Navegando por Assunto "Convolutional neural networks"

Agora exibindo 1 - 9 de 9

Acesso aberto (Open Access)
5G MIMO and LIDAR data for machine learning: mmWave beam-selection using deep learning
(Universidade Federal do Pará, 2019-08-29) DIAS, Marcus Vinicius de Oliveira; KLAUTAU JÚNIOR, Aldebaro Barreto da Rocha; http://lattes.cnpq.br/1596629769697284
Modern communication systems can exploit the increasing number of sensor data currently used in advanced equipment and reduce the overhead associated with link configuration. Also, the increasing complexity of networks suggests that machine learning (ML), such as deep neural networks, can effectively improve 5G technologies. The lack of large datasets make harder to investigate the application of deep learning in wireless communication. This work presents a simulation methodology (RayMobTime) that combines a vehicle traffic simulation (SUMO) with a ray-tracing simulator (Remcom’s Wireless InSite), to generate channels that represents realistic 5G scenarios, as well as the creation of LIDAR sensor data (via Blensor). The created dataset is utilized to investigate beam-selection techniques on vehicle-to-infrastructure using millimeter waves on different architectures, such as distributed architecture (usage of the information of only a selected vehicle, and processing of data on the vehicle) and centralized architectures (usage of all present information provided by the sensors in a given moment, processing at the base station). The results indicate that deep convolutional neural networks can be utilized to select beams under a top-M classification framework. It also shows that a distributed LIDAR-based architecture provides robust performance irrespective of car penetration rate, outperforming other architectures, as well as can be used to detect line-of-sight (LOS) with reasonable accuracy.
Acesso aberto (Open Access)
Uma Análise do uso de informacões multiescala no mapeamento da PSNR para pontuacão perceptual
(Universidade Federal do Pará, 2019-11-18) GONÇALVES, Luan Assis; ZAMPOLO, Ronaldo de Freitas; http://lattes.cnpq.br/9088524620828017; BARROS, Fabrício José Brito; http://lattes.cnpq.br/9758585938727609
The prediction of visual quality is crucial in image and video systems. For this task, image quality metrics based on the mean squared error prevail in the field, due to their mathematical straightforwardness, even though they do not correlate well with the visual human perception. Latest achievements in the area support that the use of convolutional neural networks (CNN) to assess perceptual visual quality is a clear trend. Results in other applications, like blur detection and de-raining, indicate the combination of information from different scales improves the CNN performance. However, to the best of our knowledge, the best way to embody multi-scale information in visual quality characterization is still an open issue. Thus, in this work, we investigate the influence of using multi-scale information to predict the perceptual image quality. Specifically, we propose a single-stream dense network that estimates a spatially-varying parameter of a logistic function used to map values of a objective visual quality metric to subjective visual quality scores through the reference image. The proposed method achieved a reduction of 36.37% and 69.45% for the number of parameters and floating-point operations per second, respectively, and its performance is compared with a competing state-of-the-art approach by using a public image database.
Acesso aberto (Open Access)
Classificação de arritmias cardíacas através de uma estrutura competitiva de redes neurais convolucionais autoassociativas
(Universidade Federal do Pará, 2023-05-11) CORRÊA FILHO, Sérgio Teixeira; CASTRO, Adriana Rosa Garcez; http://lattes.cnpq.br/5273686389382860
This work proposes a system for classifying cardiac arrhythmias based on a competitive structure of Autoassociative Convolutional Neural Networks. Three neural networks were trained to reconstruct Electrocardiogram (ECG) signals for cases of patients with supraventricular, ventricular and normal beats. After training, the networks were allocated in a competitive parallel structure for classification of arrhythmias. The MIT-BIH arrhythmia public database of ECG signals was used for training and testing the networks, and for each ECG signal, from each patient, the QRS complexes of the heartbeats were extracted, which were the characteristics used as input. for the system, and these signals, which were in the form of temporal signals (1D), were transformed into digital images (2D) in order to use the capacity of convolutional neural networks for pattern recognition and feature extraction in images. For the development and performance analysis of the proposed structure, two paradigms that have been used in works already presented in the literature were used: interpatient paradigm and intrapatient paradigm, and the system obtained an accuracy of 96.97%, sensitivity of 96.30% and precision of 93.59% for the intrapatient case and accuracy of 94.05%, sensitivity of 70.43% and precision of 65.74% for the interpatient case. A comparative analysis with results from arrhythmia classification systems already presented in the literature shows that the proposed system presented similar results or, in some cases, better results than those already obtained, thus showing the applicability of the proposed structure to the problem
Acesso aberto (Open Access)
Classificação de tumores cerebrais: um estudo comparativo entre rede neural convolucional e rede neural convolucional com mecanismo de atenção
(Universidade Federal do Pará, 2024-09-30) SILVA, Ulrich Kauê Mendes Alencar da; CASTRO, Adriana Rosa Garcez; http://lattes.cnpq.br/5273686389382860
Brain tumors are neurological diseases with a high potential impact on the lives of affected individuals, requiring a rapid and accurate diagnosis through complementary imaging tests, such as magnetic resonance imaging, which is considered the gold standard in this process. Considering the need for faster diagnosis, classification systems based on Machine Learning have been developed and within this context, this dissertation aims to present a comparative study between a Convolutional Neural Network (CNN) and a CNN with an attention mechanism, developed for the classification of brain tumors from magnetic resonance images. The comparative study aims to identify the impact of the attention mechanism on the performance of the CNN for tumor classification. For the development and evaluation of the proposed models, a public database was used, collected from the Kaggle website and made available by Masoud Nickparvar, which is composed of 7023 brain magnetic resonance images, segmented into four classes: glioma, meningioma, no tumor and pituitary. As a result, from the performance metrics obtained, considering the image base used for testing in both CNNs, an improvement in the CNN performance was observed after the introduction of the attention mechanism, where the network with this mechanism presented an increase of 1.98% in the accuracy metric, 2.07% in the precision metric, 2.18% in the sensitivity metric and 1.72% in the F1-score metric in relation to the CNN without the attention mechanism. It is also possible to highlight the results obtained in particular for the meningioma tumor class, since the CNN without the attention mechanism presented difficulties in classifying this class and, after the integration of the attention mechanism, the model obtained an accuracy increase of 6.54% for this class.
Acesso aberto (Open Access)
Estrutura competitiva de redes neurais convolucionais auto-associativas para classificação de arritmias
(Universidade Federal do Pará, 2019-04-17) BAIA, Alexandre Farias; CASTRO, Adriana Rosa Garcez; http://lattes.cnpq.br/5273686389382860
This work presents the proposal of two automatic systems to aid in the detection of anomalies in heart beats and medical decision support. The systems were developed for the identification of rhythmic arrhythmia and morphological arrhythmias from signals obtained from an electrocardiogram (ECG). Both systems are based on a competitive structure of Convolutional Autoencoders (CAE), and each network was trained to reconstruct the signals presented at its entrance. For the case of the rhythmic classifier, the system was developed from the use of the ECG signals, without undergoing a feature extraction process, and for the case of the morphological classifier, the system was based on the QRS complex extracted from the ECG signal. For the development and testing of the systems, the database MIT-BIH Arrhythmia of ECG signals was used. An accuracy of 88.9% was achieved for the Rhythmic Classifier and 81.73% for the Morphological Classifier, in the case in which the evaluation basis is considered. The results obtained demonstrate the applicability of the proposed competitive structures to the arrhythmia classification problem.
Acesso aberto (Open Access)
Metodologia para a classificação automática de doenças em plantas utilizando redes neurais convolucionais.
(Universidade Federal do Pará, 2019-11-07) REZENDE, Vanessa Castro; OLIVEIRA, Roberto Célio Limão de; http://lattes.cnpq.br/4497607460894318; SANTOS, Adam Dreyton Ferreira dos; http://lattes.cnpq.br/2616572481839756
Convolutional neural networks (CNNs) are one of the deep learning techniques that, due to the computational advancement of recent years, have enhanced the field of computer vision by enabling substantial gains in various classification problems, especially those involving digital images. Given the advantages of using these networks, a variety of applications for automatic plant diseases identification have been developed for specialized assistance or automated screening tools, contributing to more sustainable farming practices and improved food production security. In this context, this work aims to propose a methodology for the classification of multiple pathologies from distinct plant species, having as input a database composed of digital images of plant diseases. Initially, this methodology involved image preprocessing activities on the plant disease database to provide the appropriate input for selected CNN models (VGG16, RestNet101v1, ResNet101v2, ResNetXt50 and DenseNet169), as well as to generate ten new bases, ranging from 50 to 66 classes with greater representativeness, to submit the models to different situations. After model training, a comparative study was conducted based on widely used classification metrics such as test accuracy, f1-score, and area under the curve. To attest the significance of obtained results, the Friedman nonparametric statistical test and two post-hoc procedures were performed, which showed that ResNetXt50 and DenseNet169 obtained superior results when compared with VGG16 and ResNets.
Acesso aberto (Open Access)
Previsão de geração de energia fotovoltaica utilizando transformação de séries temporais em imagens e redes neurais convolucionais bidimensionais
(Universidade Federal do Pará, 2023-10-26) MONTEIRO, Diego Ramiro Melo; CASTRO, Adriana Rosa Garcez; http://lattes.cnpq.br/5273686389382860
This research presents a novel approach based on a Bidimensional Convolutional Neural Network (CNN) and techniques for transforming time series data into images, such as Gramian Angular Field (GAF) and Recurrence Plot (RP), for short-term forecast of electricity generation from a photovoltaic microgrid connected to the electrical grid, located at the Center of Excellence in Energy Efficiency of the Amazon (Centro de Excelência em Eficiência Energética da Amazônia –CEAMAZON) at the Federal University of Pará (Universidade Federal do Pará –UFPA). The GAF and RP techniques were employed to transform the time series data into images, which were used as input for the CNN. More accurate electricity generation forecasts enable users to better estimate the potential costs for grid implementation and the payback periods, as well as assess the available load capacity that can be connected to the system with higher precision. The prediction results using GAF and RP with a 2D CNN were compared with results obtained using other established neural network architectures in the field, such as Multilayer Perceptron and 1D CNNs, yielding satisfactory Root Mean Square Error (RMSE) values. This demonstrates the applicability of using images generated from the transformation of photovoltaic time series data in a 2D CNN for this problem.
Acesso aberto (Open Access)
Rede neural convolucional aplicada à identificação de equipamentos residenciais para sistemas de monitoramento não-intrusivo de carga
(Universidade Federal do Pará, 2018-04-03) PENHA, Deyvison de Paiva; CASTRO, Adriana Rosa Garcez; http://lattes.cnpq.br/5273686389382860
This research presents the proposal of a new methodology for the identification of residential equipment in non-intrusive load monitoring systems. The system is based on a Convolutional Neural Network to classify residential equipment, which uses directly as inputs to the system, the transient power signal data of 7 equipment obtained at the moment they are connected in a residence. The methodology was developed using data from a public database (REED) that presents data collected at a low frequency (1 Hz). The results obtained in the test database show an accuracy of more than 90%, indicating that the proposed system is capable of performing the task of identification. In addition, the results presented are considered satisfactory when compared with the results already presented in the literature for the problem in question.
Acesso aberto (Open Access)
Redes neurais profundas aplicadas ao diagnóstico de faltas incipientes em transformadores imersos em óleo isolante.
(Universidade Federal do Pará, 2019-09-11) MORAES, Hugo Riviere Silva; CASTRO, Adriana Rosa Garcez; http://lattes.cnpq.br/5273686389382860
Diagnosing incipient faults in transformers is a major challenge because it is very difficult to define the source and type of fault, due to the variability in the conditions under which faults occur. Conventional methods based on the analysis of dissolved gases in oil have been used by companies to diagnose faults, however, these methods still need to be applied together to reach a satisfactory result, as well as relying heavily on the knowledge of a specialist. In order to solve the difficulties related to conventional methods, some systems based on Computational Intelligence have been proposed in the literature and have presented promising results. This paper presents the results of the study developed of the application of deep neural networks to fault diagnosis, considering then the importance of fault diagnosis in transformers. Two models are proposed using Convolutional Neural Networks and Stacked Autoencoding Neural Networks. For the development of the systems we used the TC 10 database with faulty transformer situations. This base was used to develop the IEC 60599 method, which is one of the main methods used by power utilities for transformer diagnostics through the analysis of dissolved gases in oil. The promising results achieved with the two proposed models (100% accuracy in the test base) show the great applicability of deep neural networks to the problem of incipient transformer fault diagnosis, however showing a great alternative to the conventional methods commonly used.