Navegando por Assunto "Redes neurais"

Agora exibindo 1 - 4 de 4

Acesso aberto (Open Access)
Beam-selection otimizado por aprendizado de máquina : uma abordagem multimodal
(Universidade Federal do Pará, 2023-12-30) FERREIRA, Jamelly Freitas; GOMES, Diego de Azevedo; http://lattes.cnpq.br/5116561408505726; KLAUTAU JÚNIOR, Aldebaro Barreto da Rocha; http://lattes.cnpq.br/1596629769697284
This dissertation aims to investigate the use of machine learning models using multimodal data as input to optimize the Beam-Selection process in millimeter-wave based networks. The use of Deep Learning has intensified in different areas, and it is possible to obtaing performance equal or superior to human performance, so its use is also promising in wireless communication scenarios. This work used data from different sources, which proved to be convenient since it is possible to adjust the model according to the quality/availability of this data. After executing the experiments and obtaining the results, it was observed that it is possible to obtain significant performance in different metrics even with simpler data such as image and coordinate.
Acesso aberto (Open Access)
Uma estratégia baseada em rede neural de base radial aplicada ao gerenciamento da produção de petróleo e gás natural
(Universidade Federal do Pará, 2008-03-03) SILVA, Cleison Daniel; BARREIROS, José Augusto Lima; http://lattes.cnpq.br/1246564618922453; COSTA JÚNIOR, Carlos Tavares da; http://lattes.cnpq.br/6328549183075122
This work consists of a Neural Network for modeling the relationship between the well head surface variables and the multiphase flows of the test separator vessels in the East Urucu Field (LUC). In practice, this relationship is obtained when each producing unit is aligned to a test separator for production estimation. Data were obtained when the well is aligned to a test separator. Those data are used for training a Neural Network of Radial Basis Function (NN - RBF). The goal is to make the NN - RBF to recognize the patterns of the wel l head variables (input RBF) and the phases flow in the separator (out RBF), through using, as the training set, the patterns obtained during the production test previously executed.
Acesso aberto (Open Access)
Identificacao de larvas de mosquitos do genero aedes utilizando redes neurais convolucionais
(Universidade Federal do Pará, 2023-09-29) SILVA, Romário da Costa; FERREIRA JÚNIOR, José Jailton Henrique; http://lattes.cnpq.br/9031636126268760; FRANCÊS, Carlos Renato Lisboa
Arboviruses transmitted by mosquitoes of the Aedes genus constitute a threat to public health. Detection and control of these vectors are critical to preventing disease outbreaks including Dengue, Chikungunya, Zika and Yellow Fever. Computer vision and deep learning techniques have been increasingly used in epidemiological control, mainly with regard to the classification and detection of these mosquitoes. In this sense, three models are proposed for classification, detection and segmentation of mosquito larvae based on the use of convolutional neural networks (CNN) and object detection algorithms (YOLO). For this purpose, a dataset was created for training purposes. The dataset is composed of images of larvae, being categorized between Aedes and Non-Aedes classes. The results show that the proposed models are promising strategies and achieved accuracy values of 86.71%, mAP (Mean Average Precision) of 88.3% and 95.7% for the tasks of classification, detection and segmentation, respectively.
Acesso aberto (Open Access)
Sistema web de suporte a mobilidade multimodal em smart campus usando algoritmos baseados em inteligência artificial e análise estatística
(Universidade Federal do Pará, 2023-08-16) SILVA, Edinho do Nascimento da; ARAÚJO, Jasmine Priscyla Leite de; http://lattes.cnpq.br/4001747699670004
Urban mobility in a large city largely depends on public transport, which plays a vital role in facilitating the flow of citizens between different areas where a variety of goods and services, such as health and physical activities, are available. According to the UN, it is expected that more than 60% of the world’s population will live in urban areas by 2050, which increases the need to make the entire transport system more sustainable and energy efficient. For this, the transition from modes powered by fossil fuels to options powered by electricity is a watershed that will require the implementation of new infrastructure to provide electricity to future modes. Such installation of energy points, called points of electric recharge of electric modes, is a technical, economic and energetic challenge. To discuss this current and relevant topic, this paper presents the results obtained from the Amazon Multimodal Intelligent System Project (SIMA), developed in partnership between the company Norte Energia and the Federal University of Pará (UFPA), focusing on the implementation at UFPA’s Smart Campus in Belém. In possession of the implementation of the structure, this branch of the project, made use of the infrastructure project for the development of a software-based solution that serves as support in decision-making on the management of the energy efficiency of an intelligent environment, that is, a Smart Campus. In view of the above, this work has as its main focus the design and development of an energy efficiency management system that converts the data generated by electric modes in order to be useful in the management of the energy efficiency of the entire multimodal system. For this, several algorithms were implemented in the software, namely: linear regression, general regression neural network and moving average. From this work it is possible to conclude that the tool can be useful to help modal managers to achieve reductions in energy consumption, consequently, reducing operating costs and increasing equipment longevity, which will also impact capital costs.