@article {LOPEZ201385, title = {A hierarchical genetic fuzzy system based on genetic programming for addressing classification with highly imbalanced and borderline data-sets}, journal = {Knowledge-Based Systems}, volume = {38}, year = {2013}, note = {Special Issue on "Advances in Fuzzy Knowledge Systems: Theory and Application"}, pages = {85 - 104}, abstract = {Lots of real world applications appear to be a matter of classification with imbalanced data-sets. This problem arises when the number of instances from one class is quite different to the number of instances from the other class. Traditionally, classification algorithms are unable to correctly deal with this issue as they are biased towards the majority class. Therefore, algorithms tend to misclassify the minority class which usually is the most interesting one for the application that is being sorted out. Among the available learning approaches, fuzzy rule-based classification systems have obtained a good behavior in the scenario of imbalanced data-sets. In this work, we focus on some modifications to further improve the performance of these systems considering the usage of information granulation. Specifically, a positive synergy between data sampling methods and algorithmic modifications is proposed, creating a genetic programming approach that uses linguistic variables in a hierarchical way. These linguistic variables are adapted to the context of the problem with a genetic process that combines rule selection with the adjustment of the lateral position of the labels based on the 2-tuples linguistic model. An experimental study is carried out over highly imbalanced and borderline imbalanced data-sets which is completed by a statistical comparative analysis. The results obtained show that the proposed model outperforms several fuzzy rule based classification systems, including a hierarchical approach and presents a better behavior than the C4.5 decision tree.}, keywords = {Borderline examples, Fuzzy rule based classification systems, Genetic rule selection, Hierarchical fuzzy partitions, Imbalanced data-sets, Tuning}, issn = {0950-7051}, doi = {https://doi.org/10.1016/j.knosys.2012.08.025}, url = {http://www.sciencedirect.com/science/article/pii/S0950705112002596}, author = {Victoria L{\'o}pez and Alberto Fernandez and M. J. del Jesus and F. Herrera} } @article {FERNANDEZ201397, title = {Analysing the classification of imbalanced data-sets with multiple classes: Binarization techniques and ad-hoc approaches}, journal = {Knowledge-Based Systems}, volume = {42}, year = {2013}, pages = {97 - 110}, 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.}, keywords = {Cost-sensitive learning, Imbalanced data-sets, Multi-classification, Pairwise learning, Preprocessing}, issn = {0950-7051}, doi = {https://doi.org/10.1016/j.knosys.2013.01.018}, url = {http://www.sciencedirect.com/science/article/pii/S0950705113000300}, author = {Alberto Fernandez and Victoria L{\'o}pez and Mikel Galar and M. J. del Jesus and F. Herrera and ELSEVIER SCIENCE BV} }