Search

In classification, it is generally assumed that data from one class consist of one pure compact data cluster. However, in many cases, this cluster might consist of multiple subclusters, in other words, within-class multimodality. In such a scenario, it may be difficult or even impossible for a single classifier to find a suitable model using limited data. So, training a model using smaller chunks of data is an alternative that helps avoid complex models and reduces the task's complexity. This paper proposes the subconcept Perturbation-based Classifier (sPerC) that finds the best clusters per class using cluster validation measures, and one meta-classifier is trained per subcluster. This way, each class is represented by a set of meta-classifiers instead of one classifier. Such a design diminishes the complexity of the task, and using a divide-to-conquer strategy favors the precision of each meta-classifier. Through a set of comprehensive experiments on 30 datasets, the sPerC results compared favorably to other classifiers in multi-class classification tasks, showing that creating specialized classifiers per class in different regions of the feature space can be advantageous. [ABSTRACT FROM AUTHOR]

Entrepreneurs and small businesses have increasingly used reward-based crowdfunding to raise capital for their creative projects, whose success is central to this industry. Thus, predicting the success of crowdfunding campaigns is a topic of great importance for entrepreneurs and platform managers. The literature that employs monolithic classifiers and static ensemble learning for crowdfunding success prediction are scarce. In contrast, the dynamic selection (DS) algorithm, which belongs to the ensemble learning category, deserves a particular remark since it has overcome traditional monolithic classifiers and static ensembles in many applications. This paper proposes a dynamic selection framework for reward crowdfunding prediction. DS algorithms select a competent subset of the classifier per query instance. This procedure is performed during the generalization, and the subset is composed of local experts, favoring an increase in accuracy. Fifteen machine learning models are evaluated using three metrics (accuracy, area under the ROC curve and F-score), and ensemble learning obtained better results than traditional classifiers. In particular, Meta-DES, which performs dynamic selection, obtains the best overall results among the evaluated models. Furthermore, since usually interpreting the output of ML models is considered to be very difficult due to their complex “black box” architecture, we also use Shapley additive explanations to interpret the perdition’s outputs. Among variables evaluated in our models, the textual sentiment of the mass media, the number of pledges, and the target amount of the campaign deserve a highlight when predicting the campaign’s success. The source-code and further details about the experimental analysis are available at https://github.com/las33/Crowdfunding. [ABSTRACT FROM AUTHOR]

The sea surface temperature (SST) is an environmental indicator closely related to climate, weather, and atmospheric events worldwide. Its forecasting is essential for supporting the decision of governments and environmental organizations. Literature has shown that single machine learning (ML) models are generally more accurate than traditional statistical models for SST time series modeling. However, the parameters tuning of these ML models is a challenging task, mainly when complex phenomena, such as SST forecasting, are addressed. Issues related to misspecification, overfitting, or underfitting of the ML models can lead to underperforming forecasts. This work proposes using hybrid systems (HS) that combine (ML) models using residual forecasting as an alternative to enhance the performance of SST forecasting. In this context, two types of combinations are evaluated using two ML models: support vector regression (SVR) and long short-term memory (LSTM). The experimental evaluation was performed on three datasets from different regions of the Atlantic Ocean using three well-known measures: mean square error (MSE), mean absolute percentage error (MAPE), and mean absolute error (MAE). The best HS based on SVR improved the MSE value for each analyzed series by 82.26 % , 98.93 % , and 65.03 % compared to its respective single model. The HS employing the LSTM improved 92.15 % , 98.69 % , and 32.41 % concerning the single LSTM model. Compared to literature approaches, at least one version of HS attained higher accuracy than statistical and ML models in all study cases. In particular, the nonlinear combination of the ML models obtained the best performance among the proposed HS versions. [ABSTRACT FROM AUTHOR]

The Bayes classifier depends on the conditional densities and the prior probabilities. Among many density functions, the Gaussian density has received more attention mainly motivated by its analytical tractability. The parameters of the Bayes classifier for the Gaussian distribution data are generally unknown, and approximations are calculated for the mean vector μ ^ and the covariance matrix Σ ^ . When a pattern is inserted in the training set of the class ω i , the values of the parameters μ ^ i and Σ ^ i change by an amount given by Δ μ ^ i and Δ Σ ^ i , respectively. The insertion of one pattern can cause a perturbation, so we claim that this perturbation can be used for supervised classification purposes. Based on this assumption, we propose a supervised classifier called Perturbation-based Classifier PerC that assigns the class of the query pattern as the one that presents the smallest perturbation among all the classes after the insertion of this query pattern in the classes. The rationale is that the addition of a pattern that belongs to one specific class should not alter much the distribution of that class. PerC only uses the perturbations ( Δ μ ^ i and Δ Σ ^ i ) to evaluate the class of a query pattern; so, it is a parameter-free classifier. The proposed method was assessed on 21 datasets from the UCI Machine Learning Repository, and its results were compared with classifiers from the literature. Results have shown that PerC obtains very competitive recognition rates. [ABSTRACT FROM AUTHOR]

The particulate matter (PM) concentration has been one of the most relevant environmental concerns in recent decades due to its prejudicial effects on living beings and the earth’s atmosphere. High PM concentration affects the human health in several ways leading to short and long term diseases. Thus, forecasting systems have been developed to support decisions of the organizations and governments to alert the population. Forecasting systems based on Artificial Neural Networks (ANNs) have been highlighted in the literature due to their performances. In general, three ANN-based approaches have been found for this task: ANN trained via learning algorithms, hybrid systems that combine search algorithms with ANNs, and hybrid systems that combine ANN with other forecasters. Independent of the approach, it is common to suppose that the residuals (error series), obtained from the difference between actual series and forecasting, have a white noise behavior. However, it is possible that this assumption is infringed due to: misspecification of the forecasting model, complexity of the time series or temporal patterns of the phenomenon not captured by the forecaster. This paper proposes an approach to improve the performance of PM forecasters from residuals modeling. The approach analyzes the remaining residuals recursively in search of temporal patterns. At each iteration, if there are temporal patterns in the residuals, the approach generates the forecasting of the residuals in order to improve the forecasting of the PM time series. The proposed approach can be used with either only one forecaster or by combining two or more forecasting models. In this study, the approach is used to improve the performance of a hybrid system (HS) composed by genetic algorithm (GA) and ANN from residuals modeling performed by two methods, namely, ANN and own hybrid system. Experiments were performed for PM2.5 and PM10 concentration series in Kallio and Vallila stations in Helsinki and evaluated from six metrics. Experimental results show that the proposed approach improves the accuracy of the forecasting method in terms of fitness function for all cases, when compared with the method without correction. The correction via HS obtained a superior performance, reaching the best results in terms of fitness function and in five out of six metrics. These results also were found when a sensitivity analysis was performed varying the proportions of the sets of training, validation and test. The proposed approach reached consistent results when compared with the forecasting method without correction, showing that it can be an interesting tool for correction of PM forecasters. [ABSTRACT FROM AUTHOR]

Autoassociative artificial neural networks have been used in many different computer vision applications. However, it is difficult to define the most suitable neural network architecture because this definition is based on previous knowledge and depends on the problem domain. To address this problem, we propose a constructive autoassociative neural network called CANet (Constructive Autoassociative Neural Network). CANet integrates the concepts of receptive fields and autoassociative memory in a dynamic architecture that changes the configuration of the receptive fields by adding new neurons in the hidden layer, while a pruning algorithm removes neurons from the output layer. Neurons in the CANet output layer present lateral inhibitory connections that improve the recognition rate. Experiments in face recognition and facial expression recognition show that the CANet outperforms other methods presented in the literature. [ABSTRACT FROM AUTHOR]

The transmission line is one of the most crucial electric power system components, demanding special attention since they are subject to failures that can cause disruptions in energy supply. In this scenario, the fault location emerges as a fundamental task, providing an approximate position where the failure occurred in the line. This paper presents a method for fault location using a novel dynamic regressor selection (DRS) framework, in which we introduce embedded normalization, incorporating the data scaling process inside the framework. The DRS aims to select the most accurate models from a pool of regressors to predict the fault distance. Moreover, since there is a lack of a public dataset, this paper presents and makes a new fault dataset available to the scientific community with several features extracted from current and voltage signals of representative failure events. In our experiments, we demonstrate the importance of this embedded normalization as well as the significance in the variation of critical hyperparameters of the DRS strategy, such as the distance metric used to define the region of competence and the criterion to select the best regressors from the pool of predictors. This work also presents the definition of the oracle concept in DRS, which represents the ideal predictor selection scheme. The results demonstrate the effectiveness of the proposed method with a mean error of 0.7086 km ± 0.0068 km, representing 0.1712% ± 0.0016% of the transmission line extension (414 km). [ABSTRACT FROM AUTHOR]

In dynamic ensemble selection (DES) techniques, only the most competent classifiers, for the classification of a specific test sample, are selected to predict the sample's class labels. The key in DES techniques is estimating the competence of the base classifiers for the classification of each specific test sample. The classifiers' competence is usually estimated according to a given criterion, which is computed over the neighborhood of the test sample defined on the validation data, called the region of competence. A problem arises when there is a high degree of noise in the validation data, causing the samples belonging to the region of competence to not represent the query sample. In such cases, the dynamic selection technique might select the base classifier that overfitted the local region rather than the one with the best generalization performance. In this paper, we propose two modifications in order to improve the generalization performance of any DES technique. First, a prototype selection technique is applied over the validation data to reduce the amount of overlap between the classes, producing smoother decision borders. During generalization, a local adaptive K-Nearest Neighbor algorithm is used to minimize the influence of noisy samples in the region of competence. Thus, DES techniques can better estimate the classifiers' competence. Experiments are conducted using 10 state-of-the-art DES techniques over 30 classification problems. The results demonstrate that the proposed scheme significantly improves the classification accuracy of dynamic selection techniques. [ABSTRACT FROM AUTHOR]

Since the beginning of the COVID-19 pandemic, many works have been published proposing solutions to the problems that arose in this scenario. In this vein, one of the topics that attracted the most attention is the development of computer-based strategies to detect COVID-19 from thoracic medical imaging, such as chest X-ray (CXR) and computerized tomography scan (CT scan). By searching for works already published on this theme, we can easily find thousands of them. This is partly explained by the fact that the most severe worldwide pandemic emerged amid the technological advances recently achieved, and also considering the technical facilities to deal with the large amount of data produced in this context. Even though several of these works describe important advances, we cannot overlook the fact that others only use well-known methods and techniques without a more relevant and critical contribution. Hence, differentiating the works with the most relevant contributions is not a trivial task. The number of citations obtained by a paper is probably the most straightforward and intuitive way to verify its impact on the research community. Aiming to help researchers in this scenario, we present a review of the top-100 most cited papers in this field of investigation according to the Google Scholar search engine. We evaluate the distribution of the top-100 papers taking into account some important aspects, such as the type of medical imaging explored, learning settings, segmentation strategy, explainable artificial intelligence (XAI), and finally, the dataset and code availability. [ABSTRACT FROM AUTHOR]

DESlib is an open-source python library providing the implementation of several dynamic selection techniques. The library is divided into three modules: (i) dcs, containing the implementation of dynamic classifier selection methods (DCS); (ii) des, containing the implementation of dynamic ensemble selection methods (DES); (iii) static, with the implementation of static ensemble techniques. The library is fully documented (documentation available online on Read the Docs), has a high test coverage (codecov.io) and is part of the scikit-learn-contrib supported projects. Documentation, code and examples can be found on its GitHub page: https://github.com/scikit-learn-contrib/DESlib. [ABSTRACT FROM AUTHOR]

Class imbalance refers to classification problems in which many more instances are available for certain classes than for others. Such imbalanced datasets require special attention because traditional classifiers generally favor the majority class which has a large number of instances. Ensemble of classifiers has been reported to yield promising results. However, the majority of ensemble methods applied to imbalance learning are static ones. Moreover, they only deal with binary imbalanced problems. Hence, this paper presents an empirical analysis of Dynamic Selection techniques and data preprocessing methods for dealing with multi-class imbalanced problems. We considered five variations of preprocessing methods and 14 Dynamic Selection schemes. Our experiments conducted on 26 multi-class imbalanced problems show that the dynamic ensemble improves the AUC and the G -mean as compared to the static ensemble. Moreover, data preprocessing plays an important role in such cases. [ABSTRACT FROM AUTHOR]

Image segmentation of retinal blood vessels is a process that can help to predict and diagnose cardiovascular related diseases, such as hypertension and diabetes, which are known to affect the retinal blood vessels’ appearance. This work proposes an unsupervised method for the segmentation of retinal vessels images using a combined matched filter, Frangi’s filter and Gabor Wavelet filter to enhance the images. The combination of these three filters in order to improve the segmentation is the main motivation of this work. We investigate two approaches to perform the filter combination: weighted mean and median ranking. Segmentation methods are tested after the vessel enhancement. Enhanced images with median ranking are segmented using a simple threshold criterion. Two segmentation procedures are applied when considering enhanced retinal images using the weighted mean approach. The first method is based on deformable models and the second uses fuzzy C-means for the image segmentation. The procedure is evaluated using two public image databases, Drive and Stare. The experimental results demonstrate that the proposed methods perform well for vessel segmentation in comparison with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

COVID-19 frequently provokes pneumonia, which can be diagnosed using imaging exams. Chest X-ray (CXR) is often useful because it is cheap, fast, widespread, and uses less radiation. Here, we demonstrate the impact of lung segmentation in COVID-19 identification using CXR images and evaluate which contents of the image influenced the most. Semantic segmentation was performed using a U-Net CNN architecture, and the classification using three CNN architectures (VGG, ResNet, and Inception). Explainable Artificial Intelligence techniques were employed to estimate the impact of segmentation. A three-classes database was composed: lung opacity (pneumonia), COVID-19, and normal. We assessed the impact of creating a CXR image database from different sources, and the COVID-19 generalization from one source to another. The segmentation achieved a Jaccard distance of 0.034 and a Dice coefficient of 0.982. The classification using segmented images achieved an F1-Score of 0.88 for the multi-class setup, and 0.83 for COVID-19 identification. In the cross-dataset scenario, we obtained an F1-Score of 0.74 and an area under the ROC curve of 0.9 for COVID-19 identification using segmented images. Experiments support the conclusion that even after segmentation, there is a strong bias introduced by underlying factors from different sources. [ABSTRACT FROM AUTHOR]