https://repositorio.ifg.edu.br/handle/prefix/2499 2026-09-21T11:54:03Z 2026-09-21T11:54:03Z Morais, Felipe Antonio Estacio de Honorato, Luis Fernando Ribeiro Mendes, Pedro Gabriel Cunha https://repositorio.ifg.edu.br/handle/prefix/2532 2025-12-17T11:51:23Z 2025-09-24T00:00:00Z

Título: Ferramenta para a criação automatizada de frases com base na análise de emoções e reconhecimento da expressão facial Autor(es): Morais, Felipe Antonio Estacio de; Honorato, Luis Fernando Ribeiro; Mendes, Pedro Gabriel Cunha Primeiro Orientador: Lima, Ricardo Rodrigues Dias de Abstract: This work presents the development of a tool that automates the creation of sentences based on sentiment analysis and facial expression recognition. The proposed solution integrates Computer Vision and Natural Language Processing (NLP) techniques, using deep neural network algorithms to identify emotions in facial images and then generate coherent and contextually appropriate texts. For implementation, public image and sentence databases were used, allowing the training and validation of the models employed. The results demonstrated that the tool is capable of recognizing emotions with a good level of accuracy and producing sentences with semantic consistency and contextual relevance. In addition, the research highlights the challenges related to data quality and diversity, as well as ethical issues in the use of facial and emotional biometric information. The study contributes to the advancement of applications that combine artificial intelligence and digital content automation, offering an innovative solution for personal and corporate contexts. Editor: Insitituto Federal de Educação, Ciência e Tecnologia de Goiás Tipo: Trabalho de Conclusão de Curso

2025-09-24T00:00:00Z Campos, João Vitor https://repositorio.ifg.edu.br/handle/prefix/2531 2025-12-17T11:02:24Z 2025-09-09T00:00:00Z

Título: Método para a identificação de gestos de mão usando wi-fi sensing e aprendizado de máquina Autor(es): Campos, João Vitor Primeiro Orientador: Lopes, Victor Hugo Lazaro 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 regarding cost, privacy, and line-of-sight requirements. This work explores WiFi Sensing as a robust and non-invasive alternative, utilizing 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 classifying gestures 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 a benchmark in a complex environment, and the second with a custom dataset collected in a controlled environment to isolate hand gestures. The data processing evolved from an initial approach that treated each signal subcarrier independently to a final methodology that aggregates the entire gesture capture into a single feature vector, preserving the correlation between channels. Model optimization was performed with the Optuna framework, which allowed not only for the search of optimal hyperparameters but also for 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 at 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

2025-09-09T00:00:00Z Lopes, Victor Hugo Lazaro https://repositorio.ifg.edu.br/handle/prefix/2503 2025-12-01T15:00:27Z 2025-09-04T00:00:00Z

Título: Sistema para detecção de pessoas usando sinal do WiFi para ambientes internos Autor(es): Lopes, Victor Hugo Lazaro Primeiro Orientador: Lopes, Victor Hugo Lazaro Abstract: Detecting people has various applications across multiple sectors. Imagine a smart home that adjusts lighting, heating, and air conditioning based on the number of occupants in a room. Shopping centers can analyze customer behavior by tracking how many people visit specific areas and how long they stay. As an alternative to traditional detection methods, techniques based on radio frequency (RF) have emerged. However, some require individuals to carry active devices that emit RF signals, which can be inconvenient. Others involve the deployment of dedicated wireless sensor networks, which are expensive and difficult to maintain. Fortunately, the widespread presence of WiFi networks in homes and offices offers a new approach. WiFi signals propagate throughout the environment, reflecting and scattering off objects and people. This inherent interaction carries information about the surroundings and their occupants, incorporating relevant data on geometry and electromagnetic characteristics that can be leveraged for sensing purposes. This is possible because WiFi communication involves dynamic signal adjustments and transmission/reception methods through metrics obtained from the Channel State Information (CSI), which captures characteristics of the communication channel. WiFi Sensing has gained significant attention from both the scientific community and industry in recent years, mainly due to its strong potential for extracting information about indoor environments without relying on physical sensors or additional technologies. In this context, the present undergraduate thesis focused on leveraging WiFi signals for human detection. A new method was proposed for detecting people in indoor environments using WiFi signals and CSI-derived information, combined with supervised machine learning techniques, without requiring additional sensors or wearable devices. Validations were conducted using both a publicly available dataset widely used in the literature and a custom dataset built in controlled environments, using ESP32 prototyping boards with the ESP32 CSI Tool project. The results demonstrated the feasibility of the proposed method, achieving accuracies above 97% in the best evaluated scenarios. Editor: Insitituto Federal de Educação, Ciência e Tecnologia de Goiás Tipo: Trabalho de Conclusão de Curso

2025-09-04T00:00:00Z