Browsing Computer Science - Undergraduate degree by Author "Carbonera, Joel Luis"
Now showing items 1-8 of 8
-
Uma abordagem automática para extrair correlações geológicas a partir de descrições de poços baseadas em ontologias
Garcia, Luan Fonseca (2013) [Work completion of graduation]Neste trabalho, propomos uma abordagem automática para o problema da correlação litológica no domínio da Geologia do Petróleo. A correlação litológica visa reconhecer uma mesma dada porção de rocha em diferentes sequências ... -
An approach based on class activation maps for investigating the effects of data augmentation on neural networks for image classification
Dorneles, Lucas Marques (2024) [Work completion of graduation]Neural networks have grown more and more popular in the last few years as an effec tive tool for the task of image classification due to the impressive performance they have achieved on this task. In image classification ... -
An evaluation of pre-trained models for feature extraction in image classification
Puls, Erick da Silva (2023) [Work completion of graduation]In recent years, we have witnessed a considerable increase in performance in image clas sification tasks. This performance improvement is mainly due to the use of deep learning techniques. Generally, deep learning techniques ... -
Applying BERT language model to poem classification : a study on data imbalance issues
Ceccon, Tiago Silveira (2023) [Work completion of graduation]Art, and specifically poetry, has always been a very valuable resource to understand a society’s identity and view of life. Recently, with the rise of the big data revolution, large datasets of the most varied subjects are ... -
Evaluating data imbalance approaches for classifying semantic relations using machine learning and word embeddings
Domingues, Gabriel Couto (2023) [Work completion of graduation]Explicit knowledge models are artifacts that represent domain knowledge in an explicit way and can be used in different ways, including structuring data, supporting information retrieval and reasoning. The identification ... -
A Framework for testing Federated Learning algorithms using an edge-like environment
Schwanck, Felipe Machado (2023) [Work completion of graduation]Federated Learning [FL] is a machine learning paradigm where many clients coopera tively train a single centralized model while keeping their data private and decentralized. FL is commonly used in edge computing, which ... -
Graph Neural Networks for image classification : comparing approaches for building graphs
Rodrigues, Julia Pelayo (2024) [Work completion of graduation]Graph Neural Networks (GNNs) is an approach that allows applying deep learning tech niques to non-Euclidean data, such as graphs and manifolds. Over the past few years, graph convolutional networks (GCNs) and graph attention ... -
Rating prediction of product reviews : an approach based on the BERT language model
Santiago, Carlos Morvan Filho de Paula e (2023) [Work completion of graduation]Nowadays online shopping has become increasingly common. Without the possibility to try on the products, customers became dependent on other customers’ reviews. Those are usually written in natural language and can be ...