Trabalho de Conclusão de Curso - TCC

URI Permanente para esta coleçãohttps://repositorio.cesupa.br/handle/prefix/20

Navegar

Agora exibindo 1 - 3 de 3

iTutor: aplicação híbrida para medida de aleatoriedade em redes de discussão
(Centro Universitário do Estado do Pará, 2022-12-05) Barbosa, Elielson Fernando do Santos; Freitas, Lucas da Silva; Lima, Pedro Augusto Pinto de; Araújo, Fábio Rocha de
Networks are structures in which there is a set of elements connected to each other and can be observed in various contexts, as seen in social or material structures designed by humanity. In view of this, society has been using discussion networks with a focus on enhancing the achievement of a concise conclusion about a given topic, discussions that have a randomness metric which evaluates the efficiency of the network interactions, with a focus on obtaining the results of the discussion networks to classify the quality of the discussion. The objective of this course work is the definition of metrics for analyzing the performance of discussion networks and the creation of an application that will allow the recording and visualization of the interactions of these networks. For this, an application was developed that records interactions during a discussion and also a server that processes this data and returns it to the application. The results obtained were an application that manages the flow of groups and discussions, in addition to also generating the randomness index and the interaction graph, duly available in the play store. This course work satisfactorily fulfilled the proposed objectives, creating metrics and satisfactory forms of evaluation discussion networks.
Machine Learning e conservação da Amazônia: uma revisão sobre o uso de Machine Learning na conservação da região da Amazônia
(Centro Universitário do Estado do Pará, 2023-12-07) Dias, Carlos Eduardo Nylander Bitencourt; Barros, Rafael Luís Carvalho; Gomes, Vitor Hugo Freitas; Elgrably, Isaac Souza; http://lattes.cnpq.br/7590598824563858; http://lattes.cnpq.br/5218954387107307; Nascimento, Polyana Santos Fonseca; http://lattes.cnpq.br/6889523334917369; Araújo, Fábio Rocha de; http://lattes.cnpq.br/2407240421934932
With an approximated expanse of 6 million km², the Amazon Rainforest is a region of global interest, particularly for its great biodiversity some of which still unmeasured. The forest exercises an important part in regional and global climate control, capturing and storing CO2, contributing with rain formation and varied biogeochemical cycles. Its large contribution to the livelihood of native and traditional communities is not to be neglected. Despite it all, the territory faces great challenges, suffering with the impacts of deforestation, fires, global climate change, pollution, and more. In its conservation efforts, the usage of advancing tools and technology has resulted in the implementation of Artificial Intelligence and its sub-areas, such as Machine Learning, which has contributed to the development of predictive studies in the Amazon. Here, we revised studies that implemented Machine Learning in the conservation of Amazon’s territory, seeking a deeper understanding of its limitations and future usage of this technology. We concluded that, as a technology Machine Learning has helped in preservation efforts, but there still is much that can be done to improve its usage, such as the utilization of comprehensive data, training of professionals and experts to adequately implement the technology and to analyze the results, being these improvements crucial to the futureconservation efforts in the Amazon Region.
Otimização de carteira de investimento com a teoria de portfólio de Markowitz utilizando a linguagem de programação Python
(Centro Universitário do Estado do Pará, 2023-12-06) Oliveira Junior, José Nonato Cunha de; Girotto, Pedro Henrique Sales; Elgrably, Isaac Souza; http://lattes.cnpq.br/7590598824563858; http://lattes.cnpq.br/0421749067951878; Araújo, Fábio Rocha de; http://lattes.cnpq.br/2407240421934932
The present work presents the development of a methodology for optimization of investment portfolios using the Python programming language, based on Harry Markowitz's Portfolio Theory (1952). Based on static analyses and observations, there was an increase in the number of individuals registered on the main Stock Exchange in Brazil, B3, which shows a growing interest on the part of the population in investments. In this way, the project arises from the attempt to provide a simplification of the act of investing by enabling the optimization of investment portfolios in an accessible and practical way for investors and financial market professionals. It contains conceptualizations of risk and Markowitz's Theory in its first section. In the second section, the feasibility analysis of the product is presented, moving on to prototyping, with its specific requirements and arrangement of the Data Flow and Use Case diagram, the technologies used for the development of the methodology, including Python, Pandas, Numpy, Plotly, YFinance, Flask and PyPortfolioOpt, the product functionalities and the data analysis of the input and output files. Also in this section, the methodological nature of the work is arranged, showing the exploratory and evaluative research techniques that permeated the testing stage of the same, the commercialization model of the product to implement it in the market and possible direct and indirect competitors. In the third section, the results of the application and the data and assets considered are exposed, with a survey directed to the target audience. And, finally, in the fourth section, there are the considerations of the tool, about which it can be stated that it fulfilled the initial objective of the project and showed a real and potential possibility of visualization of portfolios and their respective risks, enabling insights for the investment area and proving the potential of the Python tool as a technology.

Navegar

Navegando Trabalho de Conclusão de Curso - TCC por Autor "Araújo, Fábio Rocha de"