https://repositorio.ifg.edu.br/handle/prefix/90 2026-09-13T21:35:06Z 2026-09-13T21:35:06Z Campos, João Vitor Aguiar, Max Lobo Magalhães de https://repositorio.ifg.edu.br/handle/prefix/2473 2025-11-19T17:33:31Z 2025-09-12T00:00:00Z

Título: Método para a identificação de gestos de mão usando Wi-Fi sensing e aprendizado de máquina Autor(es): Campos, João Vitor; Aguiar, Max Lobo Magalhães de Primeiro Orientador: Lopes, Victor Hugo Lázaro Abstract: Human-Computer Interaction (HCI) seeks increasingly intuitive interfaces, and hand gesture recognition is a promising field for this evolution. Traditional approaches, such as those based on computer vision or specialized hardware, present limitations in cost, privacy, and technical dependencies such as line of sight. This work explores WiFi Sensing as a robust and non-invasive alternative, using disturbances in Wi-Fi signals, known as Channel State Information (CSI), to classify gestures. The central hypothesis is that machine learning models can achieve high accuracy in gesture classification from CSI data. To validate this hypothesis, a proof of concept was developed with an evolutionary methodology, structured in two experimental scenarios: the first, using a public dataset to establish statistics in a complex environment, and the second, with a proprietary dataset collected in a controlled environment to isolate hand gestures. Data processing evolved from an initial approach that treated each signal subcarrier in isolation to a final methodology that aggregates the entire gesture capture into a single feature vector, preserving the correlation between channels. Model optimization was performed using the Optuna framework, which allowed not only the search for optimized hyperparameters but also an in-depth analysis of the computational cost (Work Effort) of each model. The results demonstrated the superiority of the aggregated capture approach. In the controlled scenario, the SGDClassifier model achieved the highest accuracy, with 88.14%, also standing out for its exceptional computational efficiency, with the lowest optimization cost and the fastest convergence. This work concludes that WiFi Sensing, combined with machine learning pipelines and intelligent optimization, is a viable and effective solution for gesture recognition, offering a positive balance between accuracy, cost, and respect for privacy. Editor: Insitituto Federal de Educação, Ciência e Tecnologia de Goiás Tipo: Trabalho de Conclusão de Curso

2025-09-12T00:00:00Z Silva, Arthur Dias Garcia da Silva, Aristeu Dias Garcia da Silva, Heithor Urquiza https://repositorio.ifg.edu.br/handle/prefix/2472 2025-11-19T17:32:13Z 2025-09-08T00:00:00Z

Título: Construção de um diretório de dados sobre anúncios em marketplaces: estudo de caso com o Mercado Livre Autor(es): Silva, Arthur Dias Garcia da; Silva, Aristeu Dias Garcia da; Silva, Heithor Urquiza Primeiro Orientador: Faria, Kenyo Abadio Crosara Abstract: This work presents the development of a comprehensive data directory on marketplace advertisements, using Mercado Libre as a case study. The research employs an exploratory methodology that combines web scraping techniques, heterogeneous data processing, and systematic structuring to overcome the challenges inherent in extracting information from e-commerce platforms. The developed system integrates automated data collection processes, transformation and normalization of structured and unstructured information, and implementation of analytical visualizations for identifying business patterns. Using MongoDB as a storage solution, the proposed architecture demonstrates the feasibility of transforming scattered marketplace data into structured information that enables the identification of market trends and strategic business insights. The results highlight the effectiveness of the proposed methodology in building commercial data repositories, contributing to the field of data analysis in e-commerce and providing a replicable methodological basis for similar studies in different marketplace contexts. Editor: Insitituto Federal de Educação, Ciência e Tecnologia de Goiás Tipo: Trabalho de Conclusão de Curso

2025-09-08T00:00:00Z Ribeiro, Pedro Antonio de Araújo Silva, Rodrigo Eduardo da https://repositorio.ifg.edu.br/handle/prefix/2471 2025-11-19T17:31:21Z 2025-08-27T00:00:00Z

Título: Sistema de Gerenciamento de Vagas e Estágios (SGVE) Autor(es): Ribeiro, Pedro Antonio de Araújo; Silva, Rodrigo Eduardo da Primeiro Orientador: Lima, Ricardo Rodrigues de Abstract: The FAMI-Company Integration web system for Internship Management and Job Offers aims to improve communication between the Inhumense Child Support Institution (FAMI) and partner companies, aiming to optimize the internship management process and the availability of opportunities for students. This project proposes the development of a platform that allows the registration of companies and internship profiles, as well as the registration of students with their respective skills. The platform will include a recommendation system, which will connect students to opportunities according to their qualifications. To increase the accuracy of the recommendations, clustering methods will be applied to group students with similar characteristics and suggest profiles more aligned with the requirements of the vacancies. It is estimated that this approach will simplify and make the internship management process more efficient, promoting greater transparency for the educational institution and partner companies. Editor: Insitituto Federal de Educação, Ciência e Tecnologia de Goiás Tipo: Trabalho de Conclusão de Curso

2025-08-27T00:00:00Z Sampaio, Wesley da Silva Monteiro, Joel de Paula https://repositorio.ifg.edu.br/handle/prefix/2085 2024-11-01T10:13:11Z 2024-09-11T00:00:00Z

Título: Desenvolvimento de um sistema de integração escola-empresa para gerenciamento de estágios Autor(es): Sampaio, Wesley da Silva; Monteiro, Joel de Paula Primeiro Orientador: Lima, Ricardo Rodrigues Dias de Abstract: The School-Company Integration web system for Internship Management and job offers is a technological solution that aims to facilitate communication between educational institutions and companies, with regard to internship management and job offers for students. This work aims to offer a platform for registering and managing companies, internship vacancies and students, with the generation of reports based on database queries using natural language. This way, it is possible to obtain relevant information about companies, vacancies and students, such as contact details, history of internships completed, technical and behavioral skills, among others. In addition to proposing the implementation of this web system with this functionality of generating reports using natural language. With this solution, it is possible to speed up and simplify the entire process of managing internships and offering vacancies, providing greater efficiency and transparency for educational institutions and companies. Furthermore, the possibility of generating personalized reports contributes to a more accurate and objective analysis of information, which can assist in making strategic decisions. Editor: Insitituto Federal de Educação, Ciência e Tecnologia de Goiás Tipo: Trabalho de Conclusão de Curso

2024-09-11T00:00:00Z