Search

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]

Thomson Reuters' Web of Science (WoS) is undoubtedly a great tool for scientiometrics purposes. It allows one to retrieve and compute different measures such as the total number of papers that satisfy a particular condition; however, it also is well known that this tool imposes several different restrictions that make obtaining certain results difficult. One of those constraints is that the tool does not offer the total count of documents in a dataset if it is larger than 100,000 items. In this article, we propose and analyze different approaches that involve partitioning the search space (using the Source field) to retrieve item counts for very large datasets from the WoS. The proposed techniques improve previous approaches: They do not need any extra information about the retrieved dataset (thus allowing completely automatic procedures to retrieve the results), they are designed to avoid many of the restrictions imposed by the WoS, and they can be easily applied to almost any query. Finally, a description of WoS Query Partitioner, a freely available and online interactive tool that implements those techniques, is presented. [ABSTRACT FROM AUTHOR]

Current tools and techniques devoted to examine the content of large databases are often hampered by their inability to support searches based on criteria that are meaningful to their users. These shortcomings are particularly evident in data banks storing representations of structural data such as biological networks. Conceptual clustering techniques have demonstrated to be appropriate for uncovering relationships between features that characterize objects in structural data. However, typical conceptual clustering approaches normally recover the most obvious relations, but fail to discover the less frequent but more informative underlying data associations. The combination of evolutionary algorithms with multiobjective and multimodal optimization techniques constitutes a suitable tool for solving this problem. We propose a novel conceptual clustering methodology termed evolutionary multiobjective conceptual clustering (EMO-CC), relying on the NSGA-II multiobjective (MO) genetic algorithm. We apply this methodology to identify conceptual models in structural databases generated from gene ontologies. These models can explain and predict phenotypes in the immunoinflammatory response problem, similar to those provided by gene expression or other genetic markers. The analysis of these results reveals that our approach uncovers cohesive clusters, even those comprising a small number of observations explained by several features, which allows describing objects and their interactions from different perspectives and at different levels of detail. [ABSTRACT FROM AUTHOR]

The k‐nearest neighbors algorithm is characterized as a simple yet effective data mining technique. The main drawback of this technique appears when massive amounts of data—likely to contain noise and imperfections—are involved, turning this algorithm into an imprecise and especially inefficient technique. These disadvantages have been subject of research for many years, and among others approaches, data preprocessing techniques such as instance reduction or missing values imputation have targeted these weaknesses. As a result, these issues have turned out as strengths and the k‐nearest neighbors rule has become a core algorithm to identify and correct imperfect data, removing noisy and redundant samples, or imputing missing values, transforming Big Data into Smart Data—which is data of sufficient quality to expect a good outcome from any data mining algorithm. The role of this smart data gleaning algorithm in a supervised learning context are investigated. This includes a brief overview of Smart Data, current and future trends for the k‐nearest neighbor algorithm in the Big Data context, and the existing data preprocessing techniques based on this algorithm. We present the emerging big data‐ready versions of these algorithms and develop some new methods to cope with Big Data. We carry out a thorough experimental analysis in a series of big datasets that provide guidelines as to how to use the k‐nearest neighbor algorithm to obtain Smart/Quality Data for a high‐quality data mining process. Moreover, multiple Spark Packages have been developed including all the Smart Data algorithms analyzed. This article is categorized under:Technologies > Data PreprocessingFundamental Concepts of Data and Knowledge > Big Data MiningTechnologies > Classification The k‐nearest neighbors algorithm plays a key role to cope with Big Data by transforming it into Smart data that is free of redundant information, noise and/or missing values. Gleaning quality data is essential for a correct data mining process that will uncover valuable insights. [ABSTRACT FROM AUTHOR]

Abstract: Prototype selection problem consists of reducing the size of databases by removing samples that are considered noisy or not influential on nearest neighbour classification tasks. Evolutionary algorithms have been used recently for prototype selection showing good results. However, due to the complexity of this problem when the size of the databases increases, the behaviour of evolutionary algorithms could deteriorate considerably because of a lack of convergence. This additional problem is known as the scaling up problem. Memetic algorithms are approaches for heuristic searches in optimization problems that combine a population-based algorithm with a local search. In this paper, we propose a model of memetic algorithm that incorporates an ad hoc local search specifically designed for optimizing the properties of prototype selection problem with the aim of tackling the scaling up problem. In order to check its performance, we have carried out an empirical study including a comparison between our proposal and previous evolutionary and non-evolutionary approaches studied in the literature. The results have been contrasted with the use of non-parametric statistical procedures and show that our approach outperforms previously studied methods, especially when the database scales up. [Copyright &y& Elsevier]

Obtaining data in the real world is subject to imperfections and the appearance of noise is a common consequence of such flaws. In classification, class noise will deteriorate the performance of a classifier, as it may severely mislead the model building. Among the strategies emerged to deal with class noise, the most popular is that of filtering. However, instance filtering can be harmful as it may eliminate more examples than necessary or produce loss of information. An ideal option would be relabeling the noisy instances, avoiding losing data, but instance correcting is harder to achieve and may lead to wrong information being introduced in the dataset. For this reason, we advance a new proposal based on an ensemble of noise filters with the goal not only of accurately filtering the mislabeled instances, but also correcting them when possible. A noise score is also applied to support the filtering and relabeling process. The proposal, named CNC-NOS (Class Noise Cleaner with Noise Scoring), is compared against state-of-the-art noise filters and correctors, showing that it is able to deliver a quality training instance set that overcomes the limitations of such techniques, both in terms of classification accuracy and properly treated instances. [ABSTRACT FROM AUTHOR]

Abstract: The imbalanced class problem is related to the real-world application of classification in engineering. It is characterised by a very different distribution of examples among the classes. The condition of multiple imbalanced classes is more restrictive when the aim of the final system is to obtain the most accurate precision for each of the concepts of the problem. The goal of this work is to provide a thorough experimental analysis that will allow us to determine the behaviour of the different approaches proposed in the specialised literature. First, we will make use of binarization schemes, i.e., one versus one and one versus all, in order to apply the standard approaches to solving binary class imbalanced problems. Second, we will apply several ad hoc procedures which have been designed for the scenario of imbalanced data-sets with multiple classes. This experimental study will include several well-known algorithms from the literature such as decision trees, support vector machines and instance-based learning, with the intention of obtaining global conclusions from different classification paradigms. The extracted findings will be supported by a statistical comparative analysis using more than 20 data-sets from the KEEL repository. [Copyright &y& Elsevier]