Search

Imbalanced classification is related to those problems that have an uneven distribution among classes. In addition to the former, when instances are located into the overlapped areas, the correct modeling of the problem becomes harder. Current solutions for both issues are often focused on the binary case study, as multi-class datasets require an additional effort to be addressed. In this research, we overcome these problems by carrying out a combination between feature and instance selections. Feature selection will allow simplifying the overlapping areas easing the generation of rules to distinguish among the classes. Selection of instances from all classes will address the imbalance itself by finding the most appropriate class distribution for the learning task, as well as possibly removing noise and difficult borderline examples. For the sake of obtaining an optimal joint set of features and instances, we embedded the searching for both parameters in a Multi-Objective Evolutionary Algorithm, using the C4.5 decision tree as baseline classifier in this wrapper approach. The multi-objective scheme allows taking a double advantage: the search space becomes broader, and we may provide a set of different solutions in order to build an ensemble of classifiers. This proposal has been contrasted versus several state-of-the-art solutions on imbalanced classification showing excellent results in both binary and multi-class problems.

This paper presents, for the first time, a distance metric learning algorithm for monotonic classification. Monotonic datasets arise in many real-world applications, where there exist order relations in the input and output variables, and the outputs corresponding to ordered pairs of inputs are also expected to be ordered. Monotonic classification can be addressed through several distance-based classifiers that are able to respect the monotonicity constraints of the data. The performance of distance-based classifiers can be improved with the use of distance metric learning algorithms, which are able to find the distances that best represent the similarities among each pair of data samples. However, learning a distance for monotonic data has an additional drawback: the learned distance may negatively impact the monotonic constraints of the data. In our work, we propose a new model for learning distances that does not corrupt these constraints. This methodology will also be useful in identifying and discarding non-monotonic pairs of samples that may be present in the data due to noise. The experimental analysis conducted, supported by a Bayesian statistical testing, demonstrates that the distances obtained by the proposed method can enhance the performance of several distance-based classifiers in monotonic problems. [ABSTRACT FROM AUTHOR]

Available data in machine learning applications is becoming increasingly complex, due to higher dimensionality and difficult classes. There exists a wide variety of approaches to measuring complexity of labeled data, according to class overlap, separability or boundary shapes, as well as group morphology. Many techniques can transform the data in order to find better features, but few focus on specifically reducing data complexity. Most data transformation methods mainly treat the dimensionality aspect, leaving aside the available information within class labels which can be useful when classes are somehow complex. This paper proposes an autoencoder-based approach to complexity reduction, using class labels in order to inform the loss function about the adequacy of the generated variables. This leads to three different new feature learners, Scorer, Skaler and Slicer. They are based on Fisher’s discriminant ratio, the Kullback-Leibler divergence and least-squares support vector machines, respectively. They can be applied as a preprocessing stage for a binary classification problem. A thorough experimentation across a collection of 27 datasets and a range of complexity and classification metrics shows that class-informed autoencoders perform better than 4 other popular unsupervised feature extraction techniques, especially when the final objective is using the data for a classification task. [ABSTRACT FROM AUTHOR]

Evolutionary computation has largely exhibited its potential to complement conventional learning algorithms in a variety of machine learning tasks, especially those related to unsupervised (clustering) and supervised learning. It has not been until lately when the computational efficiency of evolutionary solvers has been put in prospective for training reinforcement learning models. However, most studies framed so far within this context have considered environments and tasks conceived in isolation, without any exchange of knowledge among related tasks. In this manuscript we present A-MFEA-RL, an adaptive version of the well-known MFEA algorithm whose search and inheritance operators are tailored for multitask reinforcement learning environments. Specifically, our approach includes crossover and inheritance mechanisms for refining the exchange of genetic material, which rely on the multilayered structure of modern deep-learning-based reinforcement learning models. In order to assess the performance of the proposed approach, we design an extensive experimental setup comprising multiple reinforcement learning environments of varying levels of complexity, over which the performance of A-MFEA-RL is compared to that furnished by alternative nonevolutionary multitask reinforcement learning approaches. As concluded from the discussion of the obtained results, A-MFEA-RL not only achieves competitive success rates over the simultaneously addressed tasks, but also fosters the exchange of knowledge among tasks that could be intuitively expected to keep a degree of synergistic relationship. [ABSTRACT FROM AUTHOR]

Copyright of DYNA - Ingeniería e Industria is the property of Publicaciones Dyna SL and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Land use and land cover (LULC) mapping are of paramount importance to monitor and understand the structure and dynamics of the Earth system. One of the most promising ways to create accurate global LULC maps is by building good quality state-of-the-art machine learning models. Building such models requires large and global datasets of annotated time series of satellite images, which are not available yet. This paper presents TimeSpec4LULC 10.5281/zenodo.5913554; , a smart open-source global dataset of multispectral time series for 29 LULC classes ready to train machine learning models. TimeSpec4LULC was built based on the seven spectral bands of the MODIS sensors at 500 m resolution, from 2000 to 2021, and was annotated using spatial–temporal agreement across the 15 global LULC products available in Google Earth Engine (GEE). The 22-year monthly time series of the seven bands were created globally by (1) applying different spatial–temporal quality assessment filters on MODIS Terra and Aqua satellites; (2) aggregating their original 8 d temporal granularity into monthly composites; (3) merging Terra + Aqua data into a combined time series; and (4) extracting, at the pixel level, 6 076 531 time series of size 262 for the seven bands along with a set of metadata: geographic coordinates, country and departmental divisions, spatial–temporal consistency across LULC products, temporal data availability, and the global human modification index. A balanced subset of the original dataset was also provided by selecting 1000 evenly distributed samples from each class such that they are representative of the entire globe. To assess the annotation quality of the dataset, a sample of pixels, evenly distributed around the world from each LULC class, was selected and validated by experts using very high resolution images from both Google Earth and Bing Maps imagery. This smartly, pre-processed, and annotated dataset is targeted towards scientific users interested in developing various machine learning models, including deep learning networks, to perform global LULC mapping. [ABSTRACT FROM AUTHOR]

Land Use and Land Cover (LULCs) mapping and change detection are of paramount importance to understand the distribution and effectively monitor the dynamics of the Earth's system. An unexplored way to create global LULC maps is by building good quality LULC-models based on state-of-the-art deep learning networks. Building such models requires large global good quality time series LULC datasets, which are not available yet. This paper presents TimeSpec4LULC (Khaldi et al., 2021), a smart open-source global dataset of multi-Spectral Time series for 29 LULC classes. TimeSpec4LULC was built based on the 7 spectral bands of MODIS sensor at 500 m resolution from 2002 to 2021, and was annotated using a spatial agreement across the 15 global LULC products available in Google Earth Engine. The 19-year monthly time series of the seven bands were created globally by: (1) applying different spatio-temporal quality assessment filters on MODIS Terra and Aqua satellites, (2) aggregating their original 8-day temporal granularity into monthly composites, (3) merging their data into a Terra+Aqua combined time series, and (4) extracting, at the pixel level, 11.85 million time series for the 7 bands along with a set of metadata about geographic coordinates, country and departmental divisions, spatio-temporal consistency across LULC products, temporal data availability, and the global human modification index. To assess the annotation quality of the dataset, a sample of 100 pixels, evenly distributed around the world, from each LULC class, was selected and validated by experts using very high resolution images from both Google Earth and Bing Maps imagery. This smartly, pre-processed, and annotated dataset is targeted towards scientific users interested in developing and evaluating various machine learning models, including deep learning networks, to perform global LULC mapping and change detection. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to introduce a new distance metric learning algorithm for ordinal regression. Ordinal regression addresses the problem of predicting classes for which there is a natural ordering, but the real distances between classes are unknown. Since ordinal regression walks a fine line between standard regression and classification, it is a common pitfall to either apply a regression-like numerical treatment of variables or underrate the ordinal information applying nominal classification techniques. On a different note, distance metric learning is a discipline that has proven to be very useful when improving distance-based algorithms such as the nearest neighbors classifier. In addition, an appropriate distance can enhance the explainability of this model. In our study we propose an ordinal approach to learning a distance, called chain maximizing ordinal metric learning. It is based on the maximization of ordered sequences in local neighborhoods of the data. This approach takes into account all the ordinal information in the data without making use of any of the two extremes of classification or regression, and it is able to adapt to data for which the class separations are not clear. We also show how to extend the algorithm to learn in a non-linear setup using kernel functions. We have tested our algorithm on several ordinal regression problems, showing a high performance under the usual evaluation metrics in this domain. Results are verified through Bayesian non-parametric testing. Finally, we explore the capabilities of our algorithm in terms of explainability using the case-based reasoning approach. We show these capabilities empirically on two different datasets, experiencing significant improvements over the case-based reasoning with the traditional Euclidean nearest neighbors. [ABSTRACT FROM AUTHOR]

Data Science and Machine Learning have become fundamental assets for companies and research institutions alike. As one of its fields, supervised classification allows for class prediction of new samples, learning from given training data. However, some properties can cause datasets to be problematic to classify. In order to evaluate a dataset a priori, data complexity metrics have been used extensively. They provide information regarding different intrinsic characteristics of the data, which serve to evaluate classifier compatibility and a course of action that improves performance. However, most complexity metrics focus on just one characteristic of the data, which can be insufficient to properly evaluate the dataset towards the classifiers' performance. In fact, class overlap, a very detrimental feature for the classification process (especially when imbalance among class labels is also present) is hard to assess. This research work focuses on revisiting complexity metrics based on data morphology. In accordance to their nature, the premise is that they provide both good estimates for class overlap, and great correlations with the classification performance. For that purpose, a novel family of metrics has been developed. Being based on ball coverage by classes, they are named after Overlap Number of Balls. Finally, some prospects for the adaptation of the former family of metrics to singular (more complex) problems are discussed. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Science & Technology (JCS&T) is the property of Journal of Computer Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The Support Vector Machine (SVM) is one of the most powerful algorithms for machine learning and data mining in numerous and heterogenous application domains. However, in spite of its competitiveness, SVM suffers from scalability problems which drastically worsens its performance in terms of memory requirements and execution time. As a consequence, there is a strong emergence of approaches for supporting SVM in efficiently addressing the aforementioned problems without affecting its classification capabilities. In this scenario, methods for Training Set Selection (TSS) represent a suitable and consolidated pre-processing technique to compute a reduced but representative training dataset, and improve SVM’s scalability without deprecating its classification accuracy. Recently, TSS has been formulated as an optimization problem characterized by two objectives (the classification accuracy and the reduction rate) and solved through the application of evolutionary algorithms. However, so far, all the evolutionary approaches for TSS have been based on a so-called multi-objective a priori technique, where multiple objectives are aggregated together into a single objective through a weighted combination. This paper proposes to apply, for the first time, a Pareto-based multi-objective optimization approach to the TSS problem in order to explicitly deal with both its objectives and offer a better trade-off between SVM’s classification and reduction performance. The benefits of the proposed approach are validated by a set of experiments involving well-known datasets taken from the UCI Machine Learning Database Repository. As shown by statistical tests, the application of a Pareto-based multi-objective optimization approach improves on state-of-the-art TSS techniques and enhances SVM efficiency. [ABSTRACT FROM AUTHOR]

Support vector machines (SVMs) are among the most powerful learning algorithms for classification tasks. However, these algorithms require a high computational cost during the training phase, which can limit their application on large-scale datasets. Moreover, it is known that their effectiveness highly depends on the hyper-parameters used to train the model. With the intention of dealing with these, this paper introduces an evolutionary multiobjective model and instance selection (IS) approach for SVMs with Pareto-based ensemble, whose goals are, precisely, to optimize the size of the training set and the classification performance attained by the selection of the instances, which can be done using either a wrapper or a filter approach. Due to the nature of multiobjective evolutionary algorithms, several Pareto optimal solutions can be found. We study several ways of using such information to perform a classification task. To accomplish this, our proposal performs a processing over the Pareto solutions in order to combine them into a single ensemble. This is done in five different ways, which are based on: 1) a global Pareto ensemble; 2) error reduction; 3) a complementary error reduction; 4) maximized margin distance; and 5) boosting. Through a comprehensive experimental study we evaluate the suitability of the proposed approach and the Pareto processing, and we show its advantages over a single-objective formulation, traditional IS techniques, and learning algorithms. [ABSTRACT FROM PUBLISHER]

Mining massive and high-speed data streams among the main contemporary challenges in machine learning. This calls for methods displaying a high computational efficacy, with ability to continuously update their structure and handle ever-arriving big number of instances. In this paper, we present a new incremental and distributed classifier based on the popular nearest neighbor algorithm, adapted to such a demanding scenario. This method, implemented in Apache Spark, includes a distributed metric-space ordering to perform faster searches. Additionally, we propose an efficient incremental instance selection method for massive data streams that continuously update and remove outdated examples from the case-base. This alleviates the high computational requirements of the original classifier, thus making it suitable for the considered problem. Experimental study conducted on a set of real-life massive data streams proves the usefulness of the proposed solution and shows that we are able to provide the first efficient nearest neighbor solution for high-speed big and streaming data. [ABSTRACT FROM AUTHOR]

Multi-class classification problems can be addressed by using decomposition strategy. One of the most popular decomposition techniques is the One-vs-One (OVO) strategy, which consists of dividing multi-class classification problems into as many as possible pairs of easier-to-solve binary sub-problems. To discuss the presence of classes with different cost, in this paper, we examine the behavior of an ensemble of Cost-Sensitive Back-Propagation Neural Networks (CSBPNN) with OVO binarization techniques for multi-class problems. To implement this, the original multi-class cost-sensitive problem is decomposed into as many sub-problems as possible pairs of classes and each sub-problem is learnt in an independent manner using CSBPNN. Then a combination method is used to aggregate the binary cost-sensitive classifiers. To verify the synergy of the binarization technique and CSBPNN for multi-class cost-sensitive problems, we carry out a thorough experimental study. Specifically, we first develop the study to check the effectiveness of the OVO strategy for multi-class cost-sensitive learning problems. Then, we develop a comparison of several well-known aggregation strategies in our scenario. Finally, we explore whether further improvement can be achieved by using the management of non-competent classifiers. The experimental study is performed with three types of cost matrices and proper statistical analysis is employed to extract the meaningful findings. [ABSTRACT FROM AUTHOR]

In this paper, we propose a complete, fully automatic and efficient clinical decision support system for breast cancer malignancy grading. The estimation of the level of a cancer malignancy is important to assess the degree of its progress and to elaborate a personalized therapy. Our system makes use of both Image Processing and Machine Learning techniques to perform the analysis of biopsy slides. Three different image segmentation methods (fuzzy c-means color segmentation, level set active contours technique and grey-level quantization method) are considered to extract the features used by the proposed classification system. In this classification problem, the highest malignancy grade is the most important to be detected early even though it occurs in the lowest number of cases, and hence the malignancy grading is an imbalanced classification problem. In order to overcome this difficulty, we propose the usage of an efficient ensemble classifier named EUSBoost, which combines a boosting scheme with evolutionary undersampling for producing balanced training sets for each one of the base classifiers in the final ensemble. The usage of the evolutionary approach allows us to select the most significant samples for the classifier learning step (in terms of accuracy and a new diversity term included in the fitness function), thus alleviating the problems produced by the imbalanced scenario in a guided and effective way. Experiments, carried on a large dataset collected by the authors, confirm the high efficiency of the proposed system, shows that level set active contours technique leads to an extraction of features with the highest discriminative power, and prove that EUSBoost is able to outperform state-of-the-art ensemble classifiers in a real-life imbalanced medical problem. [ABSTRACT FROM AUTHOR]

Imbalanced classification deals with learning from data with a disproportional number of samples in its classes. Traditional classifiers exhibit poor behavior when facing this kind of data because they do not take into account the imbalanced class distribution. Four main kinds of solutions exist to solve this problem: modifying the data distribution, modifying the learning algorithm for considering the imbalance representation, including the use of costs for data samples, and ensemble methods. In this paper, we adopt the second type of solution and introduce a classification algorithm for imbalanced data that uses fuzzy rough set theory and ordered weighted average aggregation. The proposal considers different strategies to build a weight vector to take into account data imbalance. Our methods are validated by an extensive experimental study, showing statistically better results than 13 other state-of-the-art methods. [ABSTRACT FROM PUBLISHER]

Multi-objective evolutionary algorithms represent an effective tool to improve the accuracy-interpretability trade-off of fuzzy rule-based classification systems. To this aim, a tuning process and a rule selection process can be combined to obtain a set of solutions with different trade-offs between the accuracy and the compactness of models. Nevertheless, an initial model needs to be defined, in particular the parameters that describe the partitions and the number of fuzzy sets of each variable (i.e. the granularities) must be determined. The simplest approach is to use a previously established single granularity and a uniform fuzzy partition for each variable. A better approach consists in automatically identifying from data the appropriate granularities and fuzzy partitions, since this usually leads to more accurate models. This contribution presents a fuzzy discretization approach, which is used to generate automatically promising granularities and their associated fuzzy partitions. This mechanism is integrated within a Multi-Objective Fuzzy Association Rule-Based Classification method, namely D-MOFARC, which concurrently performs a tuning and a rule selection process on an initial knowledge base. The aim is to obtain fuzzy rule-based classification systems with high classification performances, while preserving their complexity. [ABSTRACT FROM AUTHOR]

Most of the algorithms for mining quantitative association rules focus on positive dependencies without paying particular attention to negative dependencies. The latter may be worth taking into account, however, as they relate the presence of certain items to the absence of others. The algorithms used to extract such rules usually consider only one evaluation criterion in measuring the quality of generated rules. Recently, some researchers have framed the process of extracting association rules as a multiobjective problem, allowing us to jointly optimize several measures that can present different degrees of trade-off depending on the dataset used. In this paper, we propose MOPNAR, a new multiobjective evolutionary algorithm, in order to mine a reduced set of positive and negative quantitative association rules with low computational cost. To accomplish this, our proposal extends a recent multiobjective evolutionary algorithm based on decomposition to perform an evolutionary learning of the intervals of the attributes and a condition selection for each rule, while introducing an external population and a restarting process to store all the nondominated rules found and to improve the diversity of the rule set obtained. Moreover, this proposal maximizes three objectives—comprehensibility, interestingness, and performance—in order to obtain rules that are interesting, easy to understand, and provide good coverage of the dataset. The effectiveness of the proposed approach is validated over several real-world datasets. [ABSTRACT FROM PUBLISHER]

Imbalanced data is a common problem in classification. This phenomenon is growing in importance since it appears in most real domains. It has special relevance to highly imbalanced data-sets (when the ratio between classes is high). Many techniques have been developed to tackle the problem of imbalanced training sets in supervised learning. Such techniques have been divided into two large groups: those at the algorithm level and those at the data level. Data level groups that have been emphasized are those that try to balance the training sets by reducing the larger class through the elimination of samples or increasing the smaller one by constructing new samples, known as undersampling and oversampling, respectively. This paper proposes a new hybrid method for preprocessing imbalanced data-sets through the construction of new samples, using the Synthetic Minority Oversampling Technique together with the application of an editing technique based on the Rough Set Theory and the lower approximation of a subset. The proposed method has been validated by an experimental study showing good results using C4.5 as the learning algorithm. [ABSTRACT FROM AUTHOR]

Cooperative coevolution is a successful trend of evolutionary computation which allows us to define partitions of the domain of a given problem, or to integrate several related techniques into one, by the use of evolutionary algorithms. It is possible to apply it to the development of advanced classification methods, which integrate several machine learning techniques into a single proposal. A novel approach integrating instance selection, instance weighting, and feature weighting into the framework of a coevolutionary model is presented in this paper. We compare it with a wide range of evolutionary and nonevolutionary related methods, in order to show the benefits of the employment of coevolution to apply the techniques considered simultaneously. The results obtained, contrasted through nonparametric statistical tests, show that our proposal outperforms other methods in the comparison, thus becoming a suitable tool in the task of enhancing the nearest neighbor classifier. [ABSTRACT FROM PUBLISHER]

Classifier learning with data-sets that suffer from imbalanced class distributions is a challenging problem in data mining community. This issue occurs when the number of examples that represent one class is much lower than the ones of the other classes. Its presence in many real-world applications has brought along a growth of attention from researchers. In machine learning, the ensemble of classifiers are known to increase the accuracy of single classifiers by combining several of them, but neither of these learning techniques alone solve the class imbalance problem, to deal with this issue the ensemble learning algorithms have to be designed specifically. In this paper, our aim is to review the state of the art on ensemble techniques in the framework of imbalanced data-sets, with focus on two-class problems. We propose a taxonomy for ensemble-based methods to address the class imbalance where each proposal can be categorized depending on the inner ensemble methodology in which it is based. In addition, we develop a thorough empirical comparison by the consideration of the most significant published approaches, within the families of the taxonomy proposed, to show whether any of them makes a difference. This comparison has shown the good behavior of the simplest approaches which combine random undersampling techniques with bagging or boosting ensembles. In addition, the positive synergy between sampling techniques and bagging has stood out. Furthermore, our results show empirically that ensemble-based algorithms are worthwhile since they outperform the mere use of preprocessing techniques before learning the classifier, therefore justifying the increase of complexity by means of a significant enhancement of the results. [ABSTRACT FROM PUBLISHER]

This paper proposes a Genetic Algorithm for jointly performing a feature selection and granularity learning for Fuzzy Rule-Based Classification Systems in the scenario of highly imbalanced data-sets. We refer to imbalanced data-sets when the class distribution is not uniform, a situation that it is present in many real application areas. The aim of this work is to get more compact models by selecting the adequate variables and adapting the number of fuzzy labels for each problem, improving the interpretability of the model. The experimental analysis is carried out over a wide range of highly imbalanced data-sets and uses the statistical tests suggested in the specialized literature. [ABSTRACT FROM AUTHOR]

Fuzzy rule-based classification systems (FRBCSs) are known due to their ability to treat with low quality data and obtain good results in these scenarios. However, their application in problems with missing data are uncommon while in real-life data, information is frequently incomplete in data mining, caused by the presence of missing values in attributes. Several schemes have been studied to overcome the drawbacks produced by missing values in data mining tasks; one of the most well known is based on preprocessing, formerly known as imputation. In this work, we focus on FRBCSs considering 14 different approaches to missing attribute values treatment that are presented and analyzed. The analysis involves three different methods, in which we distinguish between Mamdani and TSK models. From the obtained results, the convenience of using imputation methods for FRBCSs with missing values is stated. The analysis suggests that each type behaves differently while the use of determined missing values imputation methods could improve the accuracy obtained for these methods. Thus, the use of particular imputation methods conditioned to the type of FRBCSs is required. [ABSTRACT FROM AUTHOR]

In the classification framework there are problems in which the number of examples per class is not equitably distributed, formerly known as imbalanced data sets. This situation is a handicap when trying to identify the minority classes, as the learning algorithms are not usually adapted to such characteristics. An usual approach to deal with the problem of imbalanced data sets is the use of a preprocessing step. In this paper we analyze the usefulness of the data complexity measures in order to evaluate the behavior of undersampling and oversampling methods. Two classical learning methods, C4.5 and PART, are considered over a wide range of imbalanced data sets built from real data. Specifically, oversampling techniques and an evolutionary undersampling one have been selected for the study. We extract behavior patterns from the results in the data complexity space defined by the measures, coding them as intervals. Then, we derive rules from the intervals that describe both good or bad behaviors of C4.5 and PART for the different preprocessing approaches, thus obtaining a complete characterization of the data sets and the differences between the oversampling and undersampling results. [ABSTRACT FROM AUTHOR]

Abstract: The nested generalized exemplar theory accomplishes learning by storing objects in Euclidean n-space, as hyperrectangles. Classification of new data is performed by computing their distance to the nearest “generalized exemplar” or hyperrectangle. This learning method allows the combination of the distance-based classification with the axis-parallel rectangle representation employed in most of the rule-learning systems. In this paper, we propose the use of evolutionary algorithms to select the most influential hyperrectangles to obtain accurate and simple models in classification tasks. The proposal has been compared with the most representative models based on hyperrectangle learning; such as the BNGE, RISE, INNER, and SIA genetics based learning approach. Our approach is also very competitive with respect to classical rule induction algorithms such as C4.5Rules and RIPPER. The results have been contrasted through non-parametric statistical tests over multiple data sets and they indicate that our approach outperforms them in terms of accuracy requiring a lower number of hyperrectangles to be stored, thus obtaining simpler models than previous NGE approaches. Larger data sets have also been tackled with promising outcomes. [Copyright &y& Elsevier]

Abstract: The analysis of data complexity is a proper framework to characterize the tackled classification problem and to identify domains of competence of classifiers. As a practical outcome of this framework, the proposed data complexity measures may facilitate the choice of a classifier for a given problem. The aim of this paper is to study the behaviour of a fuzzy rule based classification system and its relationship to data complexity. We use as a case of study the fuzzy hybrid genetic based machine learning method presented in [H. Ishibuchi, T. Yamamoto, T. Nakashima, Hybridization of fuzzy GBML approaches for pattern classification problems, IEEE Transactions on Systems, Man, and Cybernetics—Part B: Cybernetics 35 (2) (2005) 359–365]. We examine several metrics of data complexity over a wide range of data sets built from real data and try to extract behaviour patterns from the results. We obtain rules which describe both good or bad behaviours of the fuzzy rule based classification system. These rules use values of data complexity metrics in their antecedents, so we try to predict the behaviour of the method from the data set complexity metrics prior to its application. Therefore, we can establish the domains of competence of this fuzzy rule based classification system. [Copyright &y& Elsevier]

Abstract: Classification in imbalanced domains is a recent challenge in data mining. We refer to imbalanced classification when data presents many examples from one class and few from the other class, and the less representative class is the one which has more interest from the point of view of the learning task. One of the most used techniques to tackle this problem consists in preprocessing the data previously to the learning process. This preprocessing could be done through under-sampling; removing examples, mainly belonging to the majority class; and over-sampling, by means of replicating or generating new minority examples. In this paper, we propose an under-sampling procedure guided by evolutionary algorithms to perform a training set selection for enhancing the decision trees obtained by the C4.5 algorithm and the rule sets obtained by PART rule induction algorithm. The proposal has been compared with other under-sampling and over-sampling techniques and the results indicate that the new approach is very competitive in terms of accuracy when comparing with over-sampling and it outperforms standard under-sampling. Moreover, the obtained models are smaller in terms of number of leaves or rules generated and they can considered more interpretable. The results have been contrasted through non-parametric statistical tests over multiple data sets. [Copyright &y& Elsevier]

This paper presents a genetic fuzzy system for the data mining task of subgroup discovery, the subgroup discovery iterative genetic algorithm (SDIGA), which obtains fuzzy rules for subgroup discovery in disjunctive normal form. This kind of fuzzy rule allows us to represent knowledge about patterns of interest in an explanatory and understandable form that can be used by the expert. Experimental evaluation of the algorithm and a comparison with other subgroup discovery algorithms show the validity of the proposal. SDIGA is applied to a market problem studied in the University of Mondragón, Spain, in which it is necessary to extract automatically relevant and interesting information that helps to improve fair planning policies. The application of SDIGA to this problem allows us to obtain novel and valuable knowledge for experts. [ABSTRACT FROM AUTHOR]

Invasion of the Polygraphus proximus Blandford bark beetle causes catastrophic damage to forests with firs (Abies sibirica Ledeb) in Russia, especially in Central Siberia. Determining tree damage stage based on the shape, texture and colour of tree crown in unmanned aerial vehicle (UAV) images could help to assess forest health in a faster and cheaper way. However, this task is challenging since (i) fir trees at different damage stages coexist and overlap in the canopy, (ii) the distribution of fir trees in nature is irregular and hence distinguishing between different crowns is hard, even for the human eye. Motivated by the latest advances in computer vision and machine learning, this work proposes a two-stage solution: In a first stage, we built a detection strategy that finds the regions of the input UAV image that are more likely to contain a crown, in the second stage, we developed a new convolutional neural network (CNN) architecture that predicts the fir tree damage stage in each candidate region. Our experiments show that the proposed approach shows satisfactory results on UAV Red, Green, Blue (RGB) images of forest areas in the state nature reserve "Stolby" (Krasnoyarsk, Russia). [ABSTRACT FROM AUTHOR]

Distance metric learning is a branch of machine learning that aims to learn distances from the data, which enhances the performance of similarity-based algorithms. This tutorial provides a theoretical background and foundations on this topic and a comprehensive experimental analysis of the most-known algorithms. We start by describing the distance metric learning problem and its main mathematical foundations, divided into three main blocks: convex analysis, matrix analysis and information theory. Then, we will describe a representative set of the most popular distance metric learning methods used in classification. All the algorithms studied in this paper will be evaluated with exhaustive testing in order to analyze their capabilities in standard classification problems, particularly considering dimensionality reduction and kernelization. The results, verified by Bayesian statistical tests, highlight a set of outstanding algorithms. Finally, we will discuss several potential future prospects and challenges in this field. This tutorial will serve as a starting point in the domain of distance metric learning from both a theoretical and practical perspective. [ABSTRACT FROM AUTHOR]

pyDML is an open-source python library that provides a wide range of distance metric learning algorithms. Distance metric learning can be useful to improve similarity learning algorithms, such as the nearest neighbors classifier, and also has other applications, like dimensionality reduction. The pyDML package currently provides more than 20 algorithms, which can be categorized, according to their purpose, in: dimensionality reduction algorithms, algorithms to improve nearest neighbors or nearest centroids classifiers, information theory based algorithms or kernel based algorithms, among others. In addition, the library also provides some utilities for the visualization of classifier regions, parameter tuning and a stats website with the performance of the implemented algorithms. The package relies on the scipy ecosystem, it is fully compatible with scikit-learn, and is distributed under GPLv3 license. Source code and documentation can be found at https://github.com/jlsuarezdiaz/pyDML. [ABSTRACT FROM AUTHOR]

Federated learning is a machine learning paradigm that emerges as a solution to the privacy-preservation demands in artificial intelligence. As machine learning, federated learning is threatened by adversarial attacks against the integrity of the learning model and the privacy of data via a distributed approach to tackle local and global learning. This weak point is exacerbated by the inaccessibility of data in federated learning, which makes the protection against adversarial attacks harder and evidences the need to furtherance the research on defence methods to make federated learning a real solution for safeguarding data privacy. In this paper, we present an extensive review of the threats of federated learning, as well as as their corresponding countermeasures, attacks versus defences. This survey provides a taxonomy of adversarial attacks and a taxonomy of defence methods that depict a general picture of this vulnerability of federated learning and how to overcome it. Likewise, we expound guidelines for selecting the most adequate defence method according to the category of the adversarial attack. Besides, we carry out an extensive experimental study from which we draw further conclusions about the behaviour of attacks and defences and the guidelines for selecting the most adequate defence method according to the category of the adversarial attack. Finally, we present our learned lessons and challenges. • We claim that adversarial attacks are a significant challenge in federated learning. • We propose taxonomies of adversarial attacks and defences in federated learning. • We conduct a wide experimental study the results of which support our claim. • We define guidelines for selecting a proper defence method according to the attack. • We stand out a set of lessons learnt, open challenges and final conclusions. [ABSTRACT FROM AUTHOR]

The latest Deep Learning (DL) models for detection and classification have achieved an unprecedented performance over classical machine learning algorithms. However, DL models are black-box methods hard to debug, interpret, and certify. DL alone cannot provide explanations that can be validated by a non technical audience such as end-users or domain experts. In contrast, symbolic AI systems that convert concepts into rules or symbols – such as knowledge graphs – are easier to explain. However, they present lower generalization and scaling capabilities. A very important challenge is to fuse DL representations with expert knowledge. One way to address this challenge, as well as the performance-explainability trade-off is by leveraging the best of both streams without obviating domain expert knowledge. In this paper, we tackle such problem by considering the symbolic knowledge is expressed in form of a domain expert knowledge graph. We present the eXplainable Neural-symbolic learning (X-NeSyL) methodology, designed to learn both symbolic and deep representations, together with an explainability metric to assess the level of alignment of machine and human expert explanations. The ultimate objective is to fuse DL representations with expert domain knowledge during the learning process so it serves as a sound basis for explainability. In particular, X-NeSyL methodology involves the concrete use of two notions of explanation, both at inference and training time respectively: (1) EXPLANet : Expert-aligned eXplainable Part-based cLAssifier NETwork Architecture, a compositional convolutional neural network that makes use of symbolic representations, and (2) SHAP-Backprop , an explainable AI-informed training procedure that corrects and guides the DL process to align with such symbolic representations in form of knowledge graphs. We showcase X-NeSyL methodology using MonuMAI dataset for monument facade image classification, and demonstrate that with our approach, it is possible to improve explainability at the same time as performance. • EXplainable Neural-symbolic Learning methodology fuses deep learning and symbolic representations. • EXPLANet's compositional part-based object detection and classification outperforms regular classification. • SHAP-Backprop aligns model output with expert knowledge in a knowledge graph. • SHAP Graph Edit Distance quantifies the alignment between a knowledge graph and neural representations. • X-NeSyL shows it is possible to improve over both explainability and performance. [ABSTRACT FROM AUTHOR]

Image segmentation is an important issue in many industrial processes, with high potential to enhance the manufacturing process derived from raw material imaging. For example, metal phases contained in microstructures yield information on the physical properties of the steel. Existing prior literature has been devoted to develop specific computer vision techniques able to tackle a single problem involving a particular type of metallographic image. However, the field lacks a comprehensive tutorial on the different types of techniques, methodologies, their generalizations and the algorithms that can be applied in each scenario. This paper aims to fill this gap. First, the typologies of computer vision techniques to perform the segmentation of metallographic images are reviewed and categorized in a taxonomy. Second, the potential utilization of pixel similarity is discussed by introducing novel deep learning-based ensemble techniques that exploit this information. Third, a thorough comparison of the reviewed techniques is carried out in two openly available real-world datasets, one of them being a newly published dataset directly provided by ArcelorMittal, which opens up the discussion on the strengths and weaknesses of each technique and the appropriate application framework for each one. Finally, the open challenges in the topic are discussed, aiming to provide guidance in future research to cover the existing gaps. [Display omitted] • We create a metallography dataset from additive manufacturing of steels (MetalDAM). • We provide an updated taxonomy of segmentation methods. • We propose a new DL-based ensemble specialized in the semantic segmentation task. • We compare state-of-the-art models and the new ensembles with UHCS and MetalDAM. • We present a thorough analysis of the current difficulties and challenges. [ABSTRACT FROM AUTHOR]