http://repositorio.ufc.br/handle/riufc/21982 Wed, 10 Jun 2026 05:54:11 GMT 2026-06-10T05:54:11Z https://repositorio.ufc.br:443/retrieve/a1a91991-6346-4dd7-b570-45d403df0239/comunidade_TCC-GRADUACAO_RI-moldurado.jpg http://repositorio.ufc.br/handle/riufc/21982 http://repositorio.ufc.br/handle/riufc/86671 Título: A utilização de sistemas de recomendação no contexto da desinformação Autor(es): Santos, Tales Araujo dos Abstract: The misinformation “pandemic”, facilitated by social media and mobile messaging platforms, has gone from being a minor nuisance to severely impacting law and order through the deliberate and large-scale manipulation of the general public’s sentiments. Recommender systems are an essential set of techniques and software tools capable of acting on the problem of content filtering and information retrieval in an overwhelming scenario of choice possibilities that presents the technological world today. One platform with a large data flow in the Brazilian scenario is the WhatsApp application, which has been the target of agents sharing disinformation content. With the present work, we intend to experiment to discover how recommender systems could act to recommend messages of a similar character concerning their factual content. We will demonstrate how the employed techniques could represent a recommender system, presenting their architectures, similarity methods, lists of recommendations and performance evaluation mechanisms. We will also present how the data under study, regarding messages collected from WhatsApp concerning the COVID-19 pandemic, behaved with the proposed architecture, as well as their results regarding the performance of recommendations, in order to understand how performance metrics such as mean reciprocal rank and mean average precision characterize the relevance brought by the results when using a simple criterion of similarity - cosine similarity - in purely textual contents. Finally, the ability of the recommendation system itself to be used as part of a classifier for messages that do not have a assigned label of disinformation presence will be evaluated, since the classifier uses a naive approach to identify the presence (or absence) of disinformation content. Tipo: TCC Sun, 01 Jan 2023 00:00:00 GMT http://repositorio.ufc.br/handle/riufc/86671 2023-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/86670 Título: Monitoramento de produção de torradas em uma esteira industrial por visão computacional Autor(es): Castro, Ramiro Campos de Abstract: Industry 4.0 symbolizes the union of the industry with the technological advances that are currently happening, such as artificial intelligence, internet of things and robotics. Computer vision is one of the ways that the industry can modernize itself, using cameras to monitor its processes and make decisions based on the data obtained from the analysis of the images of the processes. In this work, it is presented a computer vision system that uses digital image processing techniques for monitoring the production of toasts on a belt conveyor, making it possible to automate responses to events that may occur in a production line. For the system validation, videos were made of simulations of toasts being transported in a belt conveyor, this way there is a controlled test environment, where the angle of rotation and size of the toasts are known. Satisfactory results were obtained, where the system was able to detect all the toasts, and the measured rotation degree of the toasts had a maximum error of three degrees, showing that this system was effective in detecting and analyzing the toasts presented at the production line. Tipo: TCC Sun, 01 Jan 2023 00:00:00 GMT http://repositorio.ufc.br/handle/riufc/86670 2023-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/86669 Título: Sistema de visão computacional para auxílio ao diagnóstico de COVID-19 Autor(es): Paiva, Lucas Noleto Abstract: This work aims to perform a comparative analysis of COVID-19 image classification techniquesusing three pre-trained neural network architectures (Inception V3, VGG16, and ResNet50) forfeature extraction and three classifiers (KNN, MLP, and SVM) for classification. The datasetused was obtained from Kaggle and consists of chest X-ray images classified into three classes:normal, pneumonia, and COVID-19.Initially, the pre-trained neural network architectures were used to extract features from theimages, leveraging the pre-trained weights from the ImageNet database. The extracted featureswere then fed into the KNN, MLP, and SVM classifiers. Various evaluation metrics, includingconfusion matrix, precision, accuracy, F1-score, and recall, were calculated to analyze theperformance of the classifiers.Furthermore, an ensemble approach was employed by combining the two best performingclassifiers, which were SVM and MLP. However, it was observed that MLP outperformed theensemble of both classifiers. This finding suggests that, for this specific dataset, MLP was ableto capture the relevant information more efficiently.The obtained results demonstrated the effectiveness of pre-trained neural network architecturesfor feature extraction in COVID-19 images, as well as the classifiers’ ability to correctly classifythe images. Moreover, the ensemble approach showed promise in improving classificationperformance, although the results indicated that MLP alone achieved even better performance.This study contributes to the advancement of COVID-19 detection from chest X-ray images,presenting a comparative analysis of different neural network architectures, classifiers, andensemble techniques. The utilized evaluation metrics provide a comprehensive understanding ofthe model’s performance, enabling the selection of the most suitable approach for COVID-19image classification. Tipo: TCC Sun, 01 Jan 2023 00:00:00 GMT http://repositorio.ufc.br/handle/riufc/86669 2023-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/86668 Título: Análise das práticas de gestão de marca através das mídias sociais: um estudo de caso em uma empresa de vestuário Autor(es): Freitas, Lara Vanessa Sales de Abstract: Brand management reveals itself as a strategic tool within organizations, in which social media plays a fundamental role in the development of practices for this management. This research analyzes how brand management practices are worked through social media in a clothing company. Therefore, a qualitative descriptive research was carried out using the case study’s method. The gathering technique consisted of interviews and non-participant observation. The use of social media to provide brand management analysis contributions to the company was analyzed. It was verified that the practices are up to date and the results are satisfactory. The company is attentive to the development of the concept, value, identity, positioning and communication of its brand, launching products based on strategies that encourage customers to purchase frequently. Thus, it is concluded that even it is small, with a reduced structure and operates only on the web, a company can develop its brand through strategies already consolidated in the market. This study contributes theoretically by highlighting the viability of working on the brand in small businesses with a restricted budget. The internet is a space that allows this and the gains are exponential. Tipo: TCC Mon, 01 Jan 2024 00:00:00 GMT http://repositorio.ufc.br/handle/riufc/86668 2024-01-01T00:00:00Z