DSpace Communidade:
http://repositorio.ufc.br/handle/riufc/22049
2024-03-28T13:07:00ZFerramenta WEB para calcular o dimensionamento de um sistema fotovoltaico on-grid
http://repositorio.ufc.br/handle/riufc/76671
Título: Ferramenta WEB para calcular o dimensionamento de um sistema fotovoltaico on-grid
Autor(es): Souza, Anderson Silva
Abstract: Brazil is recognized for having one of the highest electricity tariffs in the world, with approximately 25% of Brazilian families’ budgets allocated to this expense. This work serves as an
artifact for the feasibility of adopting photovoltaic solar energy systems as an affordable, safe,
and durable solution to reduce electricity costs. To achieve this goal, we present a WEB tool for
sizing residential photovoltaic systems connected to the electrical grid (On-Grid). Through this
WEB tool, it will be possible to determine the quantity of solar panels and the inverter power
based on specific residence characteristics such as size and geographical location. Additionally,
a thorough analysis of the time required to obtain a return on investment was conducted using the
payback calculation. Thus, the following steps were performed: requirements elicitation, creation
of screen prototypes, implementation of the web tool, consumption analysis, and analysis of
the return on the invested amount. Through these steps, it was possible to provide users with
a tool capable of sizing a residential photovoltaic system, taking into account their individual
needs and providing an estimate of the associated costs. The implemented tool successfully
sized a photovoltaic system for a residence with an average monthly consumption of 360.33
kWh. Therefore, the calculated peak power of the photovoltaic system by the tool was 2.51 kWp
with an inverter power of 3012 W. The tool also calculated the payback period, and as a result,
the payback is expected to occur in around 11 to 12 years. In conclusion, this work represents
a significant advancement in the Brazilian photovoltaic solar energy scenario by offering a
practical tool for sizing residential systems. The economy and energy efficiency provided by this
technology can contribute significantly to reducing Brazilian families’ expenses on electricity,
while promoting the use of clean and sustainable sources. It is a crucial step toward a more
sustainable and economically viable future for the country.
Tipo: TCC2023-01-01T00:00:00ZSimulação de modelo de combate a incêndios florestais utilizando enxame de VANTs
http://repositorio.ufc.br/handle/riufc/75982
Título: Simulação de modelo de combate a incêndios florestais utilizando enxame de VANTs
Autor(es): Andrade Júnior, Antonio César de
Abstract: Approximately 31% of the planet’s surface is covered by forest area, serving as an important
resource for a quarter of the global population and the economy. One of the main threats to this
resource are wildfires. It is estimated that even after 15 years from burning, forests show no
signs of recovery. This work proposes a model for combating forest fires as a complement to
the existing methods of combat. The model involves the use of a swarm of drones and a control
base. A group of surveillance drones traverses an area in search of detecting any signs of a
fire. If detection occurs, a signal with fire data is sent via a LoRaWAN network to the control
base. The base then sends suppression drones to the fire location. The work focuses on the
suppression task, estimating, through simulations, the impact of drones on fires. Additionally, a
LoRaWAN network was also set up using single-board computers as nodes in the model. To
achieve these objectives, the following steps were taken: research with firefighters and analysis
of the responses obtained, analysis of the water flow necessary for the complete fire extinction,
simulation of suppression, development of the LoRaWAN network, and analysis of the results
obtained. The research with firefighters revealed that they prefer the use of drones for passive
tasks (monitoring and cargo transport). The results obtained in the analyses and simulations
demonstrate proximity to what would likely occur in real scenarios and the possibility of using
swarms as an auxiliary tool to other combat methods, especially in the early stages of a fire. Also,
a possible architecture for the LoRaWAN network was shown. As future work, it is intended to
add new variables in simulations, development of the task of detecting fire foci, and new tests on
the LoRaWAN network.
Tipo: TCC2023-01-01T00:00:00ZAnálise comparativa de tecnologias javascript focadas no front-end para desenvolvimento web
http://repositorio.ufc.br/handle/riufc/75925
Título: Análise comparativa de tecnologias javascript focadas no front-end para desenvolvimento web
Autor(es): Martins Filho, Francisco Rubens Félix
Abstract: Over time, technology, especially web applications, has become increasingly crucial in the
business sphere. To meet the ever-growing demands, these applications are becoming more
complex and resource-intensive, necessitating optimization.
Frameworks were developed precisely to address this escalating demand. Nowadays, several
technologies/frameworks handle the ongoing challenges in web development, each with its own
unique characteristics.
This study presents a comparative analysis of JavaScript technologies React, Vue, and Next
within the context of front-end web development. The project involved the creation of a Pokedex
using each of these technologies. Additionally, field research was conducted with experienced
developers in the industry.
The analysis of these technologies encompassed various aspects, including available documentation, development environment configuration, support, the size and activity of developer
communities, the learning curve, and job market prospects.
The findings of this research offer a comprehensive understanding of the distinctive features of
React, Vue, and Next, enabling developers and businesses to make informed decisions when
selecting the most suitable technology for their front-end projects.
Tipo: TCC2023-01-01T00:00:00ZO uso de aprendizado profundo para predição de diagnósticos de doenças cardiovasculares
http://repositorio.ufc.br/handle/riufc/75923
Título: O uso de aprendizado profundo para predição de diagnósticos de doenças cardiovasculares
Autor(es): Santos, Stefane Ribeiro dos
Abstract: Cardiovascular diseases (CVD) are a group of diseases of the heart and blood vessels. These
diseases are the leading cause of death worldwide. CVD is affecting more and more young
adults, due to unhealthy habits such as not exercising, being overweight, obesity, smoking, stress,
depression and eating a diet high in fat and processed foods. In this context, early detection of
CVD plays an essential role so that management with counseling and medication can begin. Most
heart conditions can be diagnosed using electrocardiogram (ECG) signals. The classification of
the ECG is highly relevant today, as there are many medical applications in which this problem
can be evidenced. In the second half of the 20th century, Machine Learning (ML) evolved as a
sub-field of Artificial Intelligence (AI), capable of developing self-learning algorithms that form
knowledge from data in order to make predictions. Although there are many AM methods that
present solutions capable of helping with ECG interpretation, predicting CVD is one of the most
complex impasses in the field of clinical data analysis. That said, carrying out analyses with
methods that have not yet been explored for this purpose could make significant contributions
to the health field. With this in mind, this work proposes the use of deep learning to classify
CVD diagnoses, developing Transformer and LSTM neural network models and evaluating
them using the metrics of accuracy, recall and f1-score, in order to compare the performance
of the methods that have been used to predict cardiovascular disease diagnoses. The results of
the experiments showed accuracy values of approximately 70% to 84% for the LSTM neural
network and accuracy values of 48% or less for the Transformer neural network. For the recall
metric, Transformer obtained values of up to 62% and LSTM obtained results of up to 77%. For
the f1-score metric, LSTM had values between 41% and 72% and Transformer had lower values
of up to 36%.
Tipo: TCC2023-01-01T00:00:00Z