DSpace Communidade:http://repositorio.ufc.br/handle/riufc/220472026-06-17T06:47:52Z2026-06-17T06:47:52ZDesenvolvimento de uma plataforma web para comunicação e organização no ambiente universitárioAbreu, Eduardo Viana dehttp://repositorio.ufc.br/handle/riufc/867492026-06-15T11:22:13Z2026-01-01T00:00:00ZTítulo: Desenvolvimento de uma plataforma web para comunicação e organização no ambiente universitário
Autor(es): Abreu, Eduardo Viana de
Abstract: This work presents the development and performance analysis of UFC Hub, a web platform designed to centralize communication and activity organization at the Universidade Federal do Ceará. The motivation stems from limitations identified in existing institutional platforms which, although robust for administrative purposes, provide insufficient support for student social interaction, study group formation, and student-led event organization, especially on mobile devices. UFC Hub was developed using TypeScript and Next.js, released as an open-source solution, and deployed on cloud services under a free-tier plan for prototyping purposes. The platform integrates features such as the creation and management of private groups with chat, academic event organization and participation, a community blog, a personal calendar, and user profiles. Results show that UFC Hub achieved high scores in the conducted audits, outperforming, across several indicators, institutional platforms such as SIGAA and the UFC News portal. In addition, the interface analysis indicated compliance with usability and accessibility requirements, with adequate responsiveness across desktop and mobile devices and support for different visual themes. Overall, the adopted architecture and technologies proved effective in meeting the established performance, usability, and accessibility requirements, providing a complementary solution to the university’s official platforms.
Tipo: TCC2026-01-01T00:00:00ZSistema leve colaborativo com redes neurais convolucionais e vision transformers para segmentação de imagens médicasLourenço, Bruna Stefanie Costahttp://repositorio.ufc.br/handle/riufc/867332026-06-11T20:36:22Z2025-01-01T00:00:00ZTítulo: Sistema leve colaborativo com redes neurais convolucionais e vision transformers para segmentação de imagens médicas
Autor(es): Lourenço, Bruna Stefanie Costa
Abstract: Medical image segmentation is fundamental for providing clear visual information about anatomical structures and anomalies. Currently, tasks related to the extraction of regions of interest
increasingly rely on deep learning approaches, which overcome the limitations of traditional methods. In recent years, Convolutional Neural Networks (CNNs) have been widely adopted in numerous studies due to their ability to capture local patterns present in images. However, CNNs exhibit limitations when the objective is to model global relationships among different image regions. To address this issue, a new research direction based on Vision Transformers (ViTs) has emerged, achieving strong performance in various computer vision tasks. In this work, I propose to combine the complementary strengths of CNNs and ViTs in a promising approach for the segmentation of chest computed tomography (CT) images with pulmonary lesions associated with COVID-19. The proposed method integrates CNNs and Vision Transformers within a collaborative system composed of three specialized agents. Each agent operates in a complementary manner, focusing on distinct image characteristics to improve segmentation quality. The system is designed to be lightweight, making it suitable for healthcare systems in developing countries and clinical environments with limited computational resources. The effectiveness of the proposed system was validated on a public lung CT image segmentation dataset using evaluation metrics widely adopted in the literature, including the Dice Coefficient, Jaccard Index, Hausdorff Distance, ASD, and bAHD. The framework achieved consistent performance, reaching Dice Coefficient = 0.8260, Jaccard Index = 0.7330, Hausdorff Distance = 9.3301, ASD = 1.3401, and bAHD = 5.7430. These results demonstrate not only the feasibility of the proposed lightweight collaborative approach but also superior performance when compared to a reference model based on a traditional CNN, implemented exclusively for comparative purposes.
Tipo: TCC2025-01-01T00:00:00ZUma análise comparativa entre diferentes paradigmas de construção de modelos preditivos para vazão de reservatóriosNascimento, Diego Melo dohttp://repositorio.ufc.br/handle/riufc/867312026-06-11T20:23:16Z2026-01-01T00:00:00ZTítulo: Uma análise comparativa entre diferentes paradigmas de construção de modelos preditivos para vazão de reservatórios
Autor(es): Nascimento, Diego Melo do
Abstract: This study investigates one-step-ahead forecasting of mean monthly natural inflow in Brazilian hydroelectric reservoirs, an activity directly related to the planning and operation of the National Interconnected System (SIN). A comparative analysis is conducted among three data-driven approaches: a regularized autoregressive model, a recurrent neural network based on long and short-term memory, long short-term memory (LSTM), and a prompt-based approach using a large language model (LLM), specifically Gemini 2.5 Flash (GEMINI-2.5-F) and Gemini 3 Flash Preview (GEMINI-3-FP). A reproducible experimental protocol is adopted, employing sliding-window validation and chronological data splitting, applied to four reservoirs with distinct hydrological regimes: Furnas, Sobradinho, Itaipu, and Ilha Solteira. Model performance is evaluated on the original scale using the root mean square error (RMSE) and the coefficient of determination (R²). The results indicate that no single method achieves superior performance across all analyzed reservoirs. The LSTM yields lower forecasting errors in Furnas and Sobradinho, whereas GEMINI-3-FP attains better results in Itaipu and Ilha Solteira. These findings indicate that LLM-based approaches, even without direct parametric training on numerical time series, can produce consistent forecasts when the problem is formulated as inference conditioned on structured textual contexts. The study highlights the relevance of treating LLMs as a complementary approach to traditional hydrological modeling, whose application depends on the characteristics of the time series and requires careful empirical validation.
Tipo: TCC2026-01-01T00:00:00ZDesenvolvimento e avaliação experimental de um dispositivo vestível multimodal para aquisição de sinais cardiovascularesSousa, Eduardo Monteiro dehttp://repositorio.ufc.br/handle/riufc/867092026-06-11T12:30:40Z2026-01-01T00:00:00ZTítulo: Desenvolvimento e avaliação experimental de um dispositivo vestível multimodal para aquisição de sinais cardiovasculares
Autor(es): Sousa, Eduardo Monteiro de
Abstract: This paper presents the development of a low-cost wearable device for the acquisition and experimental analysis of non-invasive cardiovascular signals. The system is based on the simultaneous acquisition of Electrocardiogram (ECG) and Photoplethysmography (PPG) signals, processed by an ESP32-C3 microcontroller. As a main focus, a comparative analysis of the performance of dry stainless steel and 1000 silver electrodes was conducted, evaluating ECG signal quality metrics such as noise level, QRS complex amplitude, and signal-to-noise ratio. Additionally, a qualitative comparison was made with commercial devices for non-clinical use, such as home pulse oximeters and smartwatches. The results obtained demonstrate the technical feasibility of the prototype as an experimental and educational platform for acquiring cardiovascular signals, respecting the limitations inherent to a low-cost academic prototype.
Tipo: TCC2026-01-01T00:00:00Z