Publicações

Confronting the pandemic of COVID-19 is nowadays one of the most prominent challenges of the human species. A key factor in slowing down the virus propagation is the rapid diagnosis and isolation of infected patients. The standard method for COVID-19 identification, the Reverse transcription polymerase chain reaction method, is time-consuming and in short supply due to the pandemic. Thus, researchers have been looking for alternative screening methods, and deep learning applied to chest X-rays of patients has been showing promising results. Despite their success, the computational cost of these methods remains high, which imposes difficulties to their accessibility and availability. Thus, the main goal of this work is to propose an accurate yet efficient method in terms of memory and processing time for the problem of COVID-19 screening in chest X-rays.

ABSTRACT Humulus lupulus L., also known as hops, is a vine whose flowers are a major component in brewing. It delivers flavor, bitterness, and aroma to beer and also aids in foam stabilization. Furthermore, it plays an important role in beer conservation due to its antimicrobial and antioxidant properties, which have recently been studied for food preservation. Hops can also be found in the production of cosmetics and is considered healthy food. There are more than 250 cataloged varieties of hops, and among the main attributes that differ from each other are alpha-acids, beta-acids, and essential oils. Those components give the beer a unique combination of characteristics, and may even influence its category. There are many ways to identify the hop variety from its acids and essential oils using methods such as chromatography, mass spectrometry, capillary electrophoresis, and nuclear magnetic resonance. However, these methods demand expensive and complex equipment, inaccessible or unavailable to most beer producers. In this work, we present a database that includes 1592 images of hop leaves, from 12 popular hop varieties in southeastern Brazil. From these images, it is possible to explore methods of pattern recognition and machine learning to classify hop varieties

In recent years, deep learning methods have outperformed previous state-of-the-art machine learning techniques for several problems, including image classification. Classifying cells in Pap smear images is very challenging, and it is still of paramount importance for cytopathologists. The Pap test is a cervical cancer prevention test that tracks preneoplastic changes in cervical epithelial cells. Carrying out this exam is important in that early detection. It is directly related to a greater chance of curing or reducing the number of deaths caused by the disease. The analysis of Pap smears is exhaustive and repetitive, as it is performed manually by cytopathologists. Therefore, a tool that assists cytopathologists is needed. This work considers 10 deep convolutional neural networks and proposes an ensemble of the three best architectures to classify cervical cancer upon cell nuclei and reduce the professionals’ workload. The dataset used in the experiments is available in the Center for Recognition and Inspection of Cells (CRIC) Searchable Image Database. Considering the metrics of precision, recall, F1-score, accuracy, and sensitivity, the proposed ensemble improves previous methods shown in the literature for two- and three-class classification. We also introduce the six-class classification outcome.

<p>Tuning the Proportional Integral Derivative, or PID, controller in cyber-physical systems is a major challenge as it requires advanced mathematical skills. Several authors in the literature have shown that optimization algorithms are efficient for auto-adjust PID controller constants, especially when there is no mathematical modeling. However, the literature lacks works that show the efficiency of the Variable Neighborhood Search (VNS) algorithm to auto-adjust the PID. In this work, we investigate the efficiency of the Variable Neighborhood Algorithm to fine-tune a PID controller of a real cyber physical-system: a birotor flying drone. The approach consists of applying a numerical neighborhood structure to optimize the three constants of the PID, according to a proposed fitness function. Experiments reveal the feasibility of fine-tuning the PID controller and the birotor balancing with the Variable Neighborhood Algorithm with reduced time. <br />We compared the VNS-approach against one based on genetic algorithms, and on average, the VNS-approach achieves better results with lower computational and memory costs. Results suggest that the approach may be used in real or commercial systems, helping to fine-tune the controller to new environment changes or even last-minute project modifications.</p>

Due to the application of vital signs in expert systems, new approaches have emerged, and vital signals have been gaining space in biometrics. One of these signals is the electroencephalogram (EEG). The motor task in which a subject is doing, or even thinking, influences the pattern of brain waves and disturb the signal acquired. In this work, biometrics with the EEG signal from a cross-task perspective are explored. Based on deep convolutional networks (CNN) and Squeeze-and-Excitation Blocks, a novel method is developed to produce a deep EEG signal descriptor to assess the impact of the motor task in EEG signal on biometric verification. The Physionet EEG Motor Movement/Imagery Dataset is used here for method evaluation, which has 64 EEG channels from 109 subjects performing different tasks. Since the volume of data provided by the dataset is not large enough to effectively train a Deep CNN model, it is also proposed a data augmentation technique to achieve better performance. An evaluation protocol is proposed to assess the robustness regarding the number of EEG channels and also to enforce train and test sets without individual overlapping. A new state-of-the-art result is achieved for the cross-task scenario (EER of 0.1%) and the Squeeze-and-Excitation based networks overcome the simple CNN architecture in three out of four cross-individual scenarios.

AbstractDependence measures, from linear correlation coefficients to recent copula-based methods, have been widely used to find out associations between variables. Although the latter type of measure has overcome many drawbacks of traditional measures, copula has intrinsically some undesirable characteristics for particular applications. In this paper, we discuss dependence modeling from a pattern recognition perspective and then introduce a new non-parametric approach based on anomaly detection through cluster analysis. The proposed methodology uses a weighting procedure based on Voronoi cells densities, named Weighted Voronoi Distance (WVD), to identify potentially atypical associations between univariate time series. The advantages are two-fold. First, the time series structure is respected and neither independence nor homoscedasticity is presumed within data. Second, any distribution of the data and any dependence function is allowed. An inference procedure is presented and simulation studies help to visualize the behavior and benefits of the proposed measure. Finally, real financial data is used to analyze the detection capacity of the contagion effect in financial markets during the 2007 sub-prime crisis. Different asset classes were included, and the WVD was able to signalize anomalies more strongly than the Extreme Value Theory and copula approach.

AbstractSpatial patterns studies are of great interest to the scientific community and the spatial scan statistic is a widely used technique to analyze such patterns. A key point for the construction of methods for detection of irregularly shaped clusters is that, as the geometrical shape has more degrees of freedom, some correction should be employed in order to compensate the increased flexibility. This paper proposed a multi-objective approach to cluster detection problem using the Particle Swarm Optimization technique aggregating a novel penalty function, called dispersion function, allowing only clusters which are subsets of a circular zone of moderate size. Compared to other regularity functions, the multi-objective scan with the dispersion function is faster and suited for the detection of moderately irregularly shaped clusters. An application is presented using state-wide data for Chagas’ disease in puerperal women in Minas Gerais state, Brazil.

Early detection and diagnosis are critical factors to control the COVID-19 spreading. A number of deep learning-based methodologies have been recently proposed for COVID-19 screening in CT scans as a tool to automate and help with the diagnosis. These approaches, however, suffer from at least one of the following problems: (i) they treat each CT scan slice independently and (ii) the methods are trained and tested with sets of images from the same dataset. Treating the slices independently means that the same patient may appear in the training and test sets at the same time which may produce misleading results. It also raises the question of whether the scans from the same patient should be evaluated as a group or not. Moreover, using a single dataset raises concerns about the generalization of the methods. Different datasets tend to present images of varying quality which may come from different types of CT machines reflecting the conditions of the countries and cities from where they come from. In order to address these two problems, in this work, we propose an Efficient Deep Learning Technique for the screening of COVID-19 with a voting-based approach. In this approach, the images from a given patient are classified as group in a voting system. The approach is tested in the two biggest datasets of COVID-19 CT analysis with a patient-based split. A cross dataset study is also presented to assess the robustness of the models in a more realistic scenario in which data comes from different distributions. The cross-dataset analysis has shown that the generalization power of deep learning models is far from acceptable for the task since accuracy drops from 87.68% to 56.16% on the best evaluation scenario. These results highlighted that the methods that aim at COVID-19 detection in CT-images have to improve significantly to be considered as a clinical option and larger and more diverse datasets are needed to evaluate the methods in a realistic scenario.

A new mathematical programming formulation is proposed for an optimization problem in queueing networks. The sum of the blocking probabilities of a general service time, single server, finite, acyclic queueing network is minimized, as are the total butter sizes and the overall service rates. A multi-objective genetic algorithm (MOGA) and a particle swarm optimization (MOPSO) algorithm are combined to solve this difficult stochastic problem. The derived algorithm produces a set of efficient solutions for multiple objectives in the objective function. The implementation of the optimization algorithms is dependent on the generalized expansion method (GEM), a classical tool used to evaluate the performance of finite queueing networks. A set of computational experiments is presented to attest to the efficacy and efficiency of the proposed approach. Insights obtained from the analysis of a complex network may assist in the planning of these types of queueing networks.

We present a robustness analysis of an inter-cities mobility complex network, motivated by the challenge of the COVID-19 pandemic and the seek for proper containment strategies. Brazilian data from 2016 are used to build a network with more than five thousand cities (nodes) and twenty-seven states with the edges representing the weekly flow of people between cities via terrestrial transports. Nodes are systematically isolated (removed from the network) either at random (failures) or guided by specific strategies (targeted attacks), and the impacts are assessed with three metrics: the number of components, the size of the giant component, and the total remaining flow of people. We propose strategies to identify which regions should be isolated first and their impact on people mobility. The results are compared with the so-called reactive strategy, which consists of isolating regions ordered by the date the first case of COVID-19 appeared. We assume that the nodes' failures abstract individual municipal and state initiatives that are independent and possess a certain level of unpredictability. Differently, the targeted attacks are related to centralized strategies led by the federal government in agreement with municipalities and states. Removing a node means completely restricting the mobility of people between the referred city/state and the rest of the network. Results reveal that random failures do not cause a high impact on mobility restraint, but the coordinated isolation of specific cities with targeted attacks is crucial to detach entire network areas and thus prevent spreading. Moreover, the targeted attacks perform better than the reactive strategy for the three analyzed robustness metrics.

Multimodal systems are a workaround to enhance the robustness and effectiveness of biometric systems. A proper multimodal dataset is of the utmost importance to build such systems. The literature presents some multimodal datasets, although, to the best of our knowledge, there are no previous studies combining face, iris/eye, and vital signals such as the Electrocardiogram (ECG). Moreover, there is no methodology to guide the construction and evaluation of a chimeric dataset. Taking that fact into account, we propose to create a chimeric dataset from three modalities in this work: ECG, eye, and face. Based on the Doddington Zoo criteria, we also propose a generic and systematic protocol imposing constraints for the creation of homogeneous chimeric individuals, which allow us to perform a fair and reproducible benchmark. Moreover, we have proposed a multimodal approach for these modalities based on state-of-the-art deep representations built by convolutional neural networks. We conduct the experiments in the open-world verification mode and on two different scenarios (intra-session and inter-session), using three modalities from two datasets: CYBHi (ECG) and FRGC (eye and face). Our multimodal approach achieves impressive decidability of 7.20 ± 0.18, yielding an almost perfect verification system (i.e., Equal Error Rate (EER) of 0.20% ± 0.06) on the intra-session scenario with unknown data. On the inter-session scenario, we achieve a decidability of 7.78 ± 0.78 and an EER of 0.06% ± 0.06. In summary, these figures represent a gain of over 28% in decidability and a reduction over 11% of the EER on the intra-session scenario for unknown data compared to the best-known unimodal approach. Besides, we achieve an improvement greater than 22% in decidability and an EER reduction over 6% in the inter-session scenario.

For multi-objective optimization algorithms, one of the key features is the ability to find a good approximation to the optimal trade-off among the multiple objectives. The most traditional algorithms focus only on the distribution of solutions in the objective space. Nevertheless, a good representation of solutions in the decision space is also important from the point of view of the decision-making process. This work presents a dominance-weighted uniformity-based multi-objective algorithm. The selection phase of the algorithm performs a greedy search of the uniformity measure weighted by a certain measure of dominance. Preliminary experiments suggest that this method promotes the uniformity of the population in the decision variable space while keeping the convergence performance in the objective space.

AbstractThe spatial scan statistic is a widely used technique for detecting spatial clusters. Several extensions of this technique have been developed over the years. The objectives of these techniques are the detection accuracy improvement and a flexibilization on the search clusters space. Based on Voronoi-Based Scan (VBScan), we propose a biobjective approach using a recursively VBScan method called multi-objective multiple clusters VBScan (MOMC-VBScan), alongside a new measure called matching. This approach aims to identify and delineate all multiple significant anomalies in a search space. We conduct several experiments on different simulated maps and two real datasets, showing promising results. The proposed approach proved to be fast and with good precision in determining the partitions.

The QRS complex is a very important part of a heartbeat in the electrocardiogram signal, and it provides useful information for physicians to diagnose heart diseases. Accurately detecting the fiducial points that compose the QRS complex is a challenging task. Another issue concerning the QRS detection is its computational costs since the algorithm should have a fast and real-time response. In this context, there is a trade-off between computational cost and precision. Convolutional networks are a deep learning approach, and it has achieved impressive results in several computer vision and pattern recognition problems. Nowadays there is hardware that fully embeds convolutional network models, significantly reducing computational cost for real-world and real-time applications. In this direction, this work proposes a deep learning approach, based on convolutional network, aiming to detect heartbeat pattern. We tested two different architectures with two different proposes, one very deep and that has small receptive fields, and the other that has larger receptive fields. Preliminary experiments on the MIT-BIH arrhythmia database showed that the studied convolutional network presents promising results for QRS detection which are comparable with state-of-the-art methods.

In this work, we propose to detect the iris and periocular regions simultaneously using coarse annotations and two well-known object detectors: YOLOv2 and Faster R-CNN. We believe coarse annotations can be used in recognition systems based on the iris and periocular regions, given the much smaller engineering effort required to manually annotate the training images. We manually made coarse annotations of the iris and periocular regions (≈122K images from the visible (VIS) spectrum and ≈38K images from the near-infrared (NIR) spectrum). The iris annotations in the NIR databases were generated semi-automatically by first applying an iris segmentation CNN and then performing a manual inspection. These annotations were made for 11 well-known public databases (3 NIR and 8 VIS) designed for the iris-based recognition problem, and are publicly available to the research community1. Experimenting our proposal on these databases, we highlight two results. First, the Faster R-CNN + Feature Pyramid Network (FPN) model reported an Intersection over Union (IoU) higher than YOLOv2 (91.86% vs 85.30%). Second, the detection of the iris and periocular regions being performed simultaneously is as accurate as performed separately, but with a lower computational cost, i.e. two tasks were carried out at the cost of one.

The iris is considered as the biometric trait with the highest unique probability. The iris location is an important task for biometrics systems, affecting directly the results obtained in specific applications such as iris recognition, spoofing and contact lenses detection, among others. This work defines the iris location problem as the delimitation of the smallest squared window that encompasses the iris region. In order to build a benchmark for iris location we annotate (iris squared bounding boxes) four databases from different biometric applications and make them publicly available to the community. Besides these 4 annotated databases, we include 2 others from the literature. We perform experiments on these six databases, five obtained with near infra-red sensors and one with visible light sensor. We compare the classical and outstanding Daugman iris location approach with two window based detectors: 1) a sliding window detector based on features from Histogram of Oriented Gradients (HOG) and a linear Support Vector Machines (SVM) classifier; 2) a deep learning based detector fine-tuned from YOLO object detector. Experimental results showed that the deep learning based detector outperforms the other ones in terms of accuracy and runtime (GPUs version) and should be chosen whenever possible.

The spatial scan statistic is widely used by public health professionals in the detection of spatial clusters in inhomogeneous point process. The most popular version of the spatial scan statistic uses a circular-shaped scanning window. Several other variants, using other parametric or non-parametric shapes, are also available. However, none of them offer information about the uncertainty on the borders of the detected clusters.

The global expansion of biometric systems promotes the emergence of new and more robust biometric modalities. In that context, electroencephalogram (EEG) based biometric interest has been growing in recent years. In this study, a novel approach for EEG representation, based on deep learning, is proposed. The method was evaluated on a database containing 109 subjects, and all 64 EEG channels were used as input to a Deep Convolution Neural Network. Data augmentation techniques are explored to train the deep network and results showed that the method is a promising path to represent brain signals, overcoming baseline methods published in the literature.

Usually, in the deep learning community, it is claimed that generalized representations that yielding outstanding performance / effectiveness require a huge amount of data for learning, which directly affect biometric applications. However, recent works combining transfer learning from other domains have surmounted such data application constraints designing interesting and promising deep learning approaches in diverse scenarios where data is not so abundant. In this direction, a biometric system for the periocular region based on deep learning approach is designed and applied on two non-cooperative ocular databases. Impressive representation discrimination is achieved with transfer learning from the facial domain (a deep convolutional network, called VGG) and fine tuning in the specific periocular region domain. With this design, our proposal surmounts previous state-of-the-art results on NICE (mean decidability of 3.47 against 2.57) and MobBio (equal error rate of 5.42% against 8.73%) competition databases.