Browsing by Author "Menotti, David"

Now showing 1 - 8 of 8
  • No Thumbnail Available
    Item
    Bias effect on predicting market trends with EMD.
    (2017) Furlaneto, Dennis Carnelossi; Oliveira, Luiz S.; Menotti, David; Cavalcanti, George Darmiton da Cunha
    Financial time series are notoriously difficult to analyze and predict, given their non-stationary, highly oscillatory nature. In this study, we evaluate the effectiveness of the Ensemble Empirical Mode Decom- position (EEMD), the ensemble version of Empirical Mode Decomposition (EMD), at generating a rep- resentation for market indexes that improves trend prediction. Our results suggest that the promising results reported using EEMD on financial time series were obtained by inadvertently adding look-ahead bias to the testing protocol via pre-processing the entire series with EMD, which affects predictive re- sults. In contrast to conclusions found in the literature, our results indicate that the application of EMD and EEMD with the objective of generating a better representation for financial time series is not suffi- cient to improve the accuracy or cumulative return obtained by the models used in this study.
  • No Thumbnail Available
    Item
    Evaluating a hierarchical approach for heartbeat classification from ECG.
    (2018) Luz, Eduardo José da Silva; Merschmann, Luiz Henrique de Campos; Menotti, David; Moreira, Gladston Juliano Prates
    Several types of arrhythmias that can be rare and harmless, but may result in serious cardiac issues, and several ECG analysis methods have been proposed in the literature to automatically classify the various classes of arrhythmias. Following the Association for the Advancement of Medical Instrumentation (AAMI) standard, 15 classes of heartbeats can be hierarchically grouped into five superclasses. In this work, we propose to employ the hierarchical classification paradigm to five ECG analysis methods in the literature, and compare their performance with flat classification paradigm. In our experiments, we use the MIT-BIH Arrhythmia Database and analyse the use of the hierarchical classification following AAMI standard and a well-known and established evaluation protocol using five superclasses. The experimental results showed that the hierarchical classification provided the highest gross accuracy for most of the methods used in this work and provided an improvement in classification performance of N and SVEB superclasses.
  • No Thumbnail Available
    Item
    Evaluating the use of ECG signal in low frequencies as a biometry.
    (2014) Luz, Eduardo José da Silva; Menotti, David; Schwartz, William Robson
    Traditional strategies, such as fingerprinting and face recognition, are becoming more and more fraud susceptible. As a consequence, new and more fraud proof biometrics modalities have been considered, one of them being the heartbeat pattern acquired by an electrocardiogram (ECG). While methods for subject identification based on ECG signal work with signals sampled in high frequencies (>100 Hz), the main goal of this work is to evaluate the use of ECG signal in low frequencies for such aim. In this work, the ECG signal is sampled in low frequencies (30 Hz and 60 Hz) and represented by four feature extraction methods available in the literature, which are then feed to a Support Vector Machines (SVM) classifier to perform the identification. In addition, a classification approach based on majority voting using multiple samples per subject is employed and compared to the traditional classification based on the presentation of single samples per subject each time. Considering a database composed of 193 subjects, results show identification accuracies higher than 95% and near to optimality (i.e., 100%) when the ECG signal is sampled in 30 Hz and 60 Hz, respectively, being the last one very close to the ones obtained when the signal is sampled in 360 Hz (the maximum frequency existing in our database). We also evaluate the impact of: (1) the number of training and testing samples for learning and identification, respectively; (2) the scalability of the biometry (i.e., increment on the number of subjects); and (3) the use of multiple samples for person identification.
  • No Thumbnail Available
    Item
    A methodology for photometric validation in vehicles visual interactive systems.
    (2012) Faria, Alexandre Wagner Chagas; Menotti, David; Pappa, Gisele Lobo; Lara, Daniel da Silva Diogo; Araújo, Arnaldo de Albuquerque
    This work proposes a methodology for automatically validating the internal lighting system of an automobile by assessing the visual quality of each instrument in an instrument cluster (IC) (i.e., vehicle gauges, such as speedometer, tachometer, temperature and fuel gauges) based on the user’s perceptions. Although the visual quality assessment of an instrument is a subjective matter, it is also influenced by some of its photometric features, such as the light intensity distribution. This work presents a methodology for identifying and quantifying non-homogeneous regions in the lighting distribution of these instruments, starting from a digital image. In order to accomplish this task, a set of 107 digital images of instruments were acquired and preprocessed, identifying a set of instrument regions. These instruments were also evaluated by common drivers and specialists to identify their non-homogenous regions. Then, for each region, we extracted a set of homogeneity descriptors, and also proposed a relational descriptor to study the homogeneity influence of a region in the whole instrument. These descriptors were associated with the results of the manual labeling, and given to two machine learning algorithms, which were trained to identify a region as being homogeneous or not. Experiments showed that the proposed methodology obtained an overall precision above 94% for both regions and instrument classifications. Finally, a meticulous analysis of the users’ and specialist’s image evaluations is performed
  • No Thumbnail Available
    Item
    Multi-histogram equalization methods for contrast enhancement and brightness preserving.
    (2007) Menotti, David; Najman, Laurent; Facon, Jacques; Araújo, Arnaldo de Albuquerque
    Histogram equalization (HE) has proved to be a simple and effective image contrast enhancement technique. However, it tends to change the mean brightness of the image to the middle level of the gray-level range, which is not desirable in the case of images from consumer electronics products. In the latter case, preserving the input brightness of the image is required to avoid the generation of non-existing artifacts in the output image. To surmount this drawback, Bi- HE methods for brightness preserving and contrast enhancement have been proposed. Although these methods preserve the input brightness on the output image with a significant contrast enhancement, they may produce images with do not look as natural as the input ones. In order to overcome this drawback, this work proposes a novel technique called Multi-HE, which consists of decomposing the input image into several sub-images, and then applying the classical HE process to each one. This methodology performs a less intensive image contrast enhancement, in a way that the output image presents a more natural look. We propose two discrepancy functions for image decomposing, conceiving two new Multi-HE methods. A cost function is also used for automatically deciding in how many sub-images the input image will be decomposed on. Experiments show that our methods preserve more the brightness and produce more natural looking images than the other HE methods.
  • No Thumbnail Available
    Item
    Multi-objective dynamic programming for spatial cluster detection.
    (2015) Moreira, Gladston Juliano Prates; Paquete, Luís; Duczmal, Luiz Henrique; Menotti, David; Takahashi, Ricardo Hiroshi Caldeira
    The detection and inference of arbitrarily shaped spatial clusters in aggregated geographical areas is described here as a multi-objective combinatorial optimization problem. A multi-objective dynamic programming algorithm, the Geo Dynamic Scan, is proposed for this formulation, finding a collection of Pareto-optimal solutions. It takes into account the geographical proximity between areas, thus allowing a disconnected subset of aggregated areas to be included in the efficient solutions set. It is shown that the collection of efficient solutions generated by this approach contains all the solutions maximizing the spatial scan statistic. The plurality of the efficient solutions set is potentially useful to analyze variations of the most likely cluster and to investigate covariates. Numerical simulations are conducted to evaluate the algorithm. A study case with Chagas’ disease clusters in Brazil is presented, with covariate analysis showing strong correlation of disease occurrence with environmental data.
  • No Thumbnail Available
    Item
    Ocular recognition databases and competitions : a survey.
    (2022) Zanlorensi Junior, Luiz Antonio; Laroca, Rayson; Luz, Eduardo José da Silva; Britto Junior, Alceu de Souza; Oliveira, Luiz Eduardo Soares de; Menotti, David
    The use of the iris and periocular region as biometric traits has been extensively investigated, mainly due to the singularity of the iris features and the use of the periocular region when the image resolution is not sufcient to extract iris information. In addition to providing information about an individual’s identity, features extracted from these traits can also be explored to obtain other information such as the individual’s gender, the infuence of drug use, the use of contact lenses, spoofng, among others. This work presents a survey of the databases created for ocular recognition, detailing their protocols and how their images were acquired. We also describe and discuss the most popular ocular recognition competitions (contests), highlighting the submitted algorithms that achieved the best results using only iris trait and also fusing iris and periocular region information. Finally, we describe some relevant works applying deep learning techniques to ocular recognition and point out new challenges and future directions. Considering that there are a large number of ocular databases, and each one is usually designed for a specifc problem, we believe this survey can provide a broad overview of the challenges in ocular biometrics.
  • No Thumbnail Available
    Item
    Proposta e avaliação de um sistema automático para identificação de veículos.
    (2013) Oliveira Neto, Vantuil José de; Menotti, David; Menotti, David; Cámara Chávez, Guillermo; Bianchi, Andrea Gomes Campos; Facon, Jacques; Guimarães, Silvio Jamil Ferzoli; Santos, Haroldo Gambini
    Sistemas automáticos de identificação de veículos têm como objetivo a identificação de automóveis por meio de suas placas. A maioria dos trabalhos relatados na literatura científica utilizam imagens únicas de um veículo, em geral capturadas sob condições de iluminação e distância controladas, utilizando em muitos casos um gatilho que informa ao sistema qual o momento em que a imagem deve ser processada pelo sistema. Nosso sistema parte de uma abordagem diferente: a localização e o rastreamento dos veículos ao longo da cena. Com esta abordagem o uso do gatilho é dispensado, a área para localização da placa é diminuída devido ao rastreamento do veículo e a quantidade de quadros disponíveis para um mesmo veículo é aumentada. Construímos uma base de vídeos com 1061 veículos divididos em 23 vídeos diferentes, capturados em quatro pontos distintos no acesso principal da nossa universidade. O sistema foi desenvolvido utilizando C++ e OpenCv, e constituído de 6 módulos: localização de movimento, rastreamento de veículos, seleção do melhor frame, localização da placa, segmentação dos caracteres e reconhecimento; cada um dos módulos foi construído independentemente, permitindo assim que trabalhos futuros alterem apenas um destes módulos, dando mais flexibilidade a trabalhos futuros. O sistema funciona em tempo real, processando o vídeo em menos tempo do que o tempo total do vídeo. Em nossa base, o sistema foi capaz de identificar perfeitamente apenas 27,7% dos veículos, no entanto de reconhecer 54,7% dos caracteres rotulados. Em pontos de referência mais adequados, atingimos 65,8% e 65,03% de reconhecimento de caracteres, com 71,11% e 70,30% de identificação de veículos com quatro ou mais dígitos da placa corretamente reconhecidos. Embora o sistema não apresente resultados promissores nos vídeos avaliados, ele abre espaço para que diferentes métodos e abordagens encapsulados em módulos do sistema possam ser facilmente avaliados.