Search

Combining traditional diversity and re-balancing techniques serves to design effective ensembles for solving imbalanced classification problems. Therefore, to explore the performance of new diversification procedures and new re-balancing methods is an attractive research subject which can provide even better performances. In this contribution, we propose to create ensembles of the recently introduced binary Bayesian classifiers, that show intrinsic re-balancing capacities, by means of a diversification mechanism which is based on applying different cost policies to each ensemble learner as well as appropriate aggregation schemes. Experiments with an extensive number of representative imbalanced datasets and their comparison with those of several selected high-performance classifiers show that the proposed approach provides the best overal results. [ABSTRACT FROM AUTHOR]

Consistency of preference relations is related to rationality, the lack of consistency in decision making often leads to misleading solutions. This paper studies the ordinal and cardinal consistency problems of fuzzy reciprocal preference relations. First, the concept of ordinal consistency of fuzzy reciprocal preference relations is introduced and analyzed. A l p distance-based method is proposed to formulate the underlying optimization problems as goal programming (GP) models for ordinal and additive consistency problems respectively. By setting different p , three GP models are obtained: (a) a linear GP model where p = 1; (b) a MINMAX GP model, where p = ∞; and (c) an extended GP model, which integrates the two previous models in particular cases. Utilizing these models, we can solve the ordinal and additive consistency problems for fuzzy reciprocal preference relations. The proposed model can preserve the initial preference information as much as possible. Finally, a numerical example and comparative analysis are provided to show effectiveness and validity of the proposed method. [ABSTRACT FROM AUTHOR]

Abstract: In this work we jointly analyze the performance of three classic Artificial Neural Network models and one Support Vector Machine with respect to a series of data complexity measures known as measures of separability of classes. In particular, we consider a Radial Basis Function Network, a Multi-Layer Perceptron, a Learning Vector Quantization, while the Sequential Minimal Optimization method is used to model the Support Vector Machine. We consider five measures of separability of classes over a wide range of data sets built from real data which have proved to be very discriminative when analyzing the performance of classifiers. We find that two of them allow us to extract common behavior patterns for the four learning methods due to their related nature. We obtain rules using these two metrics that describe both good or bad performance of the Artificial Neural Networks and the Support Vector Machine. With the obtained rules, we characterize the performance of the methods from the data set complexity metrics and therefore their common domains of competence are established. Using these domains of competence the shared good and bad capabilities of these four models can be used to know if the approximative models will perform well or poorly or if a more complex configuration of the model is needed for a given problem in advance. [Copyright &y& Elsevier]

Abstract: In this paper, we propose a replacement strategy for steady-state genetic algorithms that considers two features of the candidate chromosome to be included into the population: a measure of the contribution of diversity to the population and the fitness function. In particular, the proposal tries to replace an individual in the population with worse values for these two features. In this way, the diversity of the population becomes increased and the quality of the solutions gets better, thus preserving high levels of useful diversity. Experimental results show the proposed replacement strategy achieved significant performance for problems with different difficulties, with regards to other replacement strategies presented in the literature. [Copyright &y& Elsevier]

With the advent of fast data streams, real-time machine learning has become a challenging task, demanding many processing resources. In addition, they can be affected by the concept drift effect, by which learning methods have to detect changes in the data distribution and adapt to these evolving conditions. Several emerging paradigms such as the so-called Smart Dust, Utility Fog, or Swarm Robotics are in need for efficient and scalable solutions in real-time scenarios, and where usually computing resources are constrained. Cellular automata, as low-bias and robust-to-noise pattern recognition methods with competitive classification performance, meet the requirements imposed by the aforementioned paradigms mainly due to their simplicity and parallel nature. In this work we propose LUNAR, a streamified version of cellular automata devised to successfully meet the aforementioned requirements. LUNAR is able to act as a real incremental learner while adapting to drifting conditions. Furthermore, LUNAR is highly interpretable, as its cellular structure represents directly the mapping between the feature space and the labels to be predicted. Extensive simulations with synthetic and real data will provide evidence of its competitive behavior in terms of classification performance when compared to long-established and successful online learning methods. [ABSTRACT FROM AUTHOR]

Highlights • Multi-label classification is the challenging prediction of several classes at once. • We propose a nearest neighbor method with a novel consensus prediction derivation. • Our method, called FRONEC, is based on fuzzy rough set theory. • FRONEC is highly competitive with other nearest neighbor multi-label methods. Abstract A multi-label dataset consists of observations associated with one or more outcomes. The traditional classification task generalizes to the prediction of several class labels simultaneously. In this paper, we propose a new nearest neighbor based multi-label method. The nearest neighbor approach remains an intuitive and effective way to solve classification problems and popular multi-label classifiers adhering to this paradigm include the MLKNN and IBLR methods. To classify an instance, our proposal derives a consensus among the labelsets of the nearest neighbors based on fuzzy rough set theory. This mathematical framework captures data uncertainty and offers a way to extract a labelset from the dataset that summarizes the information contained in the labelsets of the neighbors. In our experimental study, we compare the performance of our method with five other nearest neighbor based multi-label classifiers using five evaluation metrics commonly used in multi-label classification. Based on the results on both synthetic and real-world datasets, we are able to conclude that our method is a strong competitor to nearest neighbor based multi-label classifiers like MLKNN and IBLR. [ABSTRACT FROM AUTHOR]

The 2-tuple linguistic representation model is widely used as a basis for computing with words (CW) in linguistic decision making problems. Two different models based on linguistic 2-tuples (i.e., the model of the use of a linguistic hierarchy and the numerical scale model) have been developed to address term sets that are not uniformly and symmetrically distributed, i.e., unbalanced linguistic term sets (ULTSs). In this study, we provide a connection between these two different models and prove the equivalence of the linguistic computational models to handle ULTSs. Further, we propose a novel CW methodology where the hesitant fuzzy linguistic term sets (HFLTSs) can be constructed based on ULTSs using a numerical scale. In the proposed CW methodology, we present several novel possibility degree formulas for comparing HFLTSs, and define novel operators based on the mixed 0–1 linear programming model to aggregate the hesitant unbalanced linguistic information. [ABSTRACT FROM AUTHOR]

In this paper we propose a specially designed memetic algorithm for multimodal optimisation problems. The proposal uses a niching strategy, called region-based niching strategy, that divides the search space in predefined and indexable hypercubes with decreasing size, called regions. This niching technique allows our proposal to keep high diversity in the population, and to keep the most promising regions in an external archive. The most promising solutions are improved with a local search method and also stored in the archive. The archive is used as an index to effiently prevent further exploration of these areas with the evolutionary algorithm. The resulting algorithm, called Region-based Memetic Algorithm with Archive, is tested on the benchmark proposed in the special session and competition on niching methods for multimodal function optimisation of the Congress on Evolutionary Computation in 2013. The results obtained show that the region-based niching strategy is more efficient than the classical niching strategy called clearing and that the use of the archive as restrictive index significantly improves the exploration efficiency of the algorithm. The proposal achieves better exploration and accuracy than other existing techniques. [ABSTRACT FROM AUTHOR]

• Explanation Sets, a new framework that unifies counterfactuals and semifactuals. • Counterfactuals and semifactuals are defined in terms of a similarity measure. • Restrictions and preferences over the explanations are defined using a neighborhood. • A taxonomy for set-based representations. Explainable Machine Learning (ML) is an emerging field of Artificial Intelligence that has gained popularity in the last decade. It focuses on explaining ML models and their predictions, enabling people to understand the rationale behind them. Counterfactuals and semifactuals are two instances of Explainable ML techniques that explain model predictions using other observations. These techniques are based on the comparison between the observation to be explained and another one. In counterfactuals, their prediction is different, and in semifactuals, it is the same. Both techniques have been studied in the Social Sciences and Explainable ML communities, and they have different use cases and properties. In this paper, the Explanation Set framework, an approach that unifies counterfactuals and semifactuals, is introduced. Explanation Sets are example-based explanations defined in a neighborhood where most observations satisfy a grouping measure. The neighborhood allows defining and combining restrictions. The grouping measure determines if the explanations are counterfactuals (dissimilarity) or semifactuals (similarity). Besides providing a unified framework, the major strength of the proposal is to extend these explanations to other tasks such as regression by using an appropriate grouping measure. The proposal is validated in a regression and classification task using several neighborhoods and grouping measures. [ABSTRACT FROM AUTHOR]

In some real-world decision processes, decision makers may prefer to provide their opinions using linguistic expressions instead of a single linguistic term. Particularly, they may hesitate between several linguistic terms. In this paper, we deal with the consensus issue in the hesitant linguistic group decision making (GDM) problem. Firstly, a novel distance-based consensus measure is proposed. Then, using this consensus measure we develop an optimization-based consensus model in the hesitant linguistic GDM, which minimizes the number of adjusted simple terms in the consensus building. Furthermore, a two-stage model is displayed to further optimize the solutions to the proposed consensus model, through which we obtain the unique optimal adjustment suggestion to support the consensus reaching process in the hesitant linguistic GDM. Finally, several desirable properties are proposed to justify the proposal, and two examples are used to demonstrate the validity of the models. [ABSTRACT FROM AUTHOR]

In certain real decision-making situations, decision makers often feel more comfortable providing their knowledge and preferences in linguistic terms. Unbalanced linguistic term sets may be used in decision problems with preference relations. However, the lack of consistency in decision-making with linguistic preference relations can lead to inconsistent conclusions. Based on the consistency measure of unbalanced linguistic preference relations, this paper proposes an optimization-based approach to improving the consistency level of unbalanced linguistic preference relations. This consistency-improving model preserves the utmost original knowledge and preferences in the process of improving consistency. Furthermore, it guarantees that the elements in the optimal adjusted unbalanced linguistic preference relation are all simple unbalanced linguistic terms. Finally, we propose a mixed 0–1 linear programming aimed to obtain the optimum solution to the proposed consistency improving model and to demonstrate its practicability. [ABSTRACT FROM AUTHOR]

Abstract: Memetic algorithms with an appropriate trade-off between the exploration and exploitation can obtain very good results in continuous optimisation. That implies the evolutionary algorithm should be focused in exploring the search space while the local search method exploits the achieved solutions. To tackle this issue, we propose to maintain a higher diversity in the evolutionary algorithm’s population by including a niching strategy in the memetic algorithm framework. In this work, we design a novel niching strategy where the niches divide the search space into hypercubes of equal size called regions forbidding the presence of two solutions in each region. The objective is to avoid the competition between the local search and the evolutionary algorithm. We tested this niching strategy in a memetic algorithm with local search chaining and obtained significant improvements. The resulting model also appeared to be very competitive with state-of-the-art algorithms. [Copyright &y& Elsevier]

Highlights: [•] A review on the state-of-the-art of fuzzy nearest neighbor classification is proposed. [•] Fuzzy sets theory and several extensions are analyzed as tools to improve the performance of the nearest neighbor classifier. [•] A taxonomy of the existing methods is proposed. [•] A full experimental study is carried out comparing the performance of the methods. [Copyright &y& Elsevier]

Abstract: In the field of Data Mining, the estimation of the quality of the learned models is a key step in order to select the most appropriate tool for the problem to be solved. Traditionally, a k-fold validation technique has been carried out so that there is a certain degree of independency among the results for the different partitions. In this way, the highest average performance will be obtained by the most robust approach. However, applying a “random” division of the instances over the folds may result in a problem known as dataset shift, which consists in having a different data distribution between the training and test folds. In classification with imbalanced datasets, in which the number of instances of one class is much lower than the other class, this problem is more severe. The misclassification of minority class instances due to an incorrect learning of the real boundaries caused by a not well fitted data distribution, truly affects the measures of performance in this scenario. Regarding this fact, we propose the use of a specific validation technique for the partitioning of the data, known as “Distribution optimally balanced stratified cross-validation” to avoid this harmful situation in the presence of imbalance. This methodology makes the decision of placing close-by samples on different folds, so that each partition will end up with enough representatives of every region. We have selected a wide number of imbalanced datasets from KEEL dataset repository for our study, using several learning techniques from different paradigms, thus making the conclusions extracted to be independent of the underlying classifier. The analysis of the results has been carried out by means of the proper statistical study, which shows the goodness of this approach for dealing with imbalanced data. [Copyright &y& Elsevier]

Abstract: The complexity and impact of many real world decision making problems lead to the necessity of considering multiple points of view, building group decision making problems in which a group of experts provide their preferences to achieve a solution. In such complex problems uncertainty is often present and although the use of linguistic information has provided successful results in managing it, these are sometimes limited because the linguistic models use single-valued and predefined terms that restrict the richness of freely eliciting the preferences of the experts. Usually, experts may doubt between different linguistic terms and require richer expressions to express their knowledge more accurately. However, linguistic group decision making approaches do not provide any model to make more flexible the elicitation of linguistic preferences in such hesitant situations. In this paper is proposed a new linguistic group decision model that facilitates the elicitation of flexible and rich linguistic expressions, in particular through the use of comparative linguistic expressions, close to human beings’ cognitive models for expressing linguistic preferences based on hesitant fuzzy linguistic term sets and context-free grammars. This model defines the group decision process and the necessary operators and tools to manage such linguistic expressions. [Copyright &y& Elsevier]

• A novel class noise filters approaches able to remove noisy instances within the bags. • It is the first attempt to identify instances within the bags as noisy instances. • A wide range of noise levels are used to compare the proposals to validate their behavior. • SW-IPF improves the performance of several SOTA Multiple instance classifiers. • A thorough analysis on the treated instances is provided. Data in the real world is far from being perfect. The appearance of noise is a common issue that arises from the limitations of data acquisition mechanisms and human knowledge. In classification, label noise will hinder the performance of almost all classifiers, inducing a bias in the built model. While label noise has recently attracted researchers' attention in standard classification, it has only recently begun to be studied in multiple instance classification. In this work, we propose the usage of filtering algorithms for multiple instance classification that are able to reduce the impact of negative instances within the bags. In order to do so, we decompose the bags to form a standard classification problem that can be efficiently treated by a specialized noise filter. Such a decomposition is tackled in different ways, with the aim of exploiting the knowledge offered by the examples from opposite bags. The bags are then rebuilt, without the identified noise instances. In our experiments, we show that by applying our approach we can diminish the impact of noise and even obtain better results at 0% noise level for several classifiers. Our approach sets out a promising approach to dealing with noise in the bags of multiple instance datasets and further improve the classification rate of the built models. [ABSTRACT FROM AUTHOR]

Abstract: When performing a classification task, we may find some data-sets with a different class distribution among their patterns. This problem is known as classification with imbalanced data-sets and it appears in many real application areas. For this reason, it has recently become a relevant topic in the area of Machine Learning. The aim of this work is to improve the behaviour of fuzzy rule based classification systems (FRBCSs) in the framework of imbalanced data-sets by means of a tuning step. Specifically, we adapt the 2-tuples based genetic tuning approach to classification problems showing the good synergy between this method and some FRBCSs. Our empirical results show that the 2-tuples based genetic tuning increases the performance of FRBCSs in all types of imbalanced data. Furthermore, when the initial Rule Base, built by a fuzzy rule learning methodology, obtains a good behaviour in terms of accuracy, we achieve a higher improvement in performance for the whole model when applying the genetic 2-tuples post-processing step. This enhancement is also obtained in the case of cooperation with a preprocessing stage, proving the necessity of rebalancing the training set before the learning phase when dealing with imbalanced data. [Copyright &y& Elsevier]

Urban resettlement projects involve a large number of stakeholders and impose tremendous cost. Developing resettlement plans and reaching an agreement amongst stakeholders about resettlement plans at a reasonable cost are some of the key issues in urban resettlement. From this perspective, urban resettlement is a typical large-scale group decision-making (GDM) problem, which is challenging because of the scale of participants and the requirement of high consensus levels. Observing that residents who are affected by a resettlement project often have tight social connections, this study proposes a framework to improve the consensus reaching and uses the minimum consensus cost to reduce the total cost for urban resettlement projects with more than 1000 participants. Firstly, we construct a network topology that consists of two layers to deal with incomplete social relationships amongst large-scale participants. An inner layer consists of participants whose preference similarities and trust relations are known. Meanwhile, an outside layer includes participants whose trust relations cannot be determined. Secondly, we develop a classification method to classify participants into small subgroups based on their preference similarities. We can then connect the participants whose trust relations are unknown (the outside layer) with the ones in the inner layer using the classification results. To facilitate effective consensus reaching in large-scale social network GDM, we develop a three-step approach to reconcile conflicting preferences and accelerate the consensus process at the minimum cost. A real-life urban resettlement example is used to validate the proposed approach. Results show that the proposed approach can reduce the total consensus cost compared with the other two practices used in the actual urban resettlement operations. [ABSTRACT FROM AUTHOR]

• An adaptive and transfer guided metaheuristic is proposed for Evolutionary Multitasking. • Synergies between tasks are analyzed along the search in a dynamic way. • 4 different combinatorial optimization problems have been considered. • 11 multitasking scenarios are solved comprised by 5 to 20 instances. • Proposed AT-MFCGA is compared with MFEA, MFEA-II and MFCGA. Transfer Optimization is an incipient research area dedicated to solving multiple optimization tasks simultaneously. Among the different approaches that can address this problem effectively, Evolutionary Multitasking resorts to concepts from Evolutionary Computation to solve multiple problems within a single search process. In this paper we introduce a novel adaptive metaheuristic algorithm to deal with Evolutionary Multitasking environments coined as Adaptive Transfer-guided Multifactorial Cellular Genetic Algorithm (AT-MFCGA). AT-MFCGA relies on cellular automata to implement mechanisms in order to exchange knowledge among the optimization problems under consideration. Furthermore, our approach is able to explain by itself the synergies among tasks that were encountered and exploited during the search, which helps us to understand interactions between related optimization tasks. A comprehensive experimental setup is designed to assess and compare the performance of AT-MFCGA to that of other renowned Evolutionary Multitasking alternatives (MFEA and MFEA-II). Experiments comprise 11 multitasking scenarios composed of 20 instances of 4 combinatorial optimization problems, yielding the largest discrete multitasking environment solved to date. Results are conclusive in regard to the superior quality of solutions provided by AT-MFCGA with respect to the rest of the methods, which are complemented by a quantitative examination of the genetic transferability among tasks throughout the search process. [ABSTRACT FROM AUTHOR]

This paper proposes a consensus model for multi-experts multi-criteria decision making (MEMCDM) problems with probabilistic linguistic term sets (PLTSs), which also considers the regret-rejoice emotions of decision makers (DMs) in their decision-making processes. Additionally, the Dempster-Shafer theory is applied to estimate the probability of the market status which is related to the perceived values of the alternatives. Moreover, an algorithm is given to determine the weight of each DM. Then, a detailed consensus procedure is proposed and an illustrative example is used to show the feasibility of the proposed model. Finally, some comparative analyses are carried out to demonstrate the advantages of the proposed consensus process. [ABSTRACT FROM AUTHOR]

• A novel definition of concentration degree for probabilistic linguistic term sets. • A novel score function for probabilistic linguistic term sets. • Two decision-making methods are proposed for probabilistic linguistic term sets. • The effectiveness and robustness of decision-making methods are tested. Probabilistic linguistic term sets (PLTSs) can express the qualitative information of decision makers more accurately in the complicated linguistic setting. However, the existing comparison methods for PLTSs cannot compare some special PLTSs. To tackle this problem, a novel score function based on the concentration degree of an PLTS, called ScoreC-PLTS, is proposed. Additionally, the existing distance measures may distort the original information and lead to unreasonable results. Therefore, a novel probability splitting algorithm is proposed to preprocess PLTSs, based on which, a novel generalized hybrid distance is proposed for PLTSs. Moreover, a novel multiplicative analytic hierarchy process (MAHP) based on ScoreC-PLTS is proposed to determine the weight vector of attributes. Based on the generalized hybrid distance and MAHP, two novel TOPSIS-ScoreC-PLTS and VIKOR-ScoreC-PLTS methods are put forward to handle multi-attribute decision-making problems with PLTSs. Afterwards, an illustrative example concerning the selection of children English educational organization is solved using the proposed TOPSIS-ScoreC-PLTS and VIKOR-ScoreC-PLTS methods. In this example, four indicators are developed and the superiority of our studies is verified by comparing with the previous TOPSIS and VIKOR methods. [ABSTRACT FROM AUTHOR]

• A novel definition of concentration degree for probabilistic linguistic term sets. • A novel score function for probabilistic linguistic term sets. • Two decision-making methods are proposed for probabilistic linguistic term sets. • The effectiveness and robustness of decision-making methods are tested. Probabilistic linguistic term sets (PLTSs) can express the qualitative information of decision makers more accurately in the complicated linguistic setting. However, the existing comparison methods for PLTSs cannot compare some special PLTSs. To tackle this problem, a novel score function based on the concentration degree of an PLTS, called ScoreC-PLTS, is proposed. Additionally, the existing distance measures may distort the original information and lead to unreasonable results. Therefore, a novel probability splitting algorithm is proposed to preprocess PLTSs, based on which, a novel generalized hybrid distance is proposed for PLTSs. Moreover, a novel multiplicative analytic hierarchy process (MAHP) based on ScoreC-PLTS is proposed to determine the weight vector of attributes. Based on the generalized hybrid distance and MAHP, two novel TOPSIS-ScoreC-PLTS and VIKOR-ScoreC-PLTS methods are put forward to handle multi-attribute decision-making problems with PLTSs. Afterwards, an illustrative example concerning the selection of children English educational organization is solved using the proposed TOPSIS-ScoreC-PLTS and VIKOR-ScoreC-PLTS methods. In this example, four indicators are developed and the superiority of our studies is verified by comparing with the previous TOPSIS and VIKOR methods. [ABSTRACT FROM AUTHOR]

Deep learning models like chatGPT exemplify AI success but necessitate a deeper understanding of trust in critical sectors. Trust can be achieved using counterfactual explanations, which is how humans become familiar with unknown processes; by understanding the hypothetical input circumstances under which the output changes. We argue that the generation of counterfactual explanations requires several aspects of the generated counterfactual instances, not just their counterfactual ability. We present a framework for generating counterfactual explanations that formulate its goal as a multiobjective optimization problem balancing three objectives: plausibility; the intensity of changes; and adversarial power. We use a generative adversarial network to model the distribution of the input, along with a multiobjective counterfactual discovery solver balancing these objectives. We demonstrate the usefulness of six classification tasks with image and 3D data confirming with evidence the existence of a trade-off between the objectives, the consistency of the produced counterfactual explanations with human knowledge, and the capability of the framework to unveil the existence of concept-based biases and misrepresented attributes in the input domain of the audited model. Our pioneering effort shall inspire further work on the generation of plausible counterfactual explanations in real-world scenarios where attribute-/concept-based annotations are available for the domain under analysis. • Trustworthy counterfactuals: plausibility, change intensity, adversarial power. • Reliability: detecting bias and data misrepresentation in deep learning models. • Generating realistic counterfactual examples for improved trust in deep learning. [ABSTRACT FROM AUTHOR]

• We propose the unique axiomatic distance in the linguistic context. • The axiomatic distance determines the ideal linguistic distance function. • We present a novel consensus model based on the axiomatic distance. The axiomatic distance-based method is a powerful tool to aggregate individual preferences, and the extant axiomatic distance-based aggregation methods are with regard to individual numerical preferences. However, in some real-world decision problems with qualitative aspects, it is more convenient and natural for individuals to express their preferences through linguistic terms rather than through numerical values. Therefore, in this paper, we propose axiomatic distance in the linguistic context based on ordered linguistic term sets to aggregate individual linguistic preferences. Specifically, we provide some natural axioms on the distance measure among linguistic preferences. We then prove that there exists a unique distance function that satisfies all the proposed axioms. Based on the axiomatic distance function, we aggregate individual linguistic preferences into the group linguistic preference, which minimizes the total distance among individual linguistic preferences. Furthermore, we present a novel consensus measure based on the unique axiomatic distance and develop a minimum cost consensus model to obtain the optimal adjusted linguistic preference, which serves as a reference for the moderator to persuade individuals to modify their linguistic preferences. [ABSTRACT FROM AUTHOR]

Existing opinion dynamics models often fail to consider the relationship between one agent and people two degrees of separation from the agent. In addition, no accurate weight determination method has yet been fully developed. To address these limitations, this paper proposes a two-step communication opinion dynamics model based on the classical DeGroot model. Self-persistence is introduced to measure the individual's adherence to the initial opinion, and a new weight determination method proposed that instead of distributing the weights evenly, defines an influence index that is calculated from the self-persistence and node degrees. To guide public opinion using the proposed opinion dynamics model, an optimization model is established by assuming a connected network; however, when the given network is not connected, a subnetwork recognition algorithm is developed and an edge adding algorithm is proposed to alter the structure. Three opinion control strategies are then used to control the opinion formation process. Numerical examples are given to verify the flexibility and practicality of the proposed opinion control strategies, and extensive simulations over random ER networks are given to provide insights into the parameter behavior of the three strategies. [ABSTRACT FROM AUTHOR]

• Refining crude oil is a highly complex industrial process, subject to a large number of variables. • We propose a novel preprocessing methodology for obtaining quality data and extracting information from the data involved in the crude oil refining process. • The methodology incorporates dynamic knowledge, treatment of noise, reduction of the dimensionality, feature selection and introduction of slopes. • The proposal is validated through optimization of three state-of-the-art regressors: GB, RF and SVR. • This methodology along with SVR offer useful information for the expert of the refining process. This paper proposes a novel preprocessing methodology, framed within the field of time series forecasting. The aim is to get quality data and to extract information on the most important variables involved in a real-world crude oil refining process. To achieve this objective, the methodology incorporates the addition of dynamic knowledge, treatment of the noise present in the data, reduction of the dimensionality, feature selection and the introduction of slopes in the variables. Predictions are made for each step of the methodology and evaluated based on four measures: MAE, MSE, SMAPE and the delay in the prediction as compared to the original variable. The final solution is chosen based on these four measures and delivered to the experts so that they can optimize the crude oil refining process. [ABSTRACT FROM AUTHOR]

The hesitant fuzzy linguistic term set (HFLTS) turns out to be useful in representing people's hesitant qualitative information. The aim of this paper is to investigate new correlation measures between HFLTSs and apply them in decision-making process. Firstly, the concepts of mean and hesitancy degree of hesitant fuzzy linguistic elements are introduced. Based on them, we address the drawbacks of the existing correlation measures between HFLTSs. Then, a new correlation coefficient between HFLTSs is established. Additionally, the hesitancy degree of the hesitant fuzzy linguistic correlation coefficient is proposed, which is composed by the upper and lower bounds of the hesitant fuzzy linguistic correlation coefficient. To show the applicability of the proposed correlation measures, a correlation coefficient-based method is developed for multiple criteria decision making in the cases that the weights of criteria are either known or unknown. A practical example concerning the strategic management of Sichuan liquor brands in China is given to validate the proposed method. It is verified that the proposed correlation coefficients between HFLTSs is more convincing than the existing ones and the developed correlation coefficient-based hesitant fuzzy linguistic MCDM with the weights of criteria being either completely known or unknown is applicable. [ABSTRACT FROM AUTHOR]

Due to the development of intelligent decision-making, social network group decision-making (SNGDM) has become increasingly valued. Generally, real SNGDM cases involve not only the mathematical formulation of the social network analysis but also the experts' psychological behaviors. Self-confidence, an expert's psychological implication of self-statement, is a significant topic in SNGDM problems, while it is overlooked in most existing research. To address this issue, this study takes experts' self-confidence into account in SNGDM. All experts use self-confident fuzzy preference relations (SC-FPRs) to express their opinions. Subsequently, we have developed a novel self-confidence-based consensus approach for SNGDM with SC-FPRs. A dynamic importance degree of experts which combines the external trust and internal self-confidence is proposed to determine their weights. A consensus index considering self-confidence is defined to assess the consensus level among experts. Meanwhile, a trust-based feedback mechanism is presented to improve the consensus efficiency. The rule of the feedback mechanism is that experts dynamically adjust their self-confidence levels while revising the preferences. Using a self-confidence score function, an alternative that has the highest self-confidence score can be selected as the best solution. An illustrative example and some comparisons are given to verify the feasibility and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

• We define double hierarchy hesitant fuzzy linguistic preference relation (DHHFLPR). • A novel method is developed to calculate the consistency thresholds. • Two consistency repairing algorithms is proposed to improve the DHHFLPR. • A method is set up to deal with GDM problems with DHHFLPRs. • The proposed method is validated by a practical group decision making problem. Group decision making, refers to inviting a group of decision makers to evaluate, prioritize or select the optimal one among some available alternatives in the actual decision making process. Considering that the double hierarchy hesitant fuzzy linguistic term set can describe natural languages clearly, in this paper, we define the concept of double hierarchy hesitant fuzzy linguistic preference relation (DHHFLPR) and propose some additive consistency measures. To judge whether a DHHFLPR is of acceptable consistency or not, we introduce a consistency index, and develop some novel threshold values for judging whether a DHHFLPR is of acceptable consistency or not. Furthermore, we develop two consistency repairing algorithms based on the automatic improving method and the feedback improving method respectively, to improve the DHHFLPR with unacceptable consistency. Additionally, a method is set up to deal with group decision making problems with double hierarchy hesitant fuzzy linguistic preference information. Finally, the proposed method is validated by a case study that is used to evaluate the water resource situations of some important cities in Sichuan Province, and some comparative analyses are given to show the efficiency of the proposed method. [ABSTRACT FROM AUTHOR]

Highlights • We study the consensus formation and convergence speed in the SNDG model. • We show the rule to determine agents' weights to form a consensus. • We show the rule to determine the convergence speed when reaching a consensus. Abstract In this paper, we investigate how the agent's self-confidence level and the node degree influence the consensus opinion formation and the consensus convergence speed in the social network DeGroot model. We find that (1) the higher self-confidence will increase the agent's importance degree to determine the consensus opinion, but will also slow down the convergence speed for all agents to be able to obtain consensus, and (2) it is conducive to accelerating the convergence speed to be able to reach a consensus where all agents can manage to balance self-confidence levels and node degrees in the social network. [ABSTRACT FROM AUTHOR]

Highlights • Domain adaptation is one of the main challenges of sentiment analysis. • Most polarity detection methods are focused on a specific domain. • Ensemble methods may improve the performance of a set of polarity detection methods. • Evolutionary algorithms may find out the right combination of polarity classification methods in an ensemble classifier. • The results show that our claim holds on 13 corpora. Abstract Currently, a plethora of industrial and academic sentiment analysis methods for classifying the opinion polarity of a text are available and ready to use. However, each of those methods have their strengths and weaknesses, due mainly to the approach followed in their design (supervised/unsupervised) or the domain of text used in their development. The weaknesses are usually related to the capacity of generalisation of machine learning algorithms, and the lexical coverage of linguistic resources. Those issues are two of the main causes of one of the challenges of Sentiment Analysis, namely the domain adaptation problem. We argue that the right ensemble of a set of heterogeneous Sentiment Analysis Methods will lessen the domain adaptation problem. Thus, we propose a new methodology for optimising the contribution of a set of off-the-shelf Sentiment Analysis Methods in an ensemble classifier depending on the domain of the input text. The results clearly show that our claim holds. [ABSTRACT FROM AUTHOR]

Highlights • We have tackled the problem of noise in Big Data classification. • Two Big Data preprocessing approaches to remove noisy examples are proposed: HME-BD and HTE-BD. • HME-BD is a homogeneous ensemble filter, while HTE-BD is a heterogeneous ensemble filter. • The proposed algorithms constitute a first suitable noise filtering approach in Big Data domains. Abstract In any knowledge discovery process the value of extracted knowledge is directly related to the quality of the data used. Big Data problems, generated by massive growth in the scale of data observed in recent years, also follow the same dictate. A common problem affecting data quality is the presence of noise, particularly in classification problems, where label noise refers to the incorrect labeling of training instances, and is known to be a very disruptive feature of data. However, in this Big Data era, the massive growth in the scale of the data poses a challenge to traditional proposals created to tackle noise, as they have difficulties coping with such a large amount of data. New algorithms need to be proposed to treat the noise in Big Data problems, providing high quality and clean data, also known as Smart Data. In this paper, two Big Data preprocessing approaches to remove noisy examples are proposed: an homogeneous ensemble and an heterogeneous ensemble filter, with special emphasis in their scalability and performance traits. The obtained results show that these proposals enable the practitioner to efficiently obtain a Smart Dataset from any Big Data classification problem. [ABSTRACT FROM AUTHOR]

Highlights • We designed and implemented a novel sampling scheme based on monotonic chains in order to preverse monotonicity while obtaining a balanced set. • This scheme has been included in five famous under- and over-sampling approaches: Random Under-Sampling, Random Over-Sampling, SMOTE, ADASYN and MWMOTE. • Empirically, we show the deterioration of the monotonicity degree in 8 data-sets caused by standard and ordinal sampling approaches, invalidating their use for monotonic classification. • We compare our new monotonic sampling techniques versus their standard versions, achieving a better monotonicity preservation than the standard ones with the same improvement of predictability. Abstract Classification with monotonic constraints arises from some ordinal real-life problems. In these real-life problems, it is common to find a big difference in the number of instances representing middle-ranked classes and the top classes, because the former usually represents the average or the normality, while the latter are the exceptional and uncommon. This is known as class imbalance problem, and it deteriorates the learning of those under-represented classes. However, the traditional solutions cannot be applied to applications that require monotonic restrictions to be asserted. Since these were not designed to consider monotonic constraints, they compromise the monotonicity of the data-sets and the performance of the monotonic classifiers. In this paper, we propose a set of new sampling techniques to mitigate the imbalanced class distribution and, at the same time, maintain the monotonicity of the data-sets. These methods perform the sampling inside monotonic chains, sets of comparable instances, in order to preserve them and, as a result, the monotonicity. Five different approaches are redesigned based on famous under- and over-sampling techniques and their standard and ordinal versions are compared with outstanding results. [ABSTRACT FROM AUTHOR]

Many real-world classification tasks suffer from the class imbalanced problem, in which some classes are highly underrepresented as compared to other classes. In this paper, we focus on multi-class imbalance problems which are considerably more difficult to address than two-class imbalanced problems. On this account, we develop a novel and effective procedure, called dynamic ensemble selection for multi-class imbalanced datasets (DES-MI), in which the competence of the candidate classifiers are assessed with weighted instances in the neighborhood. The proposed DES-MI consists of two key components: the generation of balanced training datasets and the selection of appropriate classifiers. To do so, we develop a preprocessing procedure to balance the training dataset which relies on random balance. To select the most appropriate classifiers in the scenario of multi-class imbalance problems, we propose a weighting mechanism to highlight the competence of classifiers that are more powerful in classifying examples in the region of underrepresented competence. We develop a thorough experimental study in order to verify the benefits of DES-MI in handling multi-class imbalanced datasets. The obtained results, supported by the proper statistical analysis, indicate that DES-MI is able to improve the classification performance for multi-class imbalanced datasets. [ABSTRACT FROM AUTHOR]

The study of hesitant consistency is very important in decision-making with hesitant fuzzy linguistic preference relations (HFLPRs), and generally the normalization method is used as a tool to measure the consistency degree of a HFLPR. In this paper we propose a new hesitant consistency measure, called interval consistency index, to estimate the consistency range of a HFLPR. The underlying idea of the interval consistency index consists of measuring the worst consistency index and the best consistency index of a HFLPR. Furthermore, by comparative study, a connection is shown between the interval consistency index and the normalization method, demonstrating that the normalization method should be considered as an approximate average consistency index of a HFLPR. [ABSTRACT FROM AUTHOR]

The hesitant fuzzy linguistic term set (HFLTS) is applicable in expressing people's hesitant qualitative preference information. However, it may lose preference information as all the terms in the HFLTS are assigned the same weight. The probabilistic linguistic term set (PLTS) can avoid this drawback by allowing the decision makers (DMs) to give the weight of each linguistic term as a probability. Due to the flexibility of the PLTS, the multiple criteria decision making (MCDM) with probabilistic linguistic information is now becoming a hot research topic. The aim of this paper is to propose a linear programming method to solve the MCDM problems, in which the DMs’ preferences over the alternatives with respect to the given criteria are expressed as the PLTSs. We first give the weighted deviation square measure for the normalized probabilistic linguistic positive ideal solution and each normalized probabilistic linguistic evaluation vector of each alternative. Then, we define the inconsistency index and the consistency index according to the objective and subjective evaluations given by the DMs, based on which a linear programming model is then built to derive the weight of each criterion. Furthermore, a linear programming method is developed to solve the MCDM problems with probabilistic linguistic information, and a case study about the evaluation of hospitals is conducted to illustrate the proposed method. Finally, some comparative analyses with the aggregation operator-based method and the probabilistic linguistic preference ranking organization method for enrichment evaluation (PL-PROMETHEE) method are made to show the advantages of the proposed method. [ABSTRACT FROM AUTHOR]

Fingerprint recognition, and in particular minutiae-based matching methods, are ever more deeply implanted into many companies and institutions. As the size of their identification databases grows, there is a need of flexible, reliable structures for fingerprint recognition systems. In this paper, we propose a generic decomposition methodology for minutiae-based matching algorithms that splits the calculation of the matching scores into lower level steps that can be carried out in parallel in a flexible manner. The decomposition allows to adapt any minutiae-based algorithm to frameworks such as MapReduce or Apache Spark. General and specific guidelines to enhance the performance of the adapted matching algorithms are also described. The proposal is evaluated over two matching algorithms, two Big Data frameworks (Apache Hadoop and Apache Spark) and two large-scale fingerprint databases, with promising results concerning the identification time, in addition to the reliability, scalability, distribution and availability capabilities that are provided by such underlying frameworks. [ABSTRACT FROM AUTHOR]

Opinion dynamics investigates the fusion process of the opinion formation in a group of agents, and is a powerful tool for supporting the management of public opinions. However, in real-life situations, firms or administrations are not only interested in the formation of public opinions, but also hope to influence and guide the forming opinions to reach either a consensus or even more a specific consensus point. This paper aims at developing a consensus building process in opinion dynamics, based on the concept leadership, by analyzing the structure of the social network in which all agents can form a consensus. It is then proposed a strategy adding a minimum number of interactions in the social network to form a consensus based on leadership, and afterwards it is generalized the consensus strategy to deal with the consensus problem with an established target. Eventually, detailed theoretical proofs and numerical analysis are provided to demonstrate the feasibility and effectiveness of the consensus strategy. [ABSTRACT FROM AUTHOR]

The k nearest neighbor ( k NN) rule is one of the most used techniques in data mining and pattern recognition due to its simplicity and low identification error. However, the computational effort it requires is directly related to the dataset sizes, hence delivering a poor performance on large datasets. The use of graphics processing units (GPU) has improved the run-time performance of the k NN rule but the computational requirements of current approaches limit this performance as the dataset size increases. In this paper, we propose a new scalable and memory efficient design for a GPU-based k NN rule, called GPU-SME- k NN, that breaks the dependency between dataset size and memory footprint while delivering high performance. An experimental study of GPU-SME- k NN is presented showing a high performance, even in cases that other methods cannot address, while the computational requirements are suitable for most commercial GPU devices. Our design has also been applied to k NN-based lazy learning algorithms reducing run-times in a significant way. [ABSTRACT FROM AUTHOR]

The scenario of classification with imbalanced datasets has gained a notorious significance in the last years. This is due to the fact that a large number of problems where classes are highly skewed may be found, affecting the global performance of the system. A great number of approaches have been developed to address this problem. These techniques have been traditionally proposed under three different perspectives: data treatment, adaptation of algorithms, and cost-sensitive learning. Ensemble-based models for classifiers are an extension over the former solutions. They consider a pool of classifiers, and they can in turn integrate any of these proposals. The quality and performance of this type of methodology over baseline solutions have been shown in several studies of the specialized literature. The goal of this work is to improve the capabilities of tree-based ensemble-based solutions that were specifically designed for imbalanced classification, focusing on the best behaving bagging- and boosting-based ensembles in this scenario. In order to do so, this paper proposes several new metrics for ordering-based pruning, which are properly adapted to address the skewed-class distribution. From our experimental study we show two main results: on the one hand, the use of the new metrics allows pruning to become a very successful approach in this scenario; on the other hand, the behavior of Under-Bagging model excels, achieving the highest gain with the usage of pruning, since the random undersampled sets that best complement each other can be selected. Accordingly, this scheme is capable of outperforming previous ensemble models selected from the state-of-the-art. [ABSTRACT FROM AUTHOR]

One of the most known and effective methods in supervised classification is the k -nearest neighbors classifier. Several approaches have been proposed to enhance its precision, with the fuzzy k -nearest neighbors (fuzzy- k NN) classifier being among the most successful ones. However, despite its good behavior, fuzzy- k NN lacks of a method for properly defining several mechanisms regarding the representation of the relationship between the instances and the classes of the classification problems. Such a method would be very desirable, since it would potentially lead to an improvement in the precision of the classifier. In this work we present a new approach, evolutionary fuzzy k -nearest neighbors classifier using interval-valued fuzzy sets (EF- k NN-IVFS), incorporating interval-valued fuzzy sets for computing the memberships of training instances in fuzzy- k NN. It is based on the representation of multiple choices of two key parameters of fuzzy- k NN: one is applied in the definition of the membership function, and the other is used in the computation of the voting rule. Besides, evolutionary search techniques are incorporated to the model as a self-optimization procedure for setting up these parameters. An experimental study has been carried out to assess the capabilities of our approach. The study has been validated by using nonparametric statistical tests, and remarks the strong performance of EF- k NN-IVFS compared with several state of the art techniques in fuzzy nearest neighbor classification. [ABSTRACT FROM AUTHOR]

Fingerprint recognition has found a reliable application for verification or identification of people in biometrics. Globally, fingerprints can be viewed as valuable traits due to several perceptions observed by the experts; such as the distinctiveness and the permanence on humans and the performance in real applications. Among the main stages of fingerprint recognition, the automated matching phase has received much attention from the early years up to nowadays. This paper is devoted to review and categorize the vast number of fingerprint matching methods proposed in the specialized literature. In particular, we focus on local minutiae-based matching algorithms, which provide good performance with an excellent trade-off between efficacy and efficiency. We identify the main properties and differences of existing methods. Then, we include an experimental evaluation involving the most representative local minutiae-based matching models in both verification and evaluation tasks. The results obtained will be discussed in detail, supporting the description of future directions. [ABSTRACT FROM AUTHOR]

Classification datasets often have an unequal class distribution among their examples. This problem is known as imbalanced classification. The Synthetic Minority Over-sampling Technique (SMOTE) is one of the most well-know data pre-processing methods to cope with it and to balance the different number of examples of each class. However, as recent works claim, class imbalance is not a problem in itself and performance degradation is also associated with other factors related to the distribution of the data. One of these is the presence of noisy and borderline examples, the latter lying in the areas surrounding class boundaries. Certain intrinsic limitations of SMOTE can aggravate the problem produced by these types of examples and current generalizations of SMOTE are not correctly adapted to their treatment. This paper proposes the extension of SMOTE through a new element, an iterative ensemble-based noise filter called Iterative-Partitioning Filter (IPF), which can overcome the problems produced by noisy and borderline examples in imbalanced datasets. This extension results in SMOTE–IPF. The properties of this proposal are discussed in a comprehensive experimental study. It is compared against a basic SMOTE and its most well-known generalizations. The experiments are carried out both on a set of synthetic datasets with different levels of noise and shapes of borderline examples as well as real-world datasets. Furthermore, the impact of introducing additional different types and levels of noise into these real-world data is studied. The results show that the new proposal performs better than existing SMOTE generalizations for all these different scenarios. The analysis of these results also helps to identify the characteristics of IPF which differentiate it from other filtering approaches. [ABSTRACT FROM AUTHOR]

The analysis of the performance of different approaches is a staple concern in the design of Computational Intelligence experiments. Any proper analysis of evolutionary optimization algorithms should incorporate a full set of benchmark problems and state-of-the-art comparison algorithms. For the sake of rigor, such an analysis may be completed with the use of statistical procedures, supporting the conclusions drawn. In this paper, we point out that these conclusions are usually limited to the final results, whereas intermediate results are seldom considered. We propose a new methodology for comparing evolutionary algorithms’ convergence capabilities, based on the use of Page’s trend test. The methodology is presented with a case of use, incorporating real results from selected techniques of a recent special issue. The possible applications of the method are highlighted, particularly in those cases in which the final results do not enable a clear evaluation of the differences among several evolutionary techniques. [ABSTRACT FROM AUTHOR]

The package RoughSets , written mainly in the R language, provides implementations of methods from the rough set theory (RST) and fuzzy rough set theory (FRST) for data modeling and analysis. It considers not only fundamental concepts (e.g., indiscernibility relations, lower/upper approximations, etc.), but also their applications in many tasks: discretization, feature selection, instance selection, rule induction, and nearest neighbor-based classifiers. The package architecture and examples are presented in order to introduce it to researchers and practitioners. Researchers can build new models by defining custom functions as parameters, and practitioners are able to perform analysis and prediction of their data using available algorithms. Additionally, we provide a review and comparison of well-known software packages. Overall, our package should be considered as an alternative software library for analyzing data based on RST and FRST. [ABSTRACT FROM AUTHOR]

In this age, big data applications are increasingly becoming the main focus of attention because of the enormous increment of data generation and storage that has taken place in the last years. This situation becomes a challenge when huge amounts of data are processed to extract knowledge because the data mining techniques are not adapted to the new space and time requirements. Furthermore, real-world data applications usually present a class distribution where the samples that belong to one class, which is precisely the main interest, are hugely outnumbered by the samples of the other classes. This circumstance, known as the class imbalance problem, complicates the learning process as the standard learning techniques do not correctly address this situation. In this work, we analyse the performance of several techniques used to deal with imbalanced datasets in the big data scenario using the Random Forest classifier. Specifically, oversampling, undersampling and cost-sensitive learning have been adapted to big data using MapReduce so that these techniques are able to manage datasets as large as needed providing the necessary support to correctly identify the underrepresented class. The Random Forest classifier provides a solid basis for the comparison because of its performance, robustness and versatility. An experimental study is carried out to evaluate the performance of the diverse algorithms considered. The results obtained show that there is not an approach to imbalanced big data classification that outperforms the others for all the data considered when using Random Forest. Moreover, even for the same type of problem, the best performing method is dependent on the number of mappers selected to run the experiments. In most of the cases, when the number of splits is increased, an improvement in the running times can be observed, however, this progress in times is obtained at the expense of a slight drop in the accuracy performance obtained. This decrement in the performance is related to the lack of density problem, which is evaluated in this work from the imbalanced data point of view, as this issue degrades the performance of classifiers in the imbalanced scenario more severely than in standard learning. [ABSTRACT FROM AUTHOR]

Abstract: One-vs-One strategy divides the original multi-class problem into as many binary classification problems as pairs of classes. Then, independent base classifiers are learned to face each problem, whose outputs are combined to predict a single class label. This way, the accuracy of the baseline classifiers without decomposition is usually enhanced, aside from enabling the usage of binary classifiers, i.e., Support Vector Machines, to solve multi-class problems. This paper analyzes the fact that existing aggregations favor easily recognizable classes; hence, the accuracy enhancement mainly comes from the higher correct classification rates over these classes. Using other evaluation criteria, the significant improvements of One-vs-One are diminished, showing a weakness due to the presence of difficult classes. Difficult classes can be defined as those obtaining a lower correct classification rate than that obtained by the other classes in the problem. After studying the problem of difficult classes in this framework and aiming to empower these classes, a novel similarity-based aggregation is presented, which generalizes the well-known weighted voting. The experimental analysis shows that the new methodology is able to increase the recognition of difficult classes, obtaining a more balanced performance over all classes, which is a desirable behavior. The methodology is tested within several Machine Learning paradigms and is compared with the state-of-the-art on aggregations for One-vs-One strategy. The results are contrasted by the proper statistical tests, as suggested in the literature. [Copyright &y& Elsevier]

Abstract: Training classifiers with datasets which suffer of imbalanced class distributions is an important problem in data mining. This issue occurs when the number of examples representing the class of interest 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. We shortly review the many issues in machine learning and applications of this problem, by introducing the characteristics of the imbalanced dataset scenario in classification, presenting the specific metrics for evaluating performance in class imbalanced learning and enumerating the proposed solutions. In particular, we will describe preprocessing, cost-sensitive learning and ensemble techniques, carrying out an experimental study to contrast these approaches in an intra and inter-family comparison. We will carry out a thorough discussion on the main issues related to using data intrinsic characteristics in this classification problem. This will help to improve the current models with respect to: the presence of small disjuncts, the lack of density in the training data, the overlapping between classes, the identification of noisy data, the significance of the borderline instances, and the dataset shift between the training and the test distributions. Finally, we introduce several approaches and recommendations to address these problems in conjunction with imbalanced data, and we will show some experimental examples on the behavior of the learning algorithms on data with such intrinsic characteristics. [Copyright &y& Elsevier]