Monografia_Cont_Automação
URI permanente para esta coleçãohttps://ri.ifam.edu.br/handle/4321/972
Navegar
5 resultados
Resultados da Pesquisa
Item Uso de redes neurais para identificação de embarcações(2024-09-23) Pedroso, Ytalo Ribeiro da Silva; Santos, Alyson de Jesus dos Santos; http://lattes.cnpq.br/5998752909180697; Santos, Alyson de Jesus dos; http://lattes.cnpq.br/5998752909180697; Souza, Daniel Fonseca de; http://lattes.cnpq.br/4043793492782488; Rodrigues, Marlos André Silva; http://lattes.cnpq.br/0650250324042531Due toitsuniquegeography,theriversoftheAmazonplayasignificant roleinthedailylife of theregion,includingbeingtheonlyaccessinmoreremotecommunities,andthelackof infrastructure inmuchofthiswaterwaynetworkmakesitconducivetothetransportofillegal goods duetothelackofsupervision. When comparedtourbanareas,itispossibletonoticethepotentialforpositiveassistanceto local authoritiesthroughtheuseofrecognitiontechnologies,butthelackofcommunication structures hinderstheimplementationofthesetechnologiesinthesamewayitisdoneincities. This projectproposesthedevelopmentofaneuralnetworkapplicationaimedatassistingin public securityissuesthroughthedetectionofvesselsinportregionslocatedintheStateof Amazonas, combiningArtificial IntelligencetechniquesandEmbeddedSystemsdevices,without the useofnetworkdatatransmission.Themethodologyconsistsof:(a)Acquisitionofvessel images atMarinadoDaviandtheportofManausModerna-StateofAmazonas;(b)Preparation of thedatasetintheexpectedformatforthemodel;(c)Installation,configuration, anduseofthe Jetson NanoBoardintrainingtheNeuralNetwork;(d)UseofTransferLearning,leveraginga pre-trained model(YOLOv4Tiny)formodelgenerationonthenewdataset;(e)Validationofthe obtained results. The resultsshowthatwiththeuseofversionsoptimizedforembeddeddevices,itwaspossible to executetheYOLOv4Tinyalgorithm,performingtheclassification ofvesselsandcontributing with newvesselimages,whichprovidegreaterregionalitytothepresenteddata.Item Prevenção contra deepfakes: desenvolvimento de um sistema de reconhecimento facial para diferenciar rostos humanos de rostos gerados por IA(2024-03-19) Silva, Romão Charles Silva e; Santos, Alyson de Jesus dos Santos; http://lattes.cnpq.br/5998752909180697; Santos, Alyson de Jesus dos; http://lattes.cnpq.br/5998752909180697; Martins, Gilbert Breves; http://lattes.cnpq.br/4932200790121123; Rodrigues, Marlos André Silva; http://lattes.cnpq.br/0682962508867807This work aims to develop a system based on machine learning that differentiates images of people generated by artificial intelligence from real people, a capability that can be very useful for identifying scams that use generated images. The development of the project was done in 3 main steps: data organization, training and testing. The system was entirely made in Google Colab, therefore, it used Python and the main development tool Tensorflow, two models were trained, one of which has almost twice as many images used for training, with the intention of observing the consequences of using a larger set. At the end of the project, the quantitative and qualitative results of the image classification are shown.Item Detecção de anomalias médicas no pulmão usando técnicas de inteligência artificial(2023-12-22) Silva, Rafael Reinaldo; Santos, Alyson de Jesus dos; Alyson de Jesus dos Santos; Santos, Alyson de Jesus dos; http://lattes.cnpq.br/5998752909180697; Santos, Lucélia Cunha da Rocha; Fialho, Michaella Socorro Bruce; http://lattes.cnpq.br/9348859124436505; SilvaArtificial Intelligence (AI) is not a contemporary concept, and its presence is not alien to society; currently, numerous applications employ this knowledge. However, despite the growing incorporation of technology in various contexts and increasingly in everyday life, a significant portion of the population still views technological intervention with reservations. In the medical field, it is no different; there is concern about the replacement of healthcare professionals by intelligent machines. Those who think so are mistaken; currently, AI is already involved in various aspects, such as disease prognosis, image understanding, interconnection of prescription databases, among others, and yet there is still a need for human presence. However, such advances do not spread uniformly; there will still be many gaps in the democratization of the application of this resource, whether due to a lack of technology, training, or even distances. In the latter case, it is more common in Brazil, which has continental extensions. According to the World Health Organization (WHO), in the last decade, two of the four leading causes of death in the world are related to respiratory diseases. In Brazil, according to the Ministry of Health, in the first nine months of 2022, there were more than 40,000 deaths from pneumonia alone. This work aims to compare machine learning algorithm models to present the pros and cons of each. Neural networks were used to check a dataset of images for training, validation, and testing of models with the purpose of recognizing and diagnosing cases of pneumonia through only X-ray examinations.Item Sistema de detecção de capacete baseado em inteligência artificial(2023-03-24) Ramos, Arthur Cabral; Santos, Alyson de Jesus dos; http://lattes.cnpq.br/5998752909180697; Santos, Alyson de Jesus dos; http://lattes.cnpq.br/5998752909180697; Costa, Jaidson Brandão da; http://lattes.cnpq.br/4553321582341998; Compto, Gabriel Pinheiro; http://lattes.cnpq.br/5432787843953143This work aims to develop a system based on machine learning that controls access to areas where the use of helmets as personal protective equipment is mandatory. The project was developed is three main stages: data selection, training and testing. The project used low-cost hardware and free software. The developed system used Python as a programming language in all stages and TensorFlow as the main tool. The operation occurs through a code written in Python that evaluates whether the use of the helmet is being carried out, if the answer is positive, it triggers a device that grants access, in the project the device is represented by an LED.Item Análise comparativa de algoritmos de reconhecimento facial(2023-02-17) Ricardo, Misael Marques; Santos, Alyson de Jesus dos; http://lattes.cnpq.br/5998752909180697; Santos, Alyson de Jesus dos; http://lattes.cnpq.br/5998752909180697; Costa, Jaidson Brandão da; http://lattes.cnpq.br/4553321582341998; Compto, Gabriel Pinheiro; http://lattes.cnpq.br/5432787843953143THE PURPOSE OF THIS PAPER IS TO CARRY OUT A STUDY ON THE OPERATION OF FACE RECOGNITION ALGORITHMS DESCRIBED IN THE LITERATURE. THREE OF THE FACIAL RECOGNITION ALGORITHMS DESCRIBED IN THE LITERATURE WERE USED AND A TEST SET IS PROPOSED IN ORDER TO EVALUATE THE RESULT AND VERIFY THE POSSIBILITY OF USING THE ALGORITHM IN AN ACCESS CONTROL SYSTEM TO PHYSICAL SPACES. THE EIGENFACES, FISHERFACES AND LBPH ALGORITHMS WERE USED. TO THE TESTS THREE DATABASES WERE USED: THE FIRST WAS CONSTITUTED WITH PHOTOS OF THE AUTHOR AND HIS FAMILY, THE SECOND WAS THE DATABASE OF PEOPLE WITH AND WITHOUT MASKS AND LASTLY THE DATABASE CONSISTED OF PEOPLE WITH AND WITHOUT GLASSES AND THE RESULTS THE ACCURACY OF RECOGNITION WERE REPORTED AND PRESENTED IN THIS PAPER.