https://repositorio.ifgoiano.edu.br/handle/prefix/250 Sun, 04 Oct 2026 21:45:52 GMT 2026-10-04T21:45:52Z http://repositorio.ifgoiano.edu.br:80/retrieve/311/Cincia-da-Computao.png https://repositorio.ifgoiano.edu.br/handle/prefix/250 https://repositorio.ifgoiano.edu.br/handle/prefix/6947 Título: ARQUITETURA IOT PARA MONITORAMENTO DE CULTIVOS AGRÍCOLAS: OTIMIZAÇÃO DE TRANSMISSÃO DE DADOS EM SISTEMAS EMBARCADOS DE BAIXO CUSTO Autor(es): Duarte, Athos Ferreira Primeiro Orientador: Silva, Alexandre Carvalho Abstract: This study addresses the development of an Internet of Things (IoT)-based system for continuous monitoring of environmental variables, focusing on applications for controlled environments, such as agricultural greenhouses, considering cost constraints and hardware limitations. The research is motivated by the challenge of implementing accessible solutions capable of integrating sensing, communication, and data processing efficiently in resource-constrained environments. The main objective is to develop and evaluate a functional architecture capable of collecting, transmitting, and providing environmental data continuously. Methodologically, the study is classified as applied research, with a qualitative-quantitative approach, exploratory and descriptive objectives, and experimental procedures based on the construction of a functional prototype. The proposed solution integrates analog sensors, a Raspberry Pi-based gateway, MQTT communication protocol, and a cloud infrastructure for data storage and visualization. The results indicate that the system was able to maintain a continuous data flow with operational stability and low resource consumption, as well as significant improvements in transmission efficiency after optimization strategies were implemented. It is concluded that the proposed architecture is viable in controlled environments, although it presents limitations related to scalability, sensor accuracy, and the need for adjustments for large-scale applications. Editor: Instituto Federal Goiano Tipo: Trabalho de Conclusão de Curso Thu, 20 Aug 2026 00:00:00 GMT https://repositorio.ifgoiano.edu.br/handle/prefix/6947 2026-08-20T00:00:00Z https://repositorio.ifgoiano.edu.br/handle/prefix/6870 Título: SUPERANDO O DESAFIO PEDAGÓGICO NO ENSINO DE PO: DESENVOLVIMENTO DE UM LABORATÓRIO DIGITAL PARA O MÉTODO SIMPLEX E BRANCH-AND-BOUND Autor(es): Lima, Marcos Winicyus Borges Primeiro Orientador: Belo Filho, Marcio Antonio Ferreira Primeiro Membro da Banca: Ribeiro, André da Cunha Segundo Membro da Banca: Silva, Marlus Dias Abstract: Operational Research (OR) is a fundamental discipline for the computer science field, but its teaching faces significant pedagogical barriers. Central algorithms, such as the Simplex Method and Branch-and-Bound (B&B), are abstract, and students often fail to connect the mechanical execution of the algorithms (algebra) with the conceptual intuition (ge- ometry) that underpins them. Existing educational tools, like SIMO, although relevant, present critical limitations: they operate on client-side architectures, impose a barrier to entry by requiring the manual insertion of problems in matrix form, and promote passive engagement (Level 2, Viewing). This work proposes the development of an interactive, open-source web-based educational tool to assist in the teaching and learning of the Sim- plex Method and Branch-and-Bound. The solution addresses the identified gaps through three central innovations: (1) Technological Innovation, with a modern server-side archi- tecture using Python and Streamlit, which decouples the computational logic from the interface; (2) Pedagogical Innovation, through the implementation of a Library of Edita- ble Classic Problems that fosters Inquiry-Based Learning (IBL); and (3) Visual-Analytical Integration, which synchronizes the algebraic execution of the tableau with the geometric visualization of the feasible region in 2D and 3D. Additionally, the system incorporates Post-Optimization Analysis tools, automatically generating the Dual Problem and Sensi- tivity Analysis reports. This approach provides the necessary resources to foster student engagement at Level 4 (Changing) of Naps’ taxonomy, overcoming the modeling barrier to entry and enabling a holistic understanding of optimization problems. Editor: Instituto Federal Goiano Tipo: Trabalho de Conclusão de Curso Wed, 17 Jun 2026 00:00:00 GMT https://repositorio.ifgoiano.edu.br/handle/prefix/6870 2026-06-17T00:00:00Z https://repositorio.ifgoiano.edu.br/handle/prefix/6788 Título: PROCESSO DE ADEQUAÇÃO DO SITE DO MERCADO LIVRE  À LEI GERAL DE PROTEÇÃO DE DADOS PESSOAIS (LGPD) Autor(es): Guimarães, Luiz Sérgio Costa Primeiro Orientador: França, Heyde Francielle do Carmo Abstract: The Brazilian General Data Protection Law (LGPD) established guidelines for the processing of personal data in Brazil, requiring organizations to adopt measures that ensure privacy, information security, and the protection of data subjects' rights. In this context, this study aimed to analyze the process of adapting Mercado Livre's website to the requirements of the LGPD, identifying the main practices implemented, the challenges encountered, and their impacts on legal compliance and user experience. The research is characterized as qualitative, exploratory, and descriptive, based on bibliographic and documentary research, a case study, and field research conducted with companies located in the region of Acreúna, Goiás, Brazil. The analysis addressed aspects such as privacy policies, cookie management, consent mechanisms, information security, data subjects' rights, and data governance. The results indicate that Mercado Livre demonstrates a high level of compliance with the principles established by the LGPD through accessible privacy policies, consent management mechanisms, and investments in information security. On the other hand, the field research revealed that local companies still face significant challenges, including limited knowledge of the legislation, financial constraints, lack of specific tools, and technical difficulties in implementing compliance measures. It is concluded that compliance with the LGPD is a continuous process that requires investments in technology, governance, organizational training, and awareness, contributing to the protection of personal data, strengthening users' trust, and promoting responsible digital governance. Editor: Instituto Federal Goiano Tipo: Trabalho de Conclusão de Curso Mon, 29 Jun 2026 00:00:00 GMT https://repositorio.ifgoiano.edu.br/handle/prefix/6788 2026-06-29T00:00:00Z https://repositorio.ifgoiano.edu.br/handle/prefix/6784 Título: CLASSIFICAÇÃO DO NÍVEL DE MATURAÇÃO E CONTAGEM DE TOMATES COM REDES NEURAIS CONVOLUCIONAIS USANDO DADOS DE COLORIMETRIA Autor(es): Caetano, Guilherme Honório Primeiro Orientador: França, Heyde Francielle do Carmo Primeiro Membro da Banca: França, Heyde Francielle do Carmo Segundo Membro da Banca: Silva, Fábia Barbosa da Terceiro Membro da Banca: Costa, Adriano Ferraz da Abstract: Tomato maturity classification is an important task in precision agriculture and is traditionally performed manually and subjectively. This work presents an approach that combines colorimetric measurements in the CIELAB color space with YOLO models for automatic tomato detection, counting, and classification into green, intermediary, and red classes. A dataset containing 1,040 images and 8,748 annotated fruits was built, with maturity classes defined from measurements obtained from 150 samples and grouped using the K-means algorithm. YOLOv10, YOLO11, YOLO12, and YOLO26 models, in both Small and Medium variants, were evaluated, achieving precision values above 95%, recall above 94%, and mAP@0.5 up to 97.5%. YOLO26m achieved the best overall performance. The trained models were integrated into a web application developed using Streamlit for image and video processing. The results highlight the potential of combining colorimetry and deep learning techniques for automated tomato maturity monitoring. Editor: Instituto Federal Goiano Tipo: Trabalho de Conclusão de Curso Mon, 22 Jun 2026 00:00:00 GMT https://repositorio.ifgoiano.edu.br/handle/prefix/6784 2026-06-22T00:00:00Z