Programa de Pós-Graduação em Engenharia Elétrica e de Computação
Permanent URI for this communityhttps://repositorio.ufrn.br/handle/123456789/11949
Browse
14 results
Search Results
Master Thesis Detecção de processos erosivos com aprendizado de máquina e a aplicação da Equação Universal de Perda de Solo (USLE)(Universidade Federal do Rio Grande do Norte, 2025-08-18) Marinho, Wesley José dos Santos; Alsina, Pablo Javier; http://lattes.cnpq.br/3653597363789712; http://lattes.cnpq.br/9223986328697943; Martins, Allan de Medeiros; https://orcid.org/0000-0002-9486-4509; http://lattes.cnpq.br/4402694969508077; Matos, Maria de Fátima Alves de; https://orcid.org/0000-0002-2864-2027; http://lattes.cnpq.br/7230788237148341; Laura, Tânia Luna; http://lattes.cnpq.br/8142774545918274The research in question investigates the detection of erosion processes through machine learning and the application of the Universal Soil Loss Equation (USLE). The primary issue addressed by the study is the identification and prevention of soil erosion, a significant environmental problem. Key objectives include implementing techniques to early detect erosion processes near power transmission lines, using the USLE as an additional validation factor. The motivation behind the study is to mitigate damage to power distribution networks caused by erosion and to seek effective methods for monitoring and preventing erosion. The methodology involves using machine learning algorithms, specifically Convolutional Neural Networks (CNNs), to analyze satellite images and identify areas prone to erosion. Additionally, the USLE is applied as a tool for calculating soil loss, aiding in the assessment of the likelihood of erosion in specific locations. The main contributions of the study include integrating machine learning technologies in the detection of erosion processes and validating these techniques with the USLE, demonstrating its effectiveness in this context. The results indicate the feasibility and accuracy of using machine learning for detecting erosion processes, as well as the importance of the USLE as an evaluation method. The study’s conclusions highlight the relevance of the practical application of these techniques for the preservation of power transmission lines and more efficient monitoring of their surroundings. Future research directions include expanding the study to other regions and improving the detection methodology.Doctoral Thesis Desenvolvimento de ferramenta computacional para biossensores baseados em ressonância de plasmon de superfície utilizando métodos híbridos e aprendizado de máquina(Universidade Federal do Rio Grande do Norte, 2025-06-26) Villarim, Mariana Rodrigues; Belfort, Diomadson Rodrigues; Ando Júnior, Oswaldo Hideo; https://orcid.org/0000-0002-6951-0063; http://lattes.cnpq.br/3515465412634126; https://orcid.org/0000-0001-5722-7394; http://lattes.cnpq.br/2241184480091242; http://lattes.cnpq.br/1234708675762453; Maciel, Joylan Nunes; https://orcid.org/0000-0003-0725-6917; http://lattes.cnpq.br/1177414528561833; Cavallari, Marco Roberto; https://orcid.org/0000-0002-1345-754X; http://lattes.cnpq.br/9041429608835546; Carmo, João Paulo Pereira do; https://orcid.org/0000-0001-7955-7503; http://lattes.cnpq.br/5589969124054528; Catunda, Sebastian Yuri Cavalcanti; http://lattes.cnpq.br/0873496251879638Doctoral Thesis Detecção e localização de crises epilépticas em sinais de EEG utilizando aprendizado de máquina e inteligência artificial explicável(Universidade Federal do Rio Grande do Norte, 2025-05-30) Vieira, Jusciaane Chacon; Oliveira, Luiz Affonso Henderson Guedes de; https://orcid.org/0000-0003-2690-1563; http://lattes.cnpq.br/7987212907837941; Teixeira, César; Gendriz, Ignacio Sanchez; http://lattes.cnpq.br/6338710569530857; Silva, Ivanovitch Medeiros Dantas da; https://orcid.org/0000-0002-0116-6489; http://lattes.cnpq.br/3608440944832201; Fernandes, Marcelo Augusto Costa; https://orcid.org/0000-0001-7536-2506; http://lattes.cnpq.br/3475337353676349Epilepsy is a neurological condition that affects millions of people worldwide and significantly impacts individuals’ quality of life. Epileptic seizures, which are transient events, vary in manifestations, including motor, sensory, and consciousness alterations, and represent a challenge both in diagnosis and management. This work proposes an innovative methodology for the detection and localization of epileptic seizures, using machine learning and explainable artificial intelligence approaches to optimize the identification process. The proposal is divided into two approaches: a generalist one, which uses simplified models with explainable feature and channel reduction, and a specific one, which personalizes detection for each patient based on a single electroencephalogram (EEG) channel. In the generalist approach, feature and channel reduction was explored, achieving performance above 0.95 in accuracy, precision, recall, and f1-score metrics using only six features and five channels. The use of the SHAP method allowed for the interpretation of each feature’s contribution by channel, reinforcing the explainability of the models and aligning the results with the visual knowledge of EEG specialists. The methodology proved effective, ensuring good generalization to the dataset with different patients. In the specific approach, a bipolar montage with adjacent electrodes was introduced, creating 58 channel combinations, and a centrality measure with topographic visualization was applied to identify the most relevant channels for each patient. Additionally, a 3-second temporal filter was developed to reduce the model’s false positives. A personalized supervised learning model, extreme gradient boosting, was trained for each patient using only one EEG channel. The results for the three investigated patients were remarkable, with accuracy scores of 1; 0.99; and 0.88, highlighting the feasibility of seizure detection using a single channel, considering the topographic location of seizures in each individual. This study highlights the potential to substantially reduce the number of features and channels required for epileptic seizure detection without compromising accuracy, and reinforces the importance of personalized models for each patient. Furthermore, the research contributes to the advancement of wearable devices for continuous epilepsy monitoring, facilitating the detection and localization of patients with epilepsy.Master Thesis Gerência de largura de banda do reúso fracionário de frequência em cenários dinâmicos com Hotspots utilizando aprendizado por reforço(Universidade Federal do Rio Grande do Norte, 2025-07-04) Silva, Eriberto de Souto; Sousa Júnior, Vicente Angelo de; https://orcid.org/0000-0003-2859-6136; http://lattes.cnpq.br/6358312955522220; http://lattes.cnpq.br/9594814897805733; Silva Neto, Valdemir Praxedes da; https://orcid.org/0000-0003-3867-3297; http://lattes.cnpq.br/4160231554601828; Melo, Yuri Victor Lima de; https://orcid.org/0000-0003-3026-7059; http://lattes.cnpq.br/3613517930531317The present work approaches the use of Inter-Cell Interference Coordination (ICIC) techniques, based on techniques Fractional Frequency Reuse (FFR) aimed at mitigating one of the main challenges faced when designing mobile networks: co-channel interference (CCI). ICIC is one of the primary factors contributing to the degradation of mobile communication system performance, especially in dynamic scenarios with randomly distributed user clusters, known as hotspots. Initially, the problem is characterized by the exploration of the chosen ICIC technique without automated parameterization, as well as the system’s performance in the aforementioned scenario. Then, considering the dynamic nature of the environment, the proposed solution involves the use of machine learning techniques—more specifically, the Multi-Armed Bandit (MAB)—customized for optimizing bandwidth management in ICIC techniques for 3GPP systems. The objective of the proposal is to adapt the spatial allocation of bandwidth, using system load variation and hotspot dynamics as decision-making parameters. Proof-of-concept experiments were conducted using the ns-3 network simulator. The results demonstrate that the MAB-based approach proposed in this dissertation outperforms static bandwidth distribution configurations in terms of throughput, even under varying system load conditions, showing significant gains.Master Thesis Otimização fim-a-fim de sistemas MIMO multiusuário usando autoencoders com estimação de canal bidirecional(Universidade Federal do Rio Grande do Norte, 2024-03-21) Velloso, Eduardo Nunes; Silveira, Luiz Felipe de Queiroz; https://orcid.org/0000-0002-7146-4916; http://lattes.cnpq.br/4139452169580807; https://orcid.org/0000-0002-9668-5547; http://lattes.cnpq.br/7673330596328097; Martins, Allan de Medeiros; https://orcid.org/0000-0002-9486-4509; http://lattes.cnpq.br/4402694969508077; Alencar, Marcelo Sampaio de; https://orcid.org/0000-0002-2849-1644; http://lattes.cnpq.br/0946722048975388; Lopes., Waslon Terllizzie Araújo; https://orcid.org/0000-0003-2486-9950; http://lattes.cnpq.br/5041048659000127The spectral efficiency gains introduced by multiuser MIMO systems render them relevant schemes for current and upcoming generations of mobile communication networks. Due to the intrinsic complexity of the mathematical models of these systems under realistic conditions and the interdependence between the processing steps of the transmitters and receivers, machine learning is an option that allows the complete system to be designed by training a noisy autoencoder. This paper proposes a neural network architecture for end-to-end optimization of a multiuser MIMO system. The performance of the system, measured in terms of symbol error rate, was compared to an M-PSK baseline with zero-forcing equalization and least-squares channel estimation. Simulations were performed using a Rayleigh fading channel model and the realistic 3GPP TR 38.901 model. A bidirectional channel estimator, based on the interpolation of sparse pilots, is proposed, reducing the control signaling to less than 3% in exchange for a fixed 10 ms delay. The results show that signicant gains can be achieved by applying the proposed model, but these vary with respect to the estimation errors during the pilot transmission timesDoctoral Thesis Uma metodologia orientada a dados não estruturados de produção científica para avaliação temporal de grupos de pesquisa(Universidade Federal do Rio Grande do Norte, 2023-08-29) Santos, Breno Santana; Silva, Ivanovitch Medeiros Dantas da; https://orcid.org/0000-0002-0116-6489; http://lattes.cnpq.br/3608440944832201; https://orcid.org/0000-0002-8790-2546; http://lattes.cnpq.br/1477295656421537; Sampaio, Ricardo Barros; Villanueva, Juan Moisés Mauricio; Oliveira, Luiz Affonso Henderson Guedes de; https://orcid.org/0000-0003-2690-1563; http://lattes.cnpq.br/7987212907837941; Fernandes, Marcelo Augusto CostaFunding agencies and research institutions often use quantitative methods and scientometric techniques to evaluate scientific groups. Generally, these evaluations are based on a single type of metric, be it count-based (such as the h-index) or those derived from Complex Network Analysis. However, the use of multiple measurement approaches and the proper exploration of the temporal dimension of academic production are still recurring issues. Particularly, an underexplored approach consists of combining these indicators with Machine Learning and Graph Embeddings techniques, which could enhance the evaluation process of research groups. In this context, this study proposes a Graph Data Science-oriented methodology for analyzing scientific teams over time. Through a case study involving Graduate Programs in Engineering IV, the results suggest the feasibility and suitability of the proposed method for quantitatively assessing research groups. Furthermore, the methodology was able to detect the collaboration patterns belonging to the groups evaluated, and identify trends and peculiarities associated with the programs investigated. Therefore, the proposed approach has the potential to provide strategic and proactive insights for scientific teams, contributing to a better understanding of their dynamics and shortcomings.Doctoral Thesis Machine Learning Aplicado a Triagem de Osteoporose: modelo baseado na atenuação de ondas eletromagnéticas(Universidade Federal do Rio Grande do Norte, 2023-09-21) Albuquerque, Gabriela de Araújo; Valentim, Ricardo Alexsandro de Medeiros; http://lattes.cnpq.br/3181772060208133; https://orcid.org/0000-0003-3983-796X; http://lattes.cnpq.br/2881597530431714; Morais, Antonio Higor Freire de; Campos, Antonio Luiz Pereira de Siqueira; http://lattes.cnpq.br/1982228057731254; Gusmão, Cristine Martins Gomes de; Machado, Guilherme Medeiros; Santos, João Paulo Queiroz dos; Petrella, Lorena ItatiOsteoporosis is a silent and still underdiagnosed condition, with a mortality rate higher than several types of cancer, especially when patients suffer fractures. The gold standard equipment for the diagnosis, Dual-energy X-ray absorptiometry (DXA, or DEXA), which uses ionizing radiation and is expensive, is scarce in countries considered middle or low-income, thus hindering timely access to diagnosis. In this context, a portable device, Osseus, was developed for the screening of patients who need the densitometry exam, i.e., to qualify the referrals of exams to the DEXA equipment. The thesis aimed to validate the Osseus device using machine learning techniques. For this, the planning and data collection of 505 patients who underwent the exam at DEXA and Osseus. 21.8% of them were healthy and 78.2% were diseased (they had low bone mineral density or osteoporosis). The dataset was separated into 80% for training and validation (5-fold cross-validation) and 20% for testing. The performance obtained in the test base with the best model (Random Forest) corresponded to sensitivity=0.853, specificity=0.871, and F1(harmonic average of precision and sensitivity rate)=0.859. The results showed that the most relevant variables to indicate the individual health status were age, body mass index (BMI), and the attenuation of the signal emitted and detected by the Osseus device.When compared to the results of DEXA scans, the model has proven to be effective and consistent in screening individuals with osteoporosis and facilitating early diagnosis of the disease, which consequently entails improved productivity and reduced costs for surgery, treatment, and hospitalization. Thus, by qualifying the referral of patients from primary care to the specialized network, Osseus can impact the reduction of waiting lines of the Brazilian National Health System.Master Thesis Técnicas de aprendizado de máquina para a predição de eventos extremos de sobreirradiância em Natal-RN(Universidade Federal do Rio Grande do Norte, 2023-09-22) Fernandes, Arthur Diniz Flor Torquato; Dória Neto, Adrião Duarte; https://orcid.org/0000-0002-5445-7327; http://lattes.cnpq.br/1987295209521433; http://lattes.cnpq.br/3049525197244902; Martins, Daniel Lopes; http://lattes.cnpq.br/2947003499946183; Gendriz, Ignacio Sanchez; Emiliavaca, Samira de Azevedo SantosThe current dissertation is centered on the forecasting of Overirradiance within intervals of up to five minutes, achieved through the utilization of machine learning methodologies. Overirradiance, a phenomenon characterized by solar irradiance surpassing anticipated values under clear-sky conditions at the Earth’s surface, has generated scholarly interest within the sphere of solar energy research and its implications for photovoltaic power generation systems. To date, no dedicated studies investigating the application of Machine Learning techniques for forecasting this phenomenon have been identified. In pursuit of this aim, the performance of four distinct machine learning algorithms has been meticulously examined: Random Forest, Support Vector Machines (SVM), Multilayer Perceptron (MLP), and Long Short-Term Memory (LSTM) neural networks. The present study endeavors to bridge a lacuna in research by scrutinizing the feasibility and efficacy of these algorithms in predicting Overirradiance events, thereby augmenting the comprehension and pragmatic application of this phenomenon within solar energy systems.Master Thesis Classificando o número de pessoas em um ambiente via sinal RF: uma abordagem aplicando aprendizado de máquina(Universidade Federal do Rio Grande do Norte, 2021-08-26) Campos, Millena Michely de Medeiros; Sousa Júnior, Vicente Ângelo de; http://lattes.cnpq.br/6358312955522220; http://lattes.cnpq.br/2513373459813068; Lima, Eduardo Rodrigues de; Silva, Leonardo Henrique Gonsioroski Furtado da; Silveira, Luiz Felipe de Queiroz; http://lattes.cnpq.br/4139452169580807; Medeiros, Álvaro Augusto Machado deThis work proposes a technique for counting people in an already populated environment. Initially, a survey of the technologies and solutions designed for this purpose is carried out. As a proof of concept, a counting solution is analyzed for a small number of people, at two different frequencies, applying machine learning to the descriptive statistics of an RF signal. Finally, classification results are presented for a more realistic scenario, with up to 350 people in the environment, using a software-defined radio measurement system for data collection. The results demonstrate significant accuracy in counting the number of people per classification into groups of individuals.Doctoral Thesis Novo método de síntese de FSS multibanda baseado em aprendizado de máquina para sistemas de comunicação sem fio(Universidade Federal do Rio Grande do Norte, 2021-07-09) Fontoura, Leidiane Carolina Martins de Moura; D'Assunção, Adaildo Gomes; http://lattes.cnpq.br/4159638862269940; http://lattes.cnpq.br/6260601474854896; D'Assunção Júnior, Adaildo Gomes; http://lattes.cnpq.br/7359899329008024; Gomes Neto, Alfredo; http://lattes.cnpq.br/1403715441701958; Peixeiro, Custódio José Oliveira; Lins, Hertz Wilton de Castro; http://lattes.cnpq.br/7712686175574736; Mendonça, Laercio Martins de; http://lattes.cnpq.br/1853488415531363; Silva Neto, Valdemir Praxedes da; http://lattes.cnpq.br/4160231554601828The present work is a study on the application of supervised machine learning with the decision tree algorithm in the synthesis of frequency selective surfaces, or simply FSS. For this, the sunflower (Helianthus annuus) was used as a base element, being an original and simplified geometry, with frequency response characteristics similar to those of fractal structures. The thesis work is thus divided in two parts: the proposed element characterization and synthesis of the multiband FSS. Initially, the evolution of geometry and design equations are presented. The intermediate and the proposed structures are numerically characterized using the commercial software Ansoft Designer, manufactured, and experimentally characterized, with good agreement between the simulated and measured results. In the second step, the sunflower geometry is partially modified to define parameterization variables. The Ansoft Designer numerically characterizes the value of each variable of the new geometry, and it generates the frequency responses without repetition. The decision tree algorithm performs the dataset classification and evaluation, and the random forest algorithm validates and confirms the results. This process and the synthesis of the FSS using the decision tree algorithm occur in less than 10 seconds, with accuracy greater than 90%, meeting the desirable criteria, under two different scenarios. The decision tree algorithm learns simple decision rules inferred from training data, with simple and easy to implement calculations, written in the Python language. The accuracy is a parameter used to measure the quality of prediction in training and validation of the algorithm. Based on these scenarios, two FSS are manufactured and experimentally characterized, obtaining results with good agreement. The designed and fabricated FSS structures have closely spaced operation bands. Thus, it is observed that the agility and precision of this classification algorithm make the synthesis of the structures particularly interesting. Intuitive implementation, simplicity in training and validation, and an efficient data analysis model are highlighted.