EST - Trabalho de Conclusão de Curso Graduação
URI permanente para esta coleçãohttps://ri.uea.edu.br/handle/riuea/4795
Navegar
22 resultados
Resultados da Pesquisa
Item Desenvolvimento de um software para auxiliar o aprendizado de conceitos e aplicações abordados na disciplina de processamento digital de imagens.(Universidade do Estado do Amazonas, 2023-08-31) Campos, João Vitor Da Silva; Oliveira, Jozias Parente de; Oliveira, Jozias Parente de; Figueiredo, Ingrid Sammyne Gadelha; Pantoja, Antônio Luiz AlencarThe work presents the development of a software for learning concepts of the discipline of digital image processing, bringing in assistant professors who teach these subjects and exemplifying in a practical way the techniques taught in the classroom, facilitating and contributing to the understanding by the student. . The techniques developed in the tool are the limits of where the image is binarized from a pixel intensity value, changing the brightness and contrast in the image with visualization of their respective histograms, applications of low pass filters with Gaussian and average filters that allow smoothing the image with noise like salt and pepper, applying high pass filters with edge detection by the Canny and Sobel operators, and finally the visualization of RGB and YCbCr color spaces and in grayscale. To validate the results and the functioning of the tool, a satisfaction survey was carried out with students who attended or attended the PDI subject using the average ranking calculation.Item Classificação de cenas aéreas em sensoriamento remoto: Uma abordagem utilizando dados de imagem e som e self-supervised learning(Universidade do Estado do Amazonas, 2024-02-08) Ayres, Talissa Moura; Figueiredo, Carlos Maurício Serodio; Figueiredo, Carlos Maurício Serodio; Pantoja, Antônio Luiz Alencar; Cardoso, Fábio de SousaScene classification is an activity in computer vision where models can understand a context or environment without focusing solely on classifying a single object, as in image classification. Therefore, it is an area of extensive research currently, as it is used in important tasks such as content-based retrieval and smart content moderation. Additionally, when performed with remote sensing data, it is crucial for understanding the environment around us, being applied in tasks such as city monitoring and land use classification. Emphasizing the classification of aerial scenes, many of these studies are based on using convolutional neural networks for this activity, thus relying on a large number of annotations for images. Hence, the application of new training techniques such as self-supervised learning (SSL), where the model first learns to generate representations from pseudolabels before performing the main task, has been more widely applied in recent literature. Furthermore, the possibility of using multimodal data with geolocated images and sounds to improve model performance in this task has been demonstrated through the ADVANCE and SoundingEarth datasets. Therefore, this paper demonstrates the use of SSL and audiovisual remote sensing data in conjunction with the application of vision transformers, a new deep learning architecture based on attention mechanisms, for generating embeddings. Firstly, pre-training was conducted on SoundingEarth, using batch triplet loss to bring closer pairs of positive image and sound data and separate distinct pairs. Subsequently, these representations were applied to a logistic regression model to classify aerial scenes from ADVANCE. The results obtained showed precision, recall, and F1-Score above 80% for models trained with both image and sound embeddings. Considering only image embeddings, results were also above 80%, and considering only audio, results were above 40% for these metrics.Item Desenvolvimento de um sistema de telemetria para monitoramento de qualidade de água em rios amazônicos(Universidade do Estado do Amazonas, 2023-09-01) Silva, Rubem Silas Dias; Fernandes, Rubens de Andrade; Fernandes, Rubens de Andrade; Torné, Israel Gondres; Oliveira, Jozias Parente deThe present work presents the development of a telemetry system for water quality indicators. The purpose is to enable remote, periodic, and self-sustaining monitoring of chemical and biological parameters in Amazonian rivers through precise sensors over long distances. The implementation of the proposed research began with the modeling of a microcontrolled hardware device designed for low energy consumption, featuring energy harvesting, battery backup, LoRa connectivity, and support for reading laboratory water quality measurement sensors. In addition to the envisioned hardware system, the developed firmware was designed to efficiently coordinate sensor activation, peripheral devices, and LoRa radio communication, as well as establish communication via the LoRaWAN protocol with a web application for displaying water quality information. With the implementation of the proposed telemetry device, it is expected to assess the system’s autonomy in remote locations and compare the measurements taken by the device with those recorded by the research group at the LabRios laboratory, located at the Center for Higher Studies in Parintins. This will ultimately test the viability of the developed solution as a valid tool for monitoring river parameters.Item Aplicação de técnicas de deep learning para autenticação de usuários através do reconhecimento facial em notebooks(Universidade do Estado do Amazonas, 2023-09-01) Silva, Monique Sousa; Oliveira, Jozias Parente de; Oliveira, Jozias Parente de; Fernandes, Rubens de Andrade; Pantoja, Antônio Luiz AlencarThe present work aims to apply techniques of digital image processing and neural networks to authenticate and unlock notebooks. For this, knowledge of the Viola-Jones algorithm was used on this project, which applies Haar's rectangular features to make complex images simpler for analysis, and of the Adaptive Boosting Algorithm, to classify the weight of the features identified in the images. A deep learning approach associated with artificial neural networks was also conducted to reinforce the correct identification of the faces used to verify the system, and to better understand the operation behind the manipulation of the digital image signal for its analysis. For validation and testing of the system, a dataset of 700 publicly available images from 50 distinct users was employed, utilizing evaluation metrics such as accuracy, precision, sensitivity, specificity, and F-score. According to the results, a minimum accuracy of 98,6% and a maximum of 100% were achieved, along with a minimum precision of 62,5% and a maximum of 100%. Sensitivity ranged from a minimum of 50% to a maximum of 100%, specificity ranged from a minimum of 98,5% to a maximum of 100%, and F-score ranged from a minimum of 66,7% to a maximum of 100%Item Desenvolvimento de um gateway configurável para conversão de dados de equipamentos modbus de subestação de média tensão(Universidade do Estado do Amazonas, 2024-02-19) Oshima, Abraão dos Reis; Azevedo, Cláudio Gonçalves de; Azevedo, Cláudio Gonçalves de; Río, Daniel Guzmán del; Torné, Israel GondresSubstation automation is essential to ensure the efficient and safe operation of the electrical system, in addition, obtaining and analyzing accurate and real-time data from substations is essential for strategic decision-making. A configurable gateway will allow access and efficient conversion of ModBus equipment data, providing valuable information for operators and engineers in the management and maintenance of the electrical system. This work is based on the IEC 61850 and IEC 60870-5 standards, in which the IEC 61850 aims to establish standards for communication and automation of electrical power systems, defining a set of communication protocols, often used in substations for communication between devices and systems. The IEC 60870- 5 standard aims to specify the communication protocols for supervision and control systems in substations in general, which is used for data acquisition and remote control of substation equipment. Part 101 of the IEC 60870-5 standard provides detailed guidelines on how the ModBus protocol should be implemented to ensure reliable and efficient communication in substations. It describes message formats, the structure of data packets, transmission modes, error detection and correction methods, and other relevant technical.Item Desenvolvimento de um gateway configurável para conversão de dados de equipamentos modbus de subestação de média tensão(Universidade do Estado do Amazonas, 2024-02-19) Oshima, Abraão dos Reis; Azevedo, Cláudio Gonçalves de; Azevedo, Cláudio Gonçalves de; Río, Daniel Guzmán del; Torné, Israel GondresSubstation automation is essential to ensure the efficient and safe operation of the electrical system, in addition, obtaining and analyzing accurate and real-time data from substations is essential for strategic decision-making. A configurable gateway will allow access and efficient conversion of ModBus equipment data, providing valuable information for operators and engineers in the management and maintenance of the electrical system. This work is based on the IEC 61850 and IEC 60870-5 standards, in which the IEC 61850 aims to establish standards for communication and automation of electrical power systems, defining a set of communication protocols, often used in substations for communication between devices and systems. The IEC 60870- 5 standard aims to specify the communication protocols for supervision and control systems in substations in general, which is used for data acquisition and remote control of substation equipment. Part 101 of the IEC 60870-5 standard provides detailed guidelines on how the ModBus protocol should be implemented to ensure reliable and efficient communication in substations. It describes message formats, the structure of data packets, transmission modes, error detection and correction methods, and other relevant technical.Item Sistema de inspeção de etiquetas por visão computacional e aprendizado profundo na indústria 4.0(Universidade do Estado do Amazonas, 2023-04-03) Camelo, Leonardo Yuto Suzuki; Figueiredo, Carlos Maurício Serodio; Figueiredo, Carlos Maurício Serodio; Oliveira, Jozias Parente de; Fernandes, Rubens de AndradeProduct inspection is an essential step in manufacturing processes to ensure the quality of the final product. Traditionally, this inspection has been done manually by human operators, which is time-consuming, expensive, and can lead to errors due to human subjectivity and fatigue. In recent years, most visual processes in a factory are being replaced by computer vision techniques. With the advances in deep learning approaches, optical character recognition and object recognition are technologies that can be used in different scenarios. In this study, a methodology capable of extracting textual and non-textual information applied to modem labels is developed. The proposed method consists of the following components: two object detectors that perform label detection and simultaneous QR code and barcode detection, both using YOLOv5; a content decoder for QR code and barcode using Zbar; an OCR system using PaddleOCR; and a set of rules applied to post-processing of the information. To do this, three datasets were created: the first containing images of modem labels to train the label detection model, the second containing a mixture of label images and various environments containing QR code and barcode to generate the QR code and barcode detection model, and a ground-truth base containing modem label images with their expected system outputs. The proposed system was evaluated with different label models, and its execution was done on a CPU. The label readings achieved average values of 0.21% Character Error Rate, 2.16% Field Error Rate, Label Accuracy of 76.19%, and execution time of 2.79 seconds for the first model, and 0.04% Character Error Rate, 0.62% Field Error Rate, Label Accuracy of 92.50%, and execution time of 1.73 seconds. Experimental results show that the developed solution can be used in production with high accuracy rates and significantly better execution time than a human operator.Item Prima: uma ferramenta para automação de revisão de testes aplicada a plataforma android mobile(Universidade do Estado do Amazonas, 2023-03-16) Sahdo, Klirssia Matos Isaac; Oliveira, Jozias Parente de; Oliveira, Jozias Parente de; Cardoso, Fábio de Sousa; Monteiro, Bruno da GamaWith the advances of technology, software development is becoming increasingly complex, and the need to test an embedded product with it has become a fundamental factor to avoid failures and fix errors. This factor has great relevance in Android mobile devices, which have complex software and a wide variety of models on the market. In order to ensure quality for consumers, companies are investing in standards and creating rules, as is the case with Google, which provides a series of requirements for homologation of its products on Android devices. Tests related to the homologation of these electronic devices for these regulations generate a large amount of test artifacts at the end of the process, which becomes challenging for pure manual review by the testing developer. Thus, the objective of this thesis is to propose and evaluate an automation tool called PRIMA, to improve quality assurance in Android mobile device testing. To analyze and verify the proposed tool, an experiment was conducted in a real test environment in a particular company in the field, in order to obtain sufficient data for analysis of the scenario. With the results obtained, it was possible to understand that there was a 59% improvement in preventing failures using the test review automation. This result indicates that PRIMA can help prevent failures found at the end of the Android releases homologation process.Item Predição de classes sociais com modelos de aprendizado profundo a partir de imagens de satelité e dados de renda do censo(Universidade do Estado do Amazonas, 2023-03-27) Begnini, Ana Clara; Figueiredo, Carlos Maurício Serodio; Figueiredo, Carlos Maurício Serodio; Pantoja, Antônio Luiz Alencar; Oliveira, Jozias Parente deSocioeconomic surveys that collect information on the income or economic situation of families in the Brazilian territory are costly surveys that demand time to be carried out, for example, the Brazilian Demographic Census is carried out every 10 years, at least, which can make the formulations of inefficient public policies since, in recent years, significant population growth in cities has been notorious. However, the present work has the objective of studying and analyzing the possibility of classifying the areas of the cities of Manaus (AM) and S˜ao Paulo (SP) according to social classes through deep learning models with satellite images of the cities and data from the last available Population Census. For this, satellite images of each city were collected and, based on income data from the 2010 Census, classified into social classes A, B, C, D, and E, with this, Computational Vision models were trained for classification problems with the EfficientNetV2 architecture using the transfer learning technique for training. Finally, it obtained 16 deep learning models, 8 from the city of Manaus and 8 from the city of S˜ao Paulo, however, the 2 best models from Manaus obtained the F1-Score of 0.66 for Model 1 and 0.48 for Model 2, while the 2 best models from S˜ao Paulo obtained F1-Score results of 0.53 for Model 1 and 0.58 for Model 2.Item Elaboração de ambientes virtuais para auxiliar a automação de práticas laboratoriais de sistemas de controle em engenharia elétrica e eletrônica(Universidade do Estado do Amazonas, 2023-03-23) Pimenta Junior, Edward Pinto; Río, Daniel Guzmán Del; Río, Daniel Guzmán Del; Pantoja, Antônio Luiz Alencar; Torné, Israel GondresDue to the non-existence of economic resources available in colleges and public or even private schools, or the lack of real instrumentation to carry out laboratory practices in a physical way, because of the high cost that equipment and components currently have, it was idealized that it is possible the realization and elaboration of virtual environments using MATLAB, to deliver a solution for the absence or difficulties in the execution of laboratory practices, and to have a learning, simulation and automation tool, adequate for the acquisition of the skills and experiences required in the course of Electrical Engineering, Electronics, in relation to control systems, which is the focus area of the project. In addition, it will be possible to break down the barriers that distance learning can create in laboratory practices
- «
- 1 (current)
- 2
- 3
- »