EMC - Trabalhos de Conclusão de Curso
URI Permanente para esta coleção
Navegar
Navegando EMC - Trabalhos de Conclusão de Curso por curso "Engenharia de Computação (RMG)"
Agora exibindo 1 - 11 de 11
Resultados por página
Opções de Ordenação
Item Adaptação e implementação da framework NIST em redes domésticas(Universidade Federal de Goiás, 2024-01-31) Soares, Luan Weba; Pinheiro Júnior, Carlos Galvão; Pinheiro Júnior, Carlos Galvão; Oliveira, Marco Antonio Assfalk de; Alves, João Miguel EstevãoThis study addresses the implementation and feasibility of the National Institute of Standards and Technology Cybersecurity Framework (NIST CSF). We explore the challenges brought by the rise of remote work in residential environments, both of which contribute to a more complex security landscape. Using the Raspberry Pi equipped with security tools such as SIEM and EDR, and vulnerability scanning techniques, the study proposes a comprehensive set of security practices based on the NIST CSF. It aims to provide a clear, low-cost roadmap for effectively modeling cybersecurity measures, protecting data integrity and privacy on home networks. Finally, we arrived at the result that the framework is adaptable, but requires a lot of intervention from specialists, to the point that support by them rather than the end user is more appropriate.Item Alocação de recursos em redes sem fio utilizando algoritmos baseados em aprendizagem de máquina(Universidade Federal de Goiás, 2024-02-01) Lopes, Adriano Ferreira; Silva, Jean Lucas Barbosa; Vieira, Flávio Henrique Teles; Vieira, Flávio Henrique Teles; Cardoso, Alisson Assis; Carneiro, Daniel Porto QueirozWith the increasing rise in the number of mobile devices and intelligent IoT devices, wireless networks have become increasingly complex, autonomous, and heterogeneous in terms of the types of network architectures they incorporate. Within these networks, efficiently allocating and managing resources for users is a significant problem to be solved. In this context, deep reinforcement learning techniques are expected to be among the main technologies used to achieve global optimization in dynamic resource allocation. This paper presents a proposal for resource allocation in wireless networks, termed Cross-Entropy Reinforcement Learning, in order to maximize energy efficiency and meet users’ quality of service (QoS) requirements. The approach considers a multi-user, multi-objective communication system based on CP-OFDM (Cyclic-Prefix Orthogonal Frequency Division Multiplexing) technology using reinforcement learning methods, specifically a Deep Q-Network (DQN) associated with the CrossEntropy algorithm to obtain an optimal resource allocation policy. The implementation encompasses system parameters such as bandwidth, modulation, number of users, and average packet size, while detailing the structure of resource elements, subcarrier distribution, and transmission capacity in different modulation modes within the LTE (Long Term Evolution) system frame. Simulation results demonstrate that the proposed method exhibits good convergence characteristics and performs better than the traditional DQN approach without cross-entropy.Item Análise da aplicação de RPA para atualização de segurança de senhas(Universidade Federal de Goiás, 2023-08-07) Borges, Mariana Inácia Xavier; Castro, Marcelo Stehling de; Castro, Marcelo Stehling de; Guedes, Leonardo Guerra de Rezende; Pinheiro Júnior, Carlos GalvãoWith the rapid advancement of technology, the virtual environment has become an extension of human life. As a result, information security has become an extremely important aspect in ensuring individuals' privacy. Authentication using passwords is currently the most common way to reaffirm this privacy. However, the careless use of passwords can lead to personal and professional consequences, as most data breaches in companies related to cybercrimes are associated with weak and reused credentials of their employees. This article proposes an analysis of password security using a Robotic Process Automation (RPA) tool to verify and maintain the security of passwords used in a corporate environment.Item Desenvolvimento de um reflectômetro/vector voltmeter de 6 portas para um vector network analyzer de baixo custo(Universidade Federal de Goiás, 2024-02-02) Gonçalves, Lucas de Jesus Batista; Cardoso, Álisson Assis; Cardoso, Álisson Assis; Kopcak, Igor; Vieira, Flávio Henrique TelesThroughout high-frequency circuit design procedure, there is often a demand for testing and characterization of components, frequently resorting to the use of network analyzers (VNAs). In this context, the project at hand is dedicated to the development of a 6-port reflectometer, an approach that simplifies the circuit analysis process from a single-port perspective by eliminating complex components such as mixers, filters, and phase detectors commonly used in VNA construction. By adopting power readings in a linear 6-port system, not only is construction simplified, but accessibility is also expanded, catering to a variety of users. This work has demonstrated the feasibility of providing a more accessible solution for the reflectometer, which, in turn, can be applied in the development of multi-port network analyzers at a lower cost, promoting technical efficiency and democratizing access to high-frequency technology.Item Desenvolvimento de um software identificador de incêndios utilizando um modelo de machine learning(Universidade Federal de Goiás, 2023-08-14) Oliveira , João Vitor Almeida de; Pinheiro Júnior, Carlos Galvão; Pinheiro Júnior, Carlos Galvão; Vinhal, Cássio Dener Noronha; Cruz Júnior, Gélson daThis article aims to present a real-time monitoring system to detect fires in establishments and on city streets. This system makes use of Machine Learning techniques, more specifically YOLOv5, for fire detection in images coming from IP cameras via RTSP protocol. For the training, a database was created with annotations specifically for this project. Training was performed on a local machine and the result was a model with a mAP50 of 0.577 for the validation set and 0.413 for the test set. In the test set, a precision of 0.514 and a sensitivity of 0.448 were obtained, which means that it has many occurrences of false positives and false negatives in the detections. Finally, the developed management system – server, web application and database structure – has features such as user registration, authentication, IP camera management, camera image viewing and real-time response to fire detection.Item Desenvolvimento de uma API de comando de voz para deficiência visual no xadrez(Universidade Federal de Goiás, 2024-02-01) Mulser, Rodrigo Santos; Cardoso, Alisson Assis; Cardoso, Alisson Assis; Souza, Gustavo Souto de Sá e; Nerys, José Wilson LimaThe challenges faced by individuals with disabilities throughout their educational journey, from literacy to adulthood, are numerous. Throughout the development of society, there is an incessant pursuit of providing citizens with disabilities greater access, allowing them to explore and develop their potential as individuals, and promoting social interaction. While it is crucial to encourage socialization and social inclusion, it is equally essential to create conditions that enable overcoming any limitations. With the advancement of software, hardware, and associated technologies, the development of these conditions has become a tangible reality. In the context of teaching and developing individuals with visual impairments and the benefits derived from sports practice, with an emphasis on the game of chess, this research describes the implementation of a software solution. This solution aims to facilitate the participation of individuals with visual impairments on digital platforms dedicated to chess, focusing on practical activities, study, and the promotion of this strategic game. The implementation focuses on voice interaction, involving the interpretation of vocalized instructions for piece movements, and providing the opponent's moves to the player in audio format.Item Desenvolvimento Web com acessibilidade para terceira idade(Universidade Federal de Goiás, 2023-08-17) Araújo, Karine Paes Landim; Moreira, Thallis André Faria; Castro, Marcelo Stehling de; Castro, Marcelo Stehling de; Pinheiro Júnior, Carlos Galvão; Oliveira , Gustavo Dias deWith the aging of the global population and technological advancement, the digital inclusion of the elderly on the Internet has become a major challenge. The lack of accessibility geared towards this audience has hindered their adaptation to new digital means. From this need, the development of a library with accessibility features targeted for programmers is proposed, based on research to identify the main problems and navigation difficulties on the Web faced by the elderly, in order to promote ease of use and a better user experience. Throughout the article, the need for web accessibility for the elderly will be discussed, the development process of the proposed resource library, and how it can effectively improve the online experience of the elderly. Important concepts about usability, accessibility, and visibility principles that underpinned the development of the components are explored. Testing and validation tools, such as AccessMonitor, WAVE, Axe, Lighthouse, and Pa11y were used to validate the components’ compliance with accessibility guidelines. All components were subjected to tests using the WAVE tool and the AXE tool, and after rigorous evaluation, no problems were found, confirming total compliance with accessibility standards. Additionally, all documentation is made available on the GitHub repository and with its installation via NPM, and future plans for expansion and improvement of the components.Item Implementação reduzida de MIPS-32 monociclo em system verilog(Universidade Federal de Goiás, 2024-02-05) Rochelle, Beatriz Carvalho de Barros do Vale; Badan, Tomas Antonio Costa; Badan, Tomas Antonio Costa; Pimentel, Sérgio Pires; Pinheiro Júnior, Carlos GalvãoThis paper presents an implementation of the basic processing unit of a processor derived from MIPS 32, with a reduced instruction set and single-cycle design. It does not include privileged instructions and functionalities like interrupt handling and I/O support. The memory modules were substituted for mock units for the execution of the integration tests. The tests were coded in Python and executed using the framework cocotb, due to its ease of use. The architecture was implemented using the language SystemVerilog and compiled using both Icarus Verilog and Verilator. Despite the project not having been synthesized, the simulations demonstrated proper functioning and produced accurate results.Item Modelo de machine learning aplicado à identificação do mosquito Aedes aegypti(Universidade Federal de Goiás, 2023-08-21) Morais, Débora Bruna de; Pires, Sandrerley Ramos; Pires, Sandrerley Ramos; Fernandes, Deborah Silva Alves; Silva, Karina Rocha Gomes daThe present project aimed to develop and train a machine learning model for the classification of Aedes aegypti mosquitoes and other mosquito species, with the purpose of contributing to the control of diseases transmitted by these vectors. The development process of the model included the collection of mosquito image data, the implementation of preprocessing techniques for effective model training, and the implementation of a convolutional neural network for sample classification. The dataset consisted of 14,716 images of mosquitoes from various species, with an imbalance between the classes. Data Augmentation technique was applied to increase the number of samples and balance the training set. The model was trained for 60 epochs, with the use of callbacks to optimize the training process. The results showed an accuracy of 75.4% in classifying the samples, indicating a promising performance of the model. However, signs of possible overfitting were observed due to the lack of representative samples and limitations in computational resources. Despite the challenges faced, the model demonstrated the ability to distinguish between mosquito species, contributing to advancements in the control of Aedes aegypti and other mosquito species. Future work may explore expanding the dataset and experimenting with different neural network architectures to improve the model's performance. In summary, the project represents an important step in the development of machine learningbased solutions for the prevention of mosquito-borne diseases.Item Nolan - software de gestão de salas de cinema(Universidade Federal de Goiás, 2023-08-08) Zirretta, Caio Vinícius Pinto; Castro, Marcelo Stehling de; Castro, Marcelo Stehling de; Lemos , Rodrigo Pinto; Oliveira, Gustavo Dias deThe growth of technology utilization in the latest years has been promoting a race towards small e big business to search for the most modern and efficient solutions. Those solutions range from a company organization to even perform vital operations, as it is a key element to increase productivity, earn more clients, discover new markets, and propel a product or a service. Those factors contribute to the primordial element that a business always desire: to increase profit. Web solutions, compared to conventional ones, have an easy adaptability as they can be accessed from most of the electronic devices used nowadays and do not demand a high computer power. A browser access is the only required to utilize them, eliminating the necessity for any additional tools that could harm a mobile or PC performance. The objective of this project is to create a web solution that could assist on solving common cinemas problems, such as sessions’ organization in their respective movie rooms, the register and modification of movies registers, registry of tickets and provide the customers a direct and enjoyable consumption experience.Item Sistema de controle de acesso utilizando RFID para uma biblioteca(Universidade Federal de Goiás, 2024-02-05) Rodrigues, Raphael Marques; Costa, Thiago Alves da; Cardoso, Alisson Assis; Silva, Karina Rocha Gomes da; Silva, Karina Rocha Gomes da; Melo, Fernando Ferreira de; Nerys, Jose Wilson LimaIn the current technological era, companies have sought to adapt to the advancement of industry 4.0, which has been innovating the way of production in the market. Companies are undergoing significant transformation due to the innovative implementation of RFID. Libraries should not be left behind, a computer system that helps users have a comfortable and quick experience when requesting books to borrow will never be superfluous. This study aimed to develop a prototype of a functional information system that allows managing the processes of a library, and thus meeting the demands of the service, which include the registration of books, users, loans, among others. It aims to take advantage of the benefits offered by technology, in addition to its timely and appropriate use as a facilitator of internal processes. Therefore, an information system proposed according to the needs of a library is a plausible and efficient option to support the administrative management tasks of a library system. This work presents an information system whose main function is to assist in book lending and access control in a library. A system has been developed that will help tasks carried out by library staff to be carried out more efficiently. For this, the method used consisted of data collection, analysis and comparison of technologies available on the market, where the efficiency of RFID technology was verified in comparison to competitors.