, Telma de Woerle de Lima; http://lattes.cnpq.br/6296363436468330
The accelerated dissemination of disinformation often outpaces the capacity for manual fact-checking, highlighting the urgent need for Semi-Automated Fact-Checking (SAFC) systems. Within the Portuguese language context, there is a noted scarcity of publicly available datasets (corpora) that integrate external evidence, an essential component for developing robust AFC systems, as many existing resources focus solely on classification based on intrinsic text features. This dissertation addresses this gap by developing, applying, and analyzing a methodology to enrich Portuguese news corpora (Fake.Br, COVID19.BR, MuMiN-PT) with external evidence. The approach simulates a user’s verification process, employing Large Language Models (LLMs, specifically Gemini 1.5 Flash) to extract the main claim from texts and search engine APIs (Google Search API, Google FactCheck Claims Search API) to retrieve relevant external documents (evidence). Additionally, a data validation and preprocessing framework, including near-duplicate detection, is introduced to enhance the quality of the base corpora. The main results demonstrate the methodology’s viability, providing enriched corpora and analyses that confirm the utility of claim extraction, the influence of original data characteristics on the process, and the positive impact of enrichment on the performance of classification models (Bertimbau and Gemini 1.5 Flash), especially with fine-tuning. This work contributes valuable resources and insights for advancing SAFC in Portuguese.
Proposal and Evaluation of Efficient Pruning Approaches for Multi-Vector Representation in Passage Retrieval
(Universidade Federal de Goiás, 2025-06-13) Chihururu, Alex Michael; Rosa, Thierson Couto; http://lattes.cnpq.br/4414718560764818; Rosa, Thierson Couto; http://lattes.cnpq.br/4414718560764818; Brandão, Wladmir Cardoso; http://lattes.cnpq.br/4935788335854516; Martins, Wellington Santos; http://lattes.cnpq.br/3041686206689904
Multi-vector retrieval models employ bi-encoders to generate contextualized embeddings for queries and passages, and have proven highly effective in capturing fine-grained token-level interactions. Models such as ColBERT, ColBERTv2, and PLAID leverage all token-level output vectors from the encoder to accurately model query-passage relationships. However, storing dense vectors for every token in each passage results in substantial mem-ory overhead. Additionally, query latency is significantly affected by the computational cost of computing inner products between each query token and all passage tokens to obtain similarity scores. In this work, we explore pruning techniques applied to passage vectors produced by PLAID, aiming to remove less important token vectors to improve memory efficiency and reduce query processing time, with minimal impact on retrieval effectiveness. We propose two novel pruning methods: MLM Max with Token Reordering (MMTR) and TF-IDF pruning. We conducted extensive experiments on both in-domain and zero-shot (out-of-domain) datasets, following best-practice evaluation protocols. Our results show that MMTR consistently yields the smallest effectiveness drop compared to the original, unpruned PLAID model. We observe that retaining 50% of the passage to-ken embeddings provides the best trade-off between effectiveness, index size, and latency across most datasets. Interestingly, on certain out-of-domain datasets, pruning acts as a form of noise reduction—where retaining only 25% of the token embeddings leads to improved retrieval performance over the full, unpruned index.
Sliding puzzles gym: a scalable benchmark for state representation in visual reinforcement learning
(Universidade Federal de Goiás, 2025-01-09) Oliveira, Bryan Lincoln Marques de; Soares, Telma Woerle de Lima; http://lattes.cnpq.br/6296363436468330; Soares, Telma Woerle de Lima; http://lattes.cnpq.br/6296363436468330; Maximo, Marcos Ricardo Omena de Albuquerque; http://lattes.cnpq.br/1610878342077626; Vieira (, Flávio Henrique Teles; http://lattes.cnpq.br/0920629723928382
Embargada.
Channel-aware inter-slice scheduling for SLA assurance: theoretical and simulation-based approaches
(Universidade Federal de Goiás, 2025-06-20) Silva, Daniel Campos da; Cardoso, Kleber Vieira; http://lattes.cnpq.br/0268732896111424; Cardoso, Kleber Vieira; http://lattes.cnpq.br/0268732896111424; Rocha, Flávio Geraldo Coelho; http://lattes.cnpq.br/5583470206347446; Kibilda, Jacek
As the diversity of applications with heterogeneous Quality of Service (QoS) requirements grows in mobile networks, network slicing emerges as a key technology to meet Service Level Agreements (SLAs) by isolating resources among different types of services grouped into independent slices. Efficient inter-slice radio resource scheduling (RRS) is crucial in this context, directly governing the achievable throughput - and thus SLA assurance - while also enabling energy efficiency gains in low-demand scenarios through reduced resource usage and power consumption in the base station. This thesis investigates high-performance inter-slice RRS characteristics, including channelawareness, intra-slice RRS prediction, SLA-drift-oriented allocation, dynamic slice resource proportions, and fairness among users within the same slice. We formulate the RRS problem mathematically, facilitating the design of RRS heuristics approximating optimal solutions. Through simulations, we demonstrate how our proposed algorithms outperform state-of-the-art schedulers in both SLA assurance and resource efficiency.
Orquestração de recursos para a oferta de serviços, em infraestruturas híbridas de computação de borda e nuvem, com foco em aplicações de realidade mista
(Universidade Federal de Goiás, 2025-05-30) Fraga, Luciano de Souza; Pinto, Leizer de Lima; http://lattes.cnpq.br/0611031507120144; Cardoso, Kleber Vieira; http://lattes.cnpq.br/0268732896111424; Cardoso, Kleber Vieira; http://lattes.cnpq.br/0268732896111424; Pinto, Leizer de Lima; http://lattes.cnpq.br/0611031507120144; Rezende, José Ferreira de; http://lattes.cnpq.br/8588117212005149; Bueno, Elivelton Ferreira; http://lattes.cnpq.br/2764240045623948
Efficient resource allocation in hybrid edge-cloud computing environments is becoming increasingly important due to the growing adoption of mixed reality applications and the widespread use of devices with limited energy, processing, and memory resources. A welldesigned allocation strategy not only ensures compliance with the quality of service (QoS) requirements of these applications but also promotes optimized use of computational and network infrastructure, resulting in lower operational costs. In this work, we propose a model based on Integer Linear Programming (ILP) aimed at maximizing the fulfillment of demand generated by user devices, while minimizing the cost associated with the use of virtual machines responsible for processing. We evaluate the complexity of the model and propose structural simplifications, in addition to developing a heuristic designed to reduce solution generation time. Finally, we introduce a proactive approach based on a predictive model that anticipates resource usage patterns, contributing to more accurate decisions compared to reactive strategies. Experimental results demonstrate significant improvements in the volume of demand served when compared to other approaches in the literature, as well as highlight the benefits of adopting proactive strategies for resource allocation.
Segmentação dinâmica de objetos aplicada à odometria visual
(Universidade Federal de Goiás, 2024-10-02) Oliveira, Thiago Henrique de; Laureano, Gustavo Teodoro Laureano; http://lattes.cnpq.br/4418446095942420; Laureano, Gustavo Teodoro; http://lattes.cnpq.br/4418446095942420; Osório, Fernando Santos; http://lattes.cnpq.br/7396818382676736; Soares, Anderson da Silva; http://lattes.cnpq.br/1096941114079527
The presence of dynamic objects in a scene can significantly impair the performance of visual odometry methods. Even with the use of robust methods, it is not always possible to avoid outliers and interferences in the estimation of the camera’s movement. This type of object introduces characteristic points whose movement does not align with the actual movement performed by the camera. To filter these objects, this work presents a neural network architecture that combines RGB images and optical flow to segment regions that exhibit moving objects, even while the camera itself moves. To enable the training of the network, a methodology for quick annotation of object detection datasets is presented to add semantic masks of moving objects to 98,491 images of an urban navigation dataset. The proposed neural network was trained and evaluated with these data and proved adequate for use as a dynamic object filter in visual odometry tasks. To evaluate the proposed model, comparisons of visual odometry algorithms with and without the use of filtering are presented. Based on the results obtained in this work, the identification and filtering of dynamic objects in an image emerges as a fundamental step in the task of visual odometry, being essential for applications involving the presence of dynamic objects.
Mineração de argumentos em documentos jurídicos em Português
(Universidade Federal de Goiás, 2024-12-02) Evangelista, Euripedes Balsanulfo; Silva, Nádia Félix Felipe da; http://lattes.cnpq.br/7864834001694765; Silva, Nádia Félix Felipe da; Pereira, Fabíola Souza Fernande; Cordeiro, Douglas Farias
This work presents an argument mining approach applied to Brazilian labor court documents. Although the mining of arguments in legal documents has been a subject of study for over a decade, only one work has been found that specifically applies this study to Brazilian Portuguese in the legal domain. In this dissertation, we thoroughly explore all the necessary steps to achieve the objective of the argument mining task. Thus, our approach consists of use a Transformers-based Language Model trained on a specific domain corpus of Brazilian labor justice and we report an F1-score of 88.86% on the classification task. The proposal outperformed BERTimbau by 1.88% and Deberta by 3.39%.

Navegar

Submissões Recentes