Search
Now showing items 1-7 of 7
Redes neurais aplicadas a grafos: uma abordagem semi-supervisionada
(Universidade Federal de São Carlos, 2022-04-18)
In this work, we propose an in-depth analysis of Graph Convolutional Networks, a semi-supervised machine learning method for node classification in graph-structured data. Based on the seminal work proposed by Thomas Kipf ...
Análise, seleção e agrupamento de características relevantes das equipes da NFL durante os anos de 2013-2016 e suas relações - um estudo de caso
(Universidade Federal de São Carlos, 2022-09-14)
On this work, the study of different NFL (National Football League) variables was proposed, with the main goal of analysing, selecting and clustering their characteristics and its correlations. Data on the official NFL ...
Classifcação binária via Bayes Ingênuo: um estudo comparativo de predições
(Universidade Federal de São Carlos, 2023-03-17)
In this undergraduate thesis, we propose a review of the Naive Bayes classifcation
method applied to binary response variables, with a more in-depth formalization of the
Gaussian Naive Bayes and Flexible Naive Bayes ...
Modelo de predição para dados desbalanceados utilizando informações de financiamentos de veículos
(Universidade Federal de São Carlos, 2023-03-28)
For the statistics thesis project, a model adjustment is proposed for unbalanced data,
using vehicle financing information, with the response variable being dichotomous, divided
into defaulters and non-defaulters. ...
Máquinas de vetores suporte com aplicação em classificação de crédito
(Universidade Federal de São Carlos, 2023-03-22)
The credit granting represents one of the products with the highest profitability within a financial institution. However, to ensure profit, institutions must know to whom they lend their capital. In this scenario, a ...
Estudo da prevalência de transtornos mentais comuns via métodos de classificação
(Universidade Federal de São Carlos, 2024-02-16)
The present undergraduate thesis focuses on the study of the association between specific variables and the diagnosis of common mental disorders. To achieve this goal, we examined classification methods, namely decision ...
Utilização de algoritmos de classificação para diagnóstico de diabetes
(Universidade Federal de São Carlos, 2024-02-15)
The undergraduate thesis consists of the study of binary classification algorithms for diagnosing diabetes based on clinical data and physical activity data. For this purpose, we will accomplish a statistical and conceptual ...