http://repositorio.ufc.br/handle/riufc/24007 2026-04-10T12:08:00Z 2026-04-10T12:08:00Z França, Lúcio Cauper Freitas de http://repositorio.ufc.br/handle/riufc/84613 2026-02-04T11:36:02Z 2026-01-01T00:00:00Z

Título: Implantação de recursos de acessibilidade web no observatório de dados abertos dos sertões de Crateús Autor(es): França, Lúcio Cauper Freitas de Abstract: The WEB accessibility guidelines aim to assist and help developers and programmers in building WEB sites accessible to all, accessibility that is neglected for part of the population in the digital environment. A very important guideline that is still a reference today is the WCAG, and since its emergence, other guidelines have been created based on WCAG, such as e-MAG and NBR 17225:2025. In this scenario of multiple guidelines and which ones could be applied, a parity was found between the WCAG and NBR 17225:2025 guidelines. Considering the situation of web accessibility in the municipal portals of the Sertões de Crateús region and noting that such portals have accessibility problems, this work proposed the application of accessibility resources in the Open Data Observatory of the Sertões de Crateús. As a result, the observatory portal was redesigned and a new accessibility analysis was carried out, where the levels, depending on the tool, either decreased or increased. Tipo: TCC

2026-01-01T00:00:00Z Lima, Francisco Rubens Dutra http://repositorio.ufc.br/handle/riufc/84581 2026-02-02T14:28:34Z 2026-01-01T00:00:00Z

Título: Odonto Vision: sistema cad para segmentação automática de dentes em radiografias panorâmicas. Autor(es): Lima, Francisco Rubens Dutra Abstract: Image segmentation is fundamental in automatic analysis applications, as it allows for the precise identification and delineation of relevant structures. In the dental context, this task is especially important in panoramic radiographs, which are widely used to provide a comprehensive view of the dental and bone structures. However, manual interpretation of these images is timeconsuming, subject to inter-professional variability, and affected by noise and low contrast. Recent advances in deep learning, particularly Convolutional Neural Networks (CNNs), have enabled more accurate segmentations through the automatic extraction of relevant features. Thus, this study aims to develop a CAD system to perform automatic tooth segmentation from panoramic radiographs, based on a comparative analysis of the performance of five U-Net–based architectures. The study was conducted using the Children’s Dental Panoramic Radiographs Dataset, in which the images underwent a preprocessing stage, and the models were trained using K-Fold cross-validation combined with Grid Search for hyperparameter optimization. The results of the external validation stage, conducted on two subsets of the overall dataset, showed that in the first subset, Dataset and code, the W-Net achieved the best performance, with Sensitivity 0.809, E-MEASURE 0.925, IOU 0.785, and DSC 0.879, indicating a higher capacity for segmenting dental regions. In the second subset, Panoramic Radiography Database, the Attention U-Net stood out, reaching Sensitivity 0.965, E-MEASURE 0.975, IOU 0.858, and DSC 0.924, showing higher accuracy, preservation of tooth shape, and lower fragmentation of structures. The Wilcoxon test indicated that U-Net++ and U-Net 3+ showed significant differences compared to the classical U-Net, while W-Net and Attention U-Net had equivalent performance. Finally, considering the results of both quantitative and qualitative analyses of the segmented masks, as well as the inference time required to generate the segmentations, the Attention U-Net was selected as the final architecture to be integrated into the CAD system. Tipo: TCC

2026-01-01T00:00:00Z Castro, Matheus Sampaio http://repositorio.ufc.br/handle/riufc/82418 2025-09-08T17:45:50Z 2025-01-01T00:00:00Z

Título: PP - 8 (Practice Programming): uma ferramenta para o ensino de programação de maneira lúdica e visual Autor(es): Castro, Matheus Sampaio Abstract: The traditional teaching model, although effective in transmitting structured content and in the introduction of basic fundamentals, can represent a challenge for certain individuals, especially regarding the assimilation of more advanced concepts in programming. The difficulty in understanding such topics, coupled with a lack of motivation for in-depth study, frequently compromises academic results, and can lead to disinterest and, in some cases, to the interruption of the learning process. This work is based on three essential pillars: visual programming, Serious Games, and the pedagogical development environment. These pillars not only offer a robust theoretical basis but also serve as a practical guide for the conception of innovative solutions. Throughout the study, existing tools that utilize these principles were analyzed in order to identify their strengths and limitations. Based on this analysis, a prototype was created, which integrates these three pillars in a conceptual and practical way. Furthermore, the proposed tool featured the application of artificial intelligence to offer personalized and interactive feedback, enhancing the possibility of the programming teaching and learning process. This approach aims not only to fill existing gaps in the teaching of the area, but also to provide a learning experience that is more effective, engaging, and adapted to the individual needs of the students. Tipo: TCC

2025-01-01T00:00:00Z Cruz, Francisca Isabelle de Almeida http://repositorio.ufc.br/handle/riufc/82391 2025-09-05T11:36:07Z 2025-01-01T00:00:00Z

Título: Identificação de desinformação em áudio dentro de grupos públicos do aplicativo whatsapp Autor(es): Cruz, Francisca Isabelle de Almeida Abstract: The spread of disinformation on social media is a growing concern, negatively impacting public perception and decision-making. So far, efforts to identify fake news have focused mainly on textual content, leaving a significant gap in the detection of disinformation in audio. This study proposes an approach to fill that gap by analyzing a corpus of audio content and applying it to various machine learning models, with the aim of effectively supervising the detection of disinformation in sound-based content. Initially, the audio files are transcribed using speech recognition technologies (speech-to-text), enabling textual analysis with techniques aimed at identifying fake news. The multimodal approach — integrating both audio and text — enhanced detection effectiveness by considering contextual and semantic aspects that might go unnoticed in purely textual analyses. Different vectorization combinations (BoW and TF-IDF) were evaluated, with variations of n-grams and preprocessing, using machine learning models such as SGD, SVM, Random Forest, among others. Performance was measured using metrics such as F1- score, precision, recall, and FPR. The best results were achieved with the SGD and Linear SVM models, particularly with TF-IDF combining unigrams, bigrams, and trigrams with preprocessing, reaching an F1-score of up to 0.579. This demonstrates a strong ability to identify both fake and truthful content, even in imbalanced class scenarios. The proposed methodology proved effective in detecting disinformation in audio, contributing relevant technological solutions to combat the spread of fake news on social media platforms. Tipo: TCC

2025-01-01T00:00:00Z