DSpace Coleção:https://repositorio.ifgoiano.edu.br/handle/prefix/2662026-03-27T21:47:13Z2026-03-27T21:47:13ZCOMPARAÇÃO DE MÉTODOS DE BALANCEAMENTO DE DADOS EM DIFERENTES CENÁRIOSSouto, José Antônio Ribeiro ; Sousa, Flavio Diniz dehttps://repositorio.ifgoiano.edu.br/handle/prefix/63402026-03-17T23:57:22Z2026-03-11T00:00:00ZTítulo: COMPARAÇÃO DE MÉTODOS DE BALANCEAMENTO DE DADOS EM DIFERENTES CENÁRIOS
Autor(es): Souto, José Antônio Ribeiro ; Sousa, Flavio Diniz de
Primeiro Orientador: Costa, Nattane
Primeiro Membro da Banca: Costa, Nattane
Segundo Membro da Banca: Cardoso, Cristiane
Terceiro Membro da Banca: Carvalho, Amaury
Abstract: Class imbalance occurs when there is an unequal distribution among the classes in
a dataset, such that one class has a significantly smaller number of instances compared to
the others. This scenario represents one of the challenges present in machine learning tasks,
directly impacting the performance of predictive models. This study aims to compare different
data balancing techniques, including oversampling, undersampling, and hybrid approaches,
applied to multiple datasets with different levels of imbalance. Experiments were conducted
using classification algorithms such as Decision Tree (C5.0), Random Forest, Artificial Neural
Networks (ANN), Logistic Regression, and SVM, which were evaluated using the following
performance metrics: accuracy, precision, recall, and F1-score. The analysis of the results made
it possible to identify the impact of balancing techniques in different experimental scenarios, as
well as their limitations and advantages. In general, oversampling techniques frequently showed
superior or equivalent performance compared to the other evaluated methods, while the use of
unbalanced data tended to present inferior results for certain metrics and algorithms. In addition,
tree-based models, such as Random Forest, demonstrated greater robustness across the different
analyzed scenarios. The findings of this study aim to provide support for the appropriate selection
of balancing methods, contributing to the development of more robust and reliable models.
Editor: Instituto Federal Goiano
Tipo: Trabalho de Conclusão de Curso2026-03-11T00:00:00ZSISTEMA DE GERENCIAMENTO CENTRALIZADO DE BUFFETS E EVENTOSFaria, Ítalo Gonçalves Meireles ; Meireles, João Gabriel de Oliveirahttps://repositorio.ifgoiano.edu.br/handle/prefix/63372026-03-17T23:57:58Z2026-02-26T00:00:00ZTítulo: SISTEMA DE GERENCIAMENTO CENTRALIZADO DE BUFFETS E EVENTOS
Autor(es): Faria, Ítalo Gonçalves Meireles ; Meireles, João Gabriel de Oliveira
Primeiro Orientador: Cardoso, Cristiane de Fátima dos Santos
Primeiro Membro da Banca: Costa, Nattane Luiza da
Segundo Membro da Banca: Vieira, Gabriel da Silva
Abstract: The management of buffets and events is still frequently carried out through decentralized processes, such as spreadsheets, messaging applications, and manual records, which may compromise information organization, hinder reservation tracking, and increase the occurrence of operational errors. In this context, this work presents the development of a mobile application for Android aimed at the centralized management of buffets and events, integrating the registration of food items and services, reservation control, and visual customization within a single environment. The adopted methodology included requirements gathering and analysis, definition of user profiles, and conceptual modeling using UML diagrams. The proposed solution employs a multi-tenant architecture, with the back-end implemented in Java using Spring Boot and services exposed through a RESTful API, while the front-end was developed with Angular, Ionic, and Capacitor. Among the implemented features are JWT-based authentication, management of food items and services, creation and approval of reservations with automatic event generation, and the sending of status notifications. As a result, a functional application was obtained that meets the defined requirements and centralizes, in a structured manner, the management processes of buffets and events within a single digital environment.
Editor: Instituto Federal Goiano
Tipo: Trabalho de Conclusão de Curso2026-02-26T00:00:00ZDESENVOLVIMENTO DE UMA API PARA RESTAURANTES E PAINEL DO CLIENTE CONTENDO INFORMAÇÃO NUTRICIONALLopes, Raquel Benevides; Silva, Géssica Meireles dahttps://repositorio.ifgoiano.edu.br/handle/prefix/63352026-03-14T00:33:16Z2026-03-04T00:00:00ZTítulo: DESENVOLVIMENTO DE UMA API PARA RESTAURANTES E PAINEL DO CLIENTE CONTENDO INFORMAÇÃO NUTRICIONAL
Autor(es): Lopes, Raquel Benevides; Silva, Géssica Meireles da
Primeiro Orientador: Cardoso, Cristiane de Fátima dos Santos
Primeiro Membro da Banca: Lima, Júnio César de
Segundo Membro da Banca: Santos Filho, Giovani Barbosa dos
Abstract: This work presents the development of an API for restaurant order management and order control, integrated with a web system and a client-oriented front-end. The system aims to improve the user experience by providing nutritional information about menu items and allowing filtering based on dietary restrictions. The proposal was developed based on the analysis of existing systems in the market, identifying limitations related to usability and access to nutritional information. The developed solution seeks to facilitate restaurant management while providing customers with clearer and more accessible information about the foods consumed. The system was implemented using modern web technologies, enabling integration between the back-end and front-end, and providing a more efficient and intuitive environment for both restaurant staff and customers.
Editor: Instituto Federal Goiano
Tipo: Trabalho de Conclusão de Curso2026-03-04T00:00:00ZCLASSIFICAÇÃO DE DANOS FOLIARES USANDO DEEP LEARNINGRosa, Walmir Cardoso dos Santoshttps://repositorio.ifgoiano.edu.br/handle/prefix/62732026-03-06T13:58:23Z2026-02-19T00:00:00ZTítulo: CLASSIFICAÇÃO DE DANOS FOLIARES USANDO DEEP LEARNING
Autor(es): Rosa, Walmir Cardoso dos Santos
Primeiro Orientador: Vieira, Gabriel da Silva
Primeiro Membro da Banca: Carvalho, Amaury Walbert de
Segundo Membro da Banca: Lima, Junio Cesar de
Abstract: Soybeans, an essential source of protein for human and animal nutrition, are especially vulnerable to attacks by defoliating insects. Manual collection and identification of insect forms present in crops is a time-consuming and error-prone practice. Considering the positive impact of monitoring techniques in cultivated fields, the use of mobile devices along with computer vision tools has been gaining prominence in precision agriculture.
Unlike other studies that focus solely on the development of models for predictive detection or diseases, this work proposes an approach based on the indirect classification of clues through leaf damage, in addition to integrating the model into a mobile application as a proof of concept, demonstrating its practical application.
We compared three neural network architectures, ResNet50, VGG16, and InceptionV3, to classify two soybean phrases (green beetle and soybean caterpillar). The three architectures
performed very well in classification with accuracy above 90%, but VGG16
showed the best performance, with 95.75%. The results demonstrate the ability of
deep learning models to recognize insects based on the damage they cause to pages and highlight the potential for integration between deep learning models and mobile applications, thus providing a viable alternative for monitoring guidelines in soybean crops.
Editor: Instituto Federal Goiano
Tipo: Trabalho de Conclusão de Curso2026-02-19T00:00:00Z