CT - TCC - Engenharia de Telecomunicações

Permanent URI for this collectionhttps://repositorio.ufrn.br/handle/123456789/33192

Browse

Now showing 1 - 20 of 61

API-Guard: API RESTful para detecção de ataques DoS/DDoS em redes 5G e IoT
(Universidade Federal do Rio Grande do Norte, 2026-06-19) Olegário, Wendell de Araújo; Lins, Hertz Wilton de Castro; Silveira Junior, Luiz Gonzaga de Queiroz; Rodrigues, Marcio Eduardo da Costa; Silva Neto, Valdemir Praxedes da
OptIA: Um sistema fim a fim para estimação em tempo real da qualidade de transmissão em sistemas ópticos coerentes empregando aprendizado de máquina
(Universidade Federal do Rio Grande do Norte, 2025-11-24) Pinto, Leonardo Saads; Cruz Júnior, José Hélio da; 0000-0002-1339-5895; 0009-0003-7188-7542; Silveira Júnior, Luiz Gonzaga de Queiroz; Sousa Júnior, Vicente Ângelo de
Efficient data refinement and feature selection for SYN and UDP Flood DDoS detection in 5G environments
(Universidade Federal do Rio Grande do Norte, 2025-11-19) Martins, Francisco Marcelo Melo; Silveira Junior, Luiz Gonzaga de Queiroz; Lins, Hertz Wilton de Castro; 0009-0001-8314-0230; Rodrigues, Márcio Eduardo da Costa; Cruz Júnior, José Hélio da
This paper introduces a robust and reproducible methodology for analyzing and refining large-scale DDoS datasets, specifically targeting SYN Flood and UDP Flood attacks—two of the most significant threats in 5G network environments. Utilizing CICDDOS2019 [?] as a comprehensive and challenging case study, we established a data processing pipeline with TimescaleDB to efficiently filter and balance the dataset. Feature importance was rigorously evaluated using a Random Forest model. Our results highlight the most predictive features, enabling a streamlined feature extraction workflow that lays a solid foundation for the advancement of future DDoS detection models.
Automatic Classification of Interferences in Communication Links Between Satellites and Ground Stations Using Convolutional Neural Networks
(Universidade Federal do Rio Grande do Norte, 2025-11-19) Lira, Pedro Henrique Antero; Silveira Júnior, Luiz Gonzaga de Queiroz; Cruz Júnior, José Hélio da; https://orcid.org/0009-0008-2852-6203; http://lattes.cnpq.br/5420564784846698; Lins, Hertz Wilton de Castro; Ramos, Vítor Saraiva; Taveiros, Filipe Emanuel Vieira
This work addresses a very common challenge in the use of the radio frequency (RF) spectrum: congestion, which affects the reliability of satellite communications due to radio frequency interference (RFI). To identify this issue, this work proposes an automatic classification system for continuous-wave and pulsed-wave interferences based on Deep Learning, enabling accurate and scalable RFI classification and real-time spectrum monitoring. The innovation introduced by this system begins with the development of a synthetic dataset composed of spectrograms divided into three categories: clean channel, continuous interference, and pulsed interference. It then proceeds with the training of a Convolutional Neural Network (CNN), followed by an exhaustive hyperparameter tuning process to prevent overfitting. Performance results obtained with the proposed classification system show an accuracy reaching 99% on the test set. Therefore, the proposed method is robust and effective, providing a reliable solution for automatic spectrum surveillance in mission-critical scenarios.
Contribuições para o ensino de técnicas de equalização linear forçada a zero e de mínimo erro médio quadrático por meio de simulação computacional
(Universidade Federal do Rio Grande do Norte, 2025-07-09) Silva Filho , José Tadeu Santos; Rodrigues, Marcio Eduardo da Costa; Silveira Júnior, Luiz Gonzaga de Queiroz
Implementação de redes de videomonitoramento em um complexo eólico no Rio Grande do Norte
(Universidade Federal do Rio Grande do Norte, 2025-07-01) Fagundes, Felipe Gabriel Ferreira; Pinheiro, Fred Sizenando Rossiter; Silva, Gutembergue Soares da
Estudo de caso para desenvolvimento de uma rede de fibra óptica FTTH utilizando tecnologia XGS-PON e cabeamento preconectorizado
(Universidade Federal do Rio Grande do Norte, 2025-06-27) Urbano, Rodrigo Ribeiro; Silva, Gutembergue Soares da; Pinheiro, Fred Sizenando Rossiter; Martins, Ronaldo de Andrade
Nowadays, the Fiber To The Home (FTTH) network is already implemented in a large part of Brazil. With the growing demand for constant high-speed connectivity, greater bandwidth, and reliable connections, it is necessary to improve the network infrastructure to deliver high-quality service and support an increasing number of connected users. This work presents an FTTH deployment project for the city of Macaíba, located in the metropolitan region of Natal, in the state of Rio Grande do Norte. A Passive Optical Network (PON) will be used, specifically the 10-Gigabit-capable Symmetric Passive Optical Network (XGS-PON) technology, which is an enhancement of the Gigabit Passive Optical Network (GPON), offering higher bandwidth capacity. The network will also feature a fully pre-connectorized infrastructure, from the Central Office to the last mile.
Prototipagem e análise de desempenho do nb-iot em um cenário de criação de gado semi-intensiva
(Universidade Federal do Rio Grande do Norte, 2025-06-30) Muniz,Marilia Costa; Sousa Júnior, Vicente Angelo de; http://lattes.cnpq.br/6358312955522220; Pinheiro, Fred Sizenando Rossiter; Silva, Gutembergue Soares da
Implementando service mesh no contexto do núcleo 5G
(Universidade Federal do Rio Grande do Norte, 2024-12-20) Santos, Fellipe Augusto dos; Silva, Gutembergue Soares da; Pinheiro, Fred Sizenando Rossiter; 0000-0002-4442-8784; 0000-0001-5951-4805; http://lattes.cnpq.br/1214925346969928
5G technology represents a significant advance in the evolution of mobile networks, with the introduction of the new service-based architecture (SBA). This paper explores the fundamental elements of the 5G core, highlighting the differences in relation to 4G and describing its main components. The complexity of the 5G architecture presents several operational challenges. This study investigates these complexities and demonstrates how service mesh technology offers a robust solution, facilitating communication between services, increasing security and providing observability. The transition from virtual machines (VMs) to containers is analyzed, with an emphasis on the role of cloud-native functions and the importance of Kubernetes in the orchestration of these infrastructures. The practical implementation of a service mesh using Istio in conjunction with open5GS demonstrates the benefits of this technology, including the optimization of network administration and the scalable and secure delivery of services in the dynamic environment of 5G. The results obtained indicate a more efficient and manageable network, with significant improvements in security and resilience, also including the analysis of the negative aspects of this type of implementation.
Relatório de Impacto à Proteção de Dados Pessoais (RIPD): instrumento de governança e controle no âmbito da LGPD
(Universidade Federal do Rio Grande do Norte, 2025-01-13) Emmanuelly Julião da Silva; Silva, Claudio Rodrigues Muniz da; Silva, Gutemberg Soares da; Duarte Júnior, José Garibaldi; Silva Neto, Valdemir Praxedes da
This study investigates the effectiveness of the Data Protection Impact Statement (DPIR) as a strategic tool in protecting the rights of personal data subjects, especially in the context of the General Data Protection Law (LGPD) in Brazil. The research seeks to understand how the DPIR contributes to the prevention and mitigation of risks associated with the misuse of data, identifying challenges, gaps and good practices in its implementation. To this end, a descriptive methodology is adopted, with bibliographic analysis, practical case studies and evaluation of criteria such as Privacy by Design (PbD), which integrates data protection from the design of systems and processes. The results aim to offer proposals for improvements for the effective application of the DPIR, reinforcing legal compliance and information security, in addition to contributing to the strengthening of data governance and the protection of fundamental rights.
Machine Learning Operations, conceitos e ferramentas
(Universidade Federal do Rio Grande do Norte, 2025-01-10) Lopes, Vítor Gabriel Lemos; Lins, Hertz Wilton de Castro; D’Assunção, Adaildo Gomes; Vasconcelos, Cristhianne Linhares de
The increasing adoption of Machine Learning (ML) in various fields has driven the need for efficient solutions to manage the lifecycle of models in production. Machine Learning Operations (MLOps) emerges as a response to this demand, combining software development practices (DevOps) with the specific characteristics of ML. MLOps aims to automate, integrate, and monitor the stages of model development, deployment, and maintenance, from data collection and preparation to continuous monitoring in production. This approach seeks to optimize model performance, ensure the reproducibility of experiments, and facilitate the scalability of ML solutions, allowing organizations to obtain maximum value from their investments in artificial intelligence. This study focuses on investigating the MLOps ecosystem, seeking to understand its fundamental concepts and analyze the main tools used in the construction and management of ML pipelines in production. The research, of a descriptive nature, combines a literature review with a comparative analysis of tools, addressing the origin and evolution of MLOps, its essential principles, and the challenges of its implementation. The study investigates the application of MLOps in sectors such as Industry 4.0, healthcare, and smart cities, and details the concept of MLOps pipelines, from data ingestion to continuous model monitoring, highlighting the importance of CI/CD practices. The research analyzes the main tools available on the market, describing their functionalities, architectures, use cases, advantages, and disadvantages, with the objective of providing a comprehensive view of the MLOps ecosystem and an overview of the available tools.
ExtrAI-PDF: Sistema de Extração Inteligente e Automática de Dados
(Universidade Federal do Rio Grande do Norte, 2024-11-27) Santos, Douglas Fernandes dos; Lins, Hertz Wilton de Castro; 0000-0003-1138-4276; http://lattes.cnpq.br/7712686175574736; 0009-0006-2449-4705; http://lattes.cnpq.br/1740933882674497; Vasconcelos, Cristhianne de Fatima Linhares de; http://lattes.cnpq.br/3140725798737102; Nagem, Danilo Alves Pinto; http://lattes.cnpq.br/5934458385325202
The project integrates GPT (OpenAI) artificial intelligence models to streamline infor- mation extraction from documents. The methodology involves developing a web system capable of performing this extraction quickly and reliably from multiple PDF files simul- taneously. The case studies focus on extracting information from articles about the new mobile 6G technology standard and neonatal skin lesions. In the latter case, the extracted information will serve as guidelines for training a machine learning model.
Estratégias de segurança interna em redes corporativas: mitigação de ameaças e proteção contra ataques em switches gerenciáveis
(Universidade Federal do Rio Grande do Norte, 2024-08-16) Torres, Sérgio Matheus Lima; Vasconcelos, Cristhianne de Fátima Linhares de
Computer network security is essential for protecting information and services. Managed switches, in particular, are crucial for ensuring security but are vulnerable to various types of attacks. Although many think that threats come from outside the network, it is important to recognize that they can also arise internally. These threats can range from innocent actions, such as an employee connecting an Ethernet switch to the corporate network to gain more ports, to malicious attacks perpetrated by dissatisfied individuals. This work presents techniques to mitigate threats to switches and reinforce network security. Measures for port protection, prevention of VLAN attacks, protection against DHCP and ARP spoofing, and safeguarding against STP protocol exploits are addressed. Through configurations on the switches, features such as Port Security, DHCP Snooping, Dynamic ARP Inspection, and Root Guard can be implemented. The work demonstrates the practical application of these techniques in simulations using Cisco Packet Tracer software. The analyzed measures significantly mitigate security risks in environments with managed switches, contributing to more resilient corporate networks.
Desenvolvimento de um Ambiente de Telefonia IP utilizando Asterisk com TLS
(Universidade Federal do Rio Grande do Norte, 2024-08-16) Santos, João Paulo Nascimento dos; Silva, Cláudio Rodrigues Muniz da; http://lattes.cnpq.br/6968371254983355; https://lattes.cnpq.br/6717959974013279; Mendonça, Laércio Martins de; http://lattes.cnpq.br/1853488415531363; Paiva, Fábio Augusto Procópio de; http://lattes.cnpq.br/2855980539505619
IP telephony (ToIP) has established itself as an efficient and cost-effective solution for voice communication. However, despite its advantages, the security of VoIP communications has become a growing concern, especially in the Brazilian context, where unauthorized interception of communications is a common practice that jeopardizes the privacy of personal and corporate information. This article aims to create an encrypted environment with TLS in a laboratory setting, serving as a proof of concept to validate the results obtained in various scenarios involving interception attacks. The methodology adopted is based on the process of constructing an encrypted IP Telephony environment, using Asterisk as the PBX and TLS for encrypting VoIP/ToIP signaling. The results obtained are promising and demonstrate that it is possible to protect, with relative simplicity, the video and voice communications used in ToIP by employing the proposed encryption technique.
Monitoramento de uma indústria com dispositivos IoT: estudo de caso em uma indústria farmacêutica
(Universidade Federal do Rio Grande do Norte, 2024-08-14) Fontenelle, Maria Elisa Monteiro; Florencio, Heitor Medeiros; Lopes Neto, Walter; Rocha Neto, Aluízio Ferreira da
Análise do desempenho das operadoras de SMP na Zona Sul da Cidade de Natal
(Universidade Federal do Rio Grande do Norte, 2023-12-08) Costa, Jordânia Saldanha; Batista, Yuri Max Vieira; http://lattes.cnpq.br/6732737842740606; Mendonça, Laércio Martins de; D’Assunção, Adaildo Gomes; Pinheiro, Fred Sizenando Rossiter
Análise comparativa da implantação de um modelo de classificação com aprendizado de máquina em diferentes níveis de MLOps
(Universidade Federal do Rio Grande do Norte, 2023-12-08) Oliveira, Joao Paulo Marques; Lins, Hertz Wilton de Castro; https://orcid.org/0000-0003-1138-4276; http://lattes.cnpq.br/7712686175574736; Júnior, Luiz Gonzaga de Queiroz Silveira; https://orcid.org/0000-0001-6167-1893; http://lattes.cnpq.br/5714183212530259; Fernandes, Felipe Ricardo dos Santos; https://orcid.org/0000-0003-0805-1796; http://lattes.cnpq.br/9594127311197032
The integration of machine learning (ML) application implementations with system operations is notably more complex compared to other applications in the field of Software Engineering. This is due to ML systems facing the same challenges as common software systems, compounded by the difficulties inherent in ML. Maintaining these systems is also a complex task due to the unstable nature of ML models when confronted with variations in data patterns.. This work conducts a comparative analysis between different levels of MLOps to understand the nuances of this integration. Adopting an experimental comparative methodology, we conducted a literature review on MLOps and set up a working environment on Amazon Web Services (AWS). We implemented a classification system at three different MLOps levels, assessing efficiency, quality, and ease of maintenance. The results reveal that tools like MLFlow for metric tracking and logging, along with solutions like Evidently for data monitoring in production, play crucial roles in creating a robust and reliable ML ecosystem. This study provides valuable insights into the differences between MLOps levels, emphasizing the importance of these methodologies in the broader context of integrating machine learning systems.
Desenvolvimento de um sistema de segurança residencial integrado à IoT utilizando o simulador cisco packet tracer
(Universidade Federal do Rio Grande do Norte, 2023-12-07) Santos, Dircia Maria de Oliveira dos; Vasconcelos, Cristhianne de Fatima Linhares de; Lins, Hertz Wilton de Castro; Batista, Yuri Max Vieira
The development of science and technology is currently advancing rapidly, which can make people's lives easier and more comfortable. However, security remains a significant challenge in many households. Although most homes have manual locking systems on doors and windows, these methods do not guarantee effective security against intrusions. In this context, this work aims to develop a home security system integrated with IoT (Internet of Things), which enhances the security of doors and windows through smart devices designed to be accessed by mobile devices via an Internet network. Using the Cisco Packet Tracer simulator, the work will explore the concept of IoT applied to home automation. The developed home security system will enable users to receive notifications on their mobile devices when someone enters the house through a door or window. The system will be activated when users leave the house and deactivated when they return. Additionally, the system will feature intelligent sensors that detect suspicious movements inside the house. Both the alarm and cameras will be activated automatically to notify the user and alert them about motion detections, enabling a quick and appropriate response to ensure residential security.
Filtro rejeita-faixa para uso em decodificadores de sinais de tv aberta na banda C para mitigar interferências de sinais do 5G
(Universidade Federal do Rio Grande do Norte, 2023-12-06) Silva, Túlio José Costa da; Campos, Antonio Luiz Pereira de Siqueira; http://lattes.cnpq.br/1982228057731254; https://lattes.cnpq.br/2864194116348881; Silva Neto, Valdemir Praxedes da; http://lattes.cnpq.br/4160231554601828; Rodrigues, Marcio Eduardo da Costa; http://lattes.cnpq.br/2116993138825543
Since the 5G spectrums were auctioned in Brazil for the use of mobile telephony, ANATEL has been looking for ways to resolve the interference that will affect the transmission of signals transmitted in band C. This problem is caused due to one of the spectrums that will be used for telephony mobile, in the frequency range of 3.3 to 3.7 GHz, which will cause interference in the initial frequencies used for downlink in open TV signals, which operates in the C band, in the frequency range of 3.4 to 4.2 GHz With this situation in question, a possible solution is to reject the 5G operating band, in band C, avoiding LNB saturation. Therefore, a narrowband band-reject filter is a possible solution. This work aimed to develop two microstrip band-reject filters using a Defected Ground Structure (DGS) configuration based on Matrioska geometry, with the function of mitigating 5G signal interference. The filters were designed to have a rejection band in the frequency range of 3.3 to 3.7 GHz, which is the operating band of fifth-generation mobile phone systems. The product of this work was developed through studies on band-reject filters, where we analyzed the S21 parameter using LiteVNA. In addition, parametric, analytical and computational analyzes were carried out using software, such as HFSS and Matlab, for the design and creation of prototypes, verification of operation and efficiency. The filters, in addition to solving the standard problem, could also be the subject of future research studies. Furthermore, they can be used in other systems in which their functionality may be suitable.
Desenvolvimento e avaliação de material didático com simulações no Packet Tracer para o ensino de redes de computadores
(Universidade Federal do Rio Grande do Norte, 2023-12-07) Campos, Helton Igor Souza; Vasconcelos, Cristhianne de Fátima Linhares de; Lins, Hertz Wilton de Castro; Batista, Yuri Max Vieira

SIGAA

Browse

collection.page.browse.recent.head