http://repositorio.ufc.br/handle/riufc/22047 2026-05-15T22:53:44Z 2026-05-15T22:53:44Z Ferreira, João Gabriel Soares http://repositorio.ufc.br/handle/riufc/83986 2025-12-23T16:36:07Z 2023-01-01T00:00:00Z

Título: Predição da fração de ejeção do ventrículo esquerdo por meio de algoritmos de deep learning aplicados a sinais de ECG de pacientes chagásicos Autor(es): Ferreira, João Gabriel Soares Abstract: Objective: To classify the left ventricular ejection fraction of chagasic patients into preserved and non-preserved by using electrocardiography signals. Context: Left ventricular ejection fraction is an important indicator of heart failure and sudden death. To estimate this indicator, echocardiography is necessary, which is usually more expensive and restrictive than electrocardiography. Methods: Initially, we separated the signals into two classes: ejection fraction less than 0.5 (class 1) and ejection fraction greater than or equal to 0.5 (class 2). We used a Tukey’s boxplot to separate noisy beats from non-noisy ones based on their duration. Next, we applied an LSTM (Long-short Term Memory) network to classify sets of 200 beats of each signal. Finally, we applied some methods (mode, sum of probabilities, artificial neural network and LSTM) to obtain a class for the entire signal using the network outputs. Results: We obtained, as the best result, an accuracy of 0.79 and a F1-score of 0.79. Conclusion: We obtained satisfactory results. However, we believe that them can be improved by a more sophisticated beat selection method and a more robust LSTM model. Tipo: TCC

2023-01-01T00:00:00Z Soares, Kayann Costa http://repositorio.ufc.br/handle/riufc/83985 2025-12-23T16:13:59Z 2023-01-01T00:00:00Z

Título: Desenvolvimento de um sistema embarcado de baixo custo para agricultura de precisão Autor(es): Soares, Kayann Costa Abstract: Precision agriculture plays a crucial role in increasing efficiency and productivity in crop production by monitoring environmental variables such as air humidity, temperature, atmospheric pressure, ambient light, soil moisture and pH, carbon dioxide (CO2), and volatile organic compounds (VOCs). With the advancement of the Internet of Things (IoT) and the reduction in costs of Wi-Fi modules, these technologies have become more accessible, enabling the integration of embedded systems and Wi-Fi connectivity for real-time transmission of collected data, facilitating agile and informed decision-making. In this context, the objective of this work is to develop a low-cost Printed Circuit Board (PCB) with a low-power microcontroller and precise sensors to collect relevant data for agriculture and environmental variables. The project also aims to be sustainable, utilizing solar energy as a power source and employing a rechargeable battery to minimize environmental impacts. Therefore, the proposal is to make these technologies accessible not only to large-scale producers but also to small-scale farmers with limited resources for investing in advanced solutions. Tipo: TCC

2023-01-01T00:00:00Z Paulino, Italo Aguiar do Nascimento http://repositorio.ufc.br/handle/riufc/83984 2025-12-23T13:35:17Z 2023-01-01T00:00:00Z

Título: Performance musical via rede: Estado da arte, implementação e análise Autor(es): Paulino, Italo Aguiar do Nascimento Abstract: This research provides a comprehensive understanding of the technical elements essential for successful Network Musical Performance (NMP). It explores existing solutions, system requirements, and evaluation methodologies to address the challenges faced by musicians in remote collaboration and enable synchronous interactions. The article examines the necessary technical requirements for achieving low-latency communication in NMP and emphasizes the importance of high-quality audio and effective collaboration. It also considers the impact of network distance on latency and highlights the potential advantages of advancements in computational power, network bandwidth, and 5G technology. By considering various scenarios, such as rehearsals, music lessons, and live concerts, the article showcases the potential of synchronous real-time interaction to foster musical innovation. Overall, this research contributes to the understanding of NMP and provides insights for future advancements in network musical performance. Tipo: TCC

2023-01-01T00:00:00Z Oliveira, Laura Santiago Campos http://repositorio.ufc.br/handle/riufc/83983 2025-12-23T13:25:47Z 2023-01-01T00:00:00Z

Título: Análise e visualização das estações de tratamento de esgoto e suas tecnologias no estado do Ceará Autor(es): Oliveira, Laura Santiago Campos Abstract: In the state of Ceará, the quality of the treated wastewater in the treatment plants is regulated by Resolution COEMA No. 2 of 02/02/2017. However, many of the wastewater treatment units fail to meet these standards. It is crucial to gain a deeper understanding of the reality of the treatment plants and their different technologies - Upflow Anaerobic Sludge Blanket (UASB), UASB with post-treatment, Activated Sludge, and Stabilization Ponds - and how they can be improved. Therefore, data analysis was conducted on the years 2017 to 2020 and 2021 to 2023, using the Principal Component Analysis (PCA) and t-Distributed Stochastic Neighbor Embedding (t-SNE) methods. Due to the numerous attributes, it is also challenging to determine the best way to classify the quality of the data based on the technology used. Consequently, it will be easier to identify the best stations for each technology and the key characteristics that distinguish those with good performance from those without. At the end of this study, differences were identified between levels of technologies, except Activated Sludges, and the main characteristics that influences their results. Additionally, visualizations were created for the UASB and Stabilization Ponds technologies to facilitate understanding of the wastewater quality over time and aid in identifying patterns and stations that are closer to meet the legislation’s limits. Tipo: TCC

2023-01-01T00:00:00Z