@article {792, title = {Decomposition-Fusion for Label Distribution Learning}, journal = {Information Fusion}, volume = {66}, year = {2021}, note = {TIN2017-89517-P}, month = {02/2021}, pages = {64-75}, abstract = {Label Distribution Learning (LDL) is a general learning framework that assigns an instance to a distribution over a set of labels rather than to a single label or multiple labels. Current LDL methods have proven their effectiveness in many real-life machine learning applications. However, LDL is a generalization of the classification task and as such it is exposed to the same problems as standard classification algorithms, including class-imbalanced, noise, overlapping or irregularities. The purpose of this paper is to mitigate these effects by using decomposition strategies. The technique devised, called Decomposition-Fusion for LDL (DF-LDL), is based on one of the most renowned strategy in decomposition: the One-vs-One scheme, which we adapt to be able to deal with LDL datasets. In addition, we propose a competent fusion method that allows us to discard non-competent classifiers when their output is probably not of interest. The effectiveness of the proposed DF-LDL method is verified on several real-world LDL datasets on which we have carried out two types of experiments. First, comparing our proposal with the base learners and, second, comparing our proposal with the state-of-the-art LDL algorithms. DF-LDL shows significant improvements in both experiments.}, keywords = {Decomposition strategies, Label Distribution Learning, machine learning, One vs. One}, doi = {https://doi.org/10.1016/j.inffus.2020.08.024}, author = {Gonzalez, M and Germ{\'a}n Gonz{\'a}lez-Almagro and Triguero, Isaac and J. R. Cano and Garc{\'\i}a, Salvador} } @article {793, title = {Enhancing instance-level constrained clustering through differential evolution}, journal = {Applied Soft Computing}, volume = {108}, number = {107435}, year = {2021}, note = {TIN2017-89517-P; PP2019.PRI.I.06.}, pages = {1-19}, abstract = {Clustering has always been a powerful tool in knowledge discovery. Traditionally unsupervised, it received renewed attention when it was shown to produce better results when provided with new types of information, thus leading to a new kind of semi-supervised learning: constrained clustering. This technique is a generalization of traditional clustering that considers additional information encoded by constraints. Constraints can be given in the form of instance-level must-link and cannot-link constraints, which this paper focuses on. We propose the first application of Differential Evolution to the constrained clustering problem, which has proven to produce a better exploration{\textendash}exploitation trade-off when comparing with previous approaches. We will compare the results obtained by this proposal to those obtained by previous nature-inspired techniques and by some of the state-of-the-art algorithms on 25 datasets with incremental levels of constraint-based information, supporting our conclusions with the aid of Bayesian statistical tests.}, keywords = {Cannot-link, constrained clustering, Differential evolution, Instance-level, Must-link}, doi = {https://doi.org/10.1016/j.asoc.2021.107435}, author = {Germ{\'a}n Gonz{\'a}lez-Almagro and Luengo, Juli{\'a}n and J. R. Cano and Garc{\'\i}a, Salvador} } @article {791, title = {Synthetic Sample Generation for Label Distribution Learning}, journal = {Information Sciences}, volume = {544}, year = {2021}, note = {TIN2017-89517-P}, month = {01/2021}, pages = {197-213}, abstract = {Label Distribution Learning (LDL) is a general learning framework that assigns an instance to a distribution over a set of labels rather than a single label or multiple labels. Current LDL methods have proven their effectiveness in many machine learning applications. As of the first formulation of the LDL problem, numerous studies have been carried out that apply the LDL methodology to various real-life problem solving. Others have focused more specifically on the proposal of new algorithms. The purpose of this article is to start addressing the LDL problem as of the data pre-processing stage. The baseline hypothesis is that, due to the high dimensionality of existing LDL data sets, it is very likely that this data will be incomplete and/or that poor data quality will lead to poor performance once applied to the learning algorithms. In this paper, we propose an oversampling method, which creates a superset of the original dataset by creating new instances from existing ones. Then, we apply already existing algorithms to the pre-processed training set in order to validate the effcacy of our method. The effectiveness of the proposed SSG-LDL is verified on several LDL datasets, showing significant improvements to the state-of-the-art LDL methods.}, keywords = {Data pre-processing, Label Distribution Learning, machine learning, Oversampling}, doi = {https://doi.org/10.1016/j.ins.2020.07.071}, author = {Gonzalez, M and Luengo, Juli{\'a}n and J. R. Cano and Garc{\'\i}a, Salvador} } @conference {790, title = {Agglomerative Constrained Clustering Through Similarity and Distance Recalculation}, booktitle = {International Conference on Hybrid Artificial Intelligence Systems}, year = {2020}, pages = {424-436}, abstract = {Constrained clustering has become a topic of considerable interest in machine learning, as it has been shown to produce promising results in domains where only partial information about how to solve the problem is available. Constrained clustering can be viewed as a semi-supervised generalization of clustering, which is traditionally unsupervised. It is able to leverage a new type of information encoded by constraints that guide the clustering process. In particular, this study focuses on instance-level must-link and cannot-link constraints. We propose an agglomerative constrained clustering algorithm, which combines distance-based and clustering-engine adapting methods to incorporate constraints into the partitioning process. It computes a similarity measure on the basis of distances (in the dataset) and constraints (in the constraint set) to later apply an agglomerative clustering method, whose clustering engine has been adapted to consider constraints and raw distances. We prove its capability to produce quality results for the constrained clustering problem by comparing its performance to previous proposals on several datasets with incremental levels of constraint-based information.}, keywords = {Agglomerative clustering, constrained clustering, Semi-supervised learning, Similarity recalculation}, doi = {https://doi.org/10.1007/978-3-030-61705-9_35}, author = {Germ{\'a}n Gonz{\'a}lez-Almagro and Juan Luis Suarez and Luengo, Juli{\'a}n and J. R. Cano and Garc{\'\i}a, Salvador} } @article {789, title = {DILS: Constrained clustering through dual iterative local search}, journal = {Computers \& Operations Research}, volume = {121}, year = {2020}, note = {TIN2017- 89517-P; PP2016.PRI.I.02.}, pages = {104979}, abstract = {Clustering has always been a powerful tool in knowledge discovery. Traditionally unsupervised, it has received renewed attention recently as it has shown to produce better results when provided with new types of information, thus leading to a new kind of semi-supervised learning: constrained clustering. This technique is a generalization of traditional clustering that considers additional information encoded by constraints. Constraints can be given in the form of instance-level must-link and cannot-link constraints, which is the focus of this paper. We propose a new metaheuristic algorithm, the Dual Iterative Local Search, and prove its ability to produce quality results for the constrained clustering problem. We compare the results obtained by this proposal to those obtained by the state-of-the-art algorithms on 25 datasets with incremental levels of constraint-based information, supporting our conclusions with the aid of Bayesian statistical tests.}, keywords = {Cannot-link, constrained clustering, Dual iterative local search, Instance-level, Must-link}, doi = {https://doi.org/10.1016/j.cor.2020.104979}, author = {Germ{\'a}n Gonz{\'a}lez-Almagro and Luengo, Juli{\'a}n and J. R. Cano and Garc{\'\i}a, Salvador} } @conference {788, title = {Improving constrained clustering via decomposition-based multiobjective optimization with memetic elitism}, booktitle = {GECCO {\textquoteright}20: Proceedings of the 2020 Genetic and Evolutionary Computation Conference}, year = {2020}, note = {TIN2017-89517-P; PP2016.PRI.I.02.}, month = {06/2020}, pages = {333{\textendash}341}, abstract = {Clustering has always been a topic of interest in knowledge discovery, it is able to provide us with valuable information within the unsupervised machine learning framework. It received renewed attention when it was shown to produce better results in environments where partial information about how to solve the problem is available, thus leading to a new machine learning paradigm: semi-supervised machine learning. This new type of information can be given in the form of constraints, which guide the clustering process towards quality solutions. In particular, this study considers the pairwise instance-level must-link and cannot-link constraints. Given the ill-posed nature of the constrained clustering problem, we approach it from the multiobjective optimization point of view. Our proposal consists in a memetic elitist evolutionary strategy that favors exploitation by applying a local search procedure to the elite of the population and transferring its results only to the external population, which will also be used to generate new individuals. We show the capability of this method to produce quality results for the constrained clustering problem when considering incremental levels of constraint-based information. For the comparison with state-of-the-art methods, we include previous multi-objective approaches, single-objective genetic algorithms and classic constrained clustering methods.}, keywords = {constrained clustering, memetic elitis MOEA, multiobjective optimization, pairwise instance- level constraints, Semi-supervised learning}, doi = {https://doi.org/10.1145/3377930.3390187}, author = {Germ{\'a}n Gonz{\'a}lez-Almagro and Rosales-P{\'e}rez, Alejandro and Luengo, Juli{\'a}n and J. R. Cano and Garc{\'\i}a, Salvador} } @article {786, title = {ProLSFEO-LDL: Prototype Selection and Label- Specific Feature Evolutionary Optimization for Label Distribution Learning}, journal = {Applied Sciences}, volume = {10}, year = {2020}, note = {TIN2017-89517-P}, pages = {3089}, abstract = {Label Distribution Learning (LDL) is a general learning framework that assigns an instance to a distribution over a set of labels rather than to a single label or multiple labels. Current LDL methods have proven their effectiveness in many real-life machine learning applications. In LDL problems, instance-based algorithms and particularly the adapted version of the k-nearest neighbors method for LDL (AA-kNN) has proven to be very competitive, achieving acceptable results and allowing an explainable model. However, it suffers from several handicaps: it needs large storage requirements, it is not efficient predicting and presents a low tolerance to noise. The purpose of this paper is to mitigate these effects by adding a data reduction stage. The technique devised, called Prototype selection and Label-Specific Feature Evolutionary Optimization for LDL (ProLSFEO-LDL), is a novel method to simultaneously address the prototype selection and the label-specific feature selection pre-processing techniques. Both techniques pose a complex optimization problem with a huge search space. Therefore, we have proposed a search method based on evolutionary algorithms that allows us to obtain a solution to both problems in a reasonable time. The effectiveness of the proposed ProLSFEO-LDL method is verified on several real-world LDL datasets, showing significant improvements in comparison with using raw datasets.}, doi = {https://doi.org/10.3390/app10093089}, author = {Gonzalez, M and J. R. Cano and Garc{\'\i}a, Salvador} } @article {787, title = {Similarity-based and Iterative Label Noise Filters for Monotonic Classification}, journal = {Proceedings of the 53rd Hawaii International Conference on System Sciences}, year = {2020}, note = {TIN2017-89517-P; TEC2015-69496-R; BigDaP-TOOLS - Ayudas Fundaci{\'o}n BBVA a Equipos de Investigaci{\'o}n Cient{\'\i}fica 2016}, pages = {1698-1706}, abstract = {Monotonic ordinal classification has received an increasing interest in the latest years. Building monotone models from these problems usually requires datasets that verify monotonic relationships among the samples. When the monotonic relationships are not met, changing the labels may be a viable option, but the risk is high: wrong label changes would completely change the information contained in the data. In this work, we tackle the construction of monotone datasets by removing the wrong or noisy examples that violate monotonicity restrictions. We propose two monotonic noise filtering algorithms to preprocess the ordinal datasets and improve the monotonic relations between instances. The experiments are carried out over eleven ordinal datasets, showing that the application of the proposed filters improve the prediction capabilities over different levels of noise.}, keywords = {Monotonic classification, noise, noise filter, Ordinal classification, Soft Computing: Theory Innovations and Problem Solving Benefits}, doi = {https://doi.org/10.24251/HICSS.2020.210}, author = {J. R. Cano and Luengo, Juli{\'a}n and Garc{\'\i}a, Salvador} } @article {CANO2019, title = {Label noise filtering techniques to improve monotonic classification}, journal = {Neurocomputing}, volume = {353}, year = {2019}, note = {TIN2014-57251-P; TIN2017-89517-P; TEC2015-69496-R; BigDaP-TOOLS}, month = {08/2019}, pages = {83-95}, abstract = {The monotonic ordinal classification has increased the interest of researchers and practitioners within machine learning community in the last years. In real applications, the problems with monotonicity constraints are very frequent. To construct predictive monotone models from those problems, many classifiers require as input a data set satisfying the monotonicity relationships among all samples. Changing the class labels of the data set (relabeling) is useful for this. Relabeling is assumed to be an important building block for the construction of monotone classifiers and it is proved that it can improve the predictive performance. In this paper, we will address the construction of monotone datasets considering as noise the cases that do not meet the monotonicity restrictions. For the first time in the specialized literature, we propose the use of noise filtering algorithms in a preprocessing stage with a double goal: to increase both the monotonicity index of the models and the accuracy of the predictions for different monotonic classifiers. The experiments are performed over 12 datasets coming from classification and regression problems and show that our scheme improves the prediction capabilities of the monotonic classifiers instead of being applied to original and relabeled datasets. In addition, we have included the analysis of noise filtering process in the particular case of wine quality classification to understand its effect in the predictive models generated.}, keywords = {Monotonic classification, Noise filtering, Ordinal classification, Preprocessing}, issn = {0925-2312}, doi = {https://doi.org/10.1016/j.neucom.2018.05.131}, url = {http://www.sciencedirect.com/science/article/pii/S092523121930325X}, author = {J. R. Cano and J. Luengo and S. Garc{\'\i}a} } @article {785, title = {Monotonic classification: An overview on algorithms, performance measures and data sets}, journal = {Neurocomputing}, volume = {341}, year = {2019}, note = {TIN2017-89517-P; TIN2015-70308-REDT; TIN2014-54583-C2-1-R; TEC2015-69496-R}, month = {05/2019}, pages = {168-182}, abstract = {Currently, knowledge discovery in databases is an essential first step when identifying valid, novel and useful patterns for decision making. There are many real-world scenarios, such as bankruptcy prediction, option pricing or medical diagnosis, where the classification models to be learned need to fulfill restrictions of monotonicity (i.e. the target class label should not decrease when input attributes values increase). For instance, it is rational to assume that a higher debt ratio of a company should never result in a lower level of bankruptcy risk. Consequently, there is a growing interest from the data mining research community concerning monotonic predictive models. This paper aims to present an overview of the literature in the field, analyzing existing techniques and proposing a taxonomy of the algorithms based on the type of model generated. For each method, we review the quality metrics considered in the evaluation and the different data sets and monotonic problems used in the analysis. In this way, this paper serves as an overview of monotonic classification research in specialized literature and can be used as a functional guide for the field.}, keywords = {Monotonic classification, Monotonic data sets, Ordinal classification, Software Performance metrics, Taxonomy}, doi = {https://doi.org/10.1016/j.neucom.2019.02.024}, author = {J. R. Cano and Pedro Antonio Guti{\'e}rrez and Bartosz Krawczyk and Michat Wo{\'z}niak and Garc{\'\i}a, Salvador} } @conference {10.1007/978-3-319-92639-1_23, title = {A First Attempt on Monotonic Training Set Selection}, booktitle = {Hybrid Artificial Intelligent Systems}, year = {2018}, pages = {277{\textendash}288}, publisher = {Springer International Publishing}, organization = {Springer International Publishing}, address = {Cham}, abstract = {Monotonicity constraints frequently appear in real-life problems. Many of the monotonic classifiers used in these cases require that the input data satisfy the monotonicity restrictions. This contribution proposes the use of training set selection to choose the most representative instances which improves the monotonic classifiers performance, fulfilling the monotonic constraints. We have developed an experiment on 30 data sets in order to demonstrate the benefits of our proposal.}, isbn = {978-3-319-92639-1}, author = {J. R. Cano and S. Garc{\'\i}a}, editor = {de Cos Juez, Francisco Javier and Villar, Jos{\'e} Ram{\'o}n and de la Cal, Enrique A. and Herrero, {\'A}lvaro and Quinti{\'a}n, H{\'e}ctor and S{\'a}ez, Jos{\'e} Ant{\'o}nio and Corchado, Emilio} } @conference {10.1007/978-3-319-91479-4_61, title = {Credal C4.5 with Refinement of~Parameters}, booktitle = {Information Processing and Management of Uncertainty in Knowledge-Based Systems. Applications}, year = {2018}, pages = {739{\textendash}747}, publisher = {Springer International Publishing}, organization = {Springer International Publishing}, address = {Cham}, abstract = {Recently, a classification method called Credal C4.5 (CC4.5) has been presented which combines imprecise probabilities and the C4.5 algorithm. The action of the CC4.5 algorithm depends on a parameter s. In previous works, it has been shown that this parameter has relation with the degree of overfitting of the model. The noise level of a data set can influence on the choice of a good value for s. In this paper, it is presented a new method based on the CC4.5 method with a refining of its parameter in the time of training. The new method has an equivalent performance than CC4.5 with the best value of s for each level noise.}, isbn = {978-3-319-91479-4}, author = {Mantas, Carlos J. and Abell{\'a}n, Joaqu{\'\i}n and Castellano, Javier G. and J. R. Cano and Moral, Seraf{\'\i}n}, editor = {Medina, Jes{\'u}s and Ojeda-Aciego, Manuel and Verdegay, Jos{\'e} Luis and Perfilieva, Irina and Bouchon-Meunier, Bernadette and Yager, Ronald R.} } @article {552, title = {CommuniMents: A Framework for Detecting Community Based Sentiments for Events}, journal = {International Journal on Semantic Web and Information Systems}, volume = {13}, year = {2017}, pages = {87-108}, author = {Jarwar, Muhammad Aslam and Abbasi, Rabeeh Ayaz and Mushtaq, Mubashar and Maqbool, Onaiza and Aljohani, Naif R and Daud, Ali and Alowibdi, Jalal S and J. R. Cano and Garc{\'\i}a, Salvador and Chong, Ilyoung} } @article {Garc{\'\i}a2017, title = {MoNGEL: monotonic nested generalized exemplar learning}, journal = {Pattern Analysis and Applications}, volume = {20}, number = {2}, year = {2017}, month = {May}, pages = {441{\textendash}452}, abstract = {In supervised prediction problems, the response attribute depends on certain explanatory attributes. Some real problems require the response attribute to represent ordinal values that should increase with some of the explaining attributes. They are called classification problems with monotonicity constraints. In this paper, we aim at formalizing the approach to nested generalized exemplar learning with monotonicity constraints, proposing the monotonic nested generalized exemplar learning (MoNGEL) method. It accomplishes learning by storing objects in {\$}{\$}{\{}{\backslash}mathbb {\{}R{\}}{\}}^n{\$}{\$}Rn, hybridizing instance-based learning and rule learning into a combined model. An experimental analysis is carried out over a wide range of monotonic data sets. The results obtained have been verified by non-parametric statistical tests and show that MoNGEL outperforms well-known techniques for monotonic classification, such as ordinal learning model, ordinal stochastic dominance learner and k-nearest neighbor, considering accuracy, mean absolute error and simplicity of constructed models.}, issn = {1433-755X}, doi = {10.1007/s10044-015-0506-y}, url = {https://doi.org/10.1007/s10044-015-0506-y}, author = {Javier Garc{\'\i}a and Fardoun, Habib M. and Alghazzawi, Daniyal M. and J. R. Cano and S. Garc{\'\i}a} } @article {CANO2017128, title = {Prototype selection to improve monotonic nearest neighbor}, journal = {Engineering Applications of Artificial Intelligence}, volume = {60}, year = {2017}, pages = {128 - 135}, abstract = {Student surveys occupy a central place in the evaluation of courses at teaching institutions. At the end of each course, students are requested to evaluate various aspects such as activities, methodology, coordination or resources used. In addition, a final qualification is given to summarize the quality of the course. The prediction of this final qualification can be accomplished by using monotonic classification techniques. The outcome offered by these surveys is particularly significant for faculty and teaching staff associated with the course. The monotonic nearest neighbor classifier is one of the most relevant algorithms in monotonic classification. However, it does suffer from two drawbacks, (a) inefficient execution time in classification and (b) sensitivity to no monotonic examples. Prototype selection is a data reduction process for classification based on nearest neighbor that can be used to alleviate these problems. This paper proposes a prototype selection algorithm called Monotonic Iterative Prototype Selection (MONIPS) algorithm. Our objective is two-fold. The first one is to introduce MONIPS as a method for obtaining monotonic solutions. MONIPS has proved to be competitive with classical prototype selection solutions adapted to monotonic domain. Besides, to further demonstrate the good performance of MONIPS in the context of a student survey about taught courses.}, keywords = {Data reduction, Monotone nearest neighbor, Monotonic classification, Opinion surveys, Prototype selection}, issn = {0952-1976}, doi = {https://doi.org/10.1016/j.engappai.2017.02.006}, url = {http://www.sciencedirect.com/science/article/pii/S0952197617300295}, author = {J. R. Cano and Naif R. Aljohani and Rabeeh Ayaz Abbasi and Jalal S. Alowidbi and S. Garc{\'\i}a} } @article {CANO201794, title = {Training set selection for monotonic ordinal classification}, journal = {Data \& Knowledge Engineering}, volume = {112}, year = {2017}, pages = {94 - 105}, abstract = {In recent years, monotonic ordinal classification has increased the focus of attention for machine learning community. Real life problems frequently have monotonicity constraints. Many of the monotonic classifiers require that the input data sets satisfy the monotonicity relationships between its samples. To address this, a conventional strategy consists of relabeling the input data to achieve complete monotonicity. As an alternative, we explore the use of preprocessing algorithms without modifying the class label of the input data. In this paper we propose the use of training set selection to choose the most effective instances which lead the monotonic classifiers to obtain more accurate and efficient models, fulfilling the monotonic constraints. To show the benefits of our proposed training set selection algorithm, called MonTSS, we carry out an experimentation over 30 data sets related to ordinal classification problems.}, keywords = {Data preprocessing, machine learning, Monotonic classification, Ordinal classification, Training set selection}, issn = {0169-023X}, doi = {https://doi.org/10.1016/j.datak.2017.10.003}, url = {http://www.sciencedirect.com/science/article/pii/S0169023X16303585}, author = {J. R. Cano and S. Garc{\'\i}a} } @conference {GarciaCG16, title = {A Nearest Hyperrectangle Monotonic Learning Method}, booktitle = {Proceedings of the 11th International Conference Hybrid Artificial Intelligent Systems, 2016, Seville, Spain, April 18-20, 2016}, year = {2016}, pages = {311{\textendash}322}, author = {Javier Garc{\'\i}a and J. R. Cano and S. Garc{\'\i}a} } @article {GarciaAACG16, title = {Hyperrectangles Selection for Monotonic Classification by Using Evolutionary Algorithms}, journal = {International Journal Computational Intelligence Systems}, volume = {9}, number = {1}, year = {2016}, pages = {184{\textendash}201}, doi = {10.1080/18756891.2016.1146536}, author = {Javier Garc{\'\i}a and Adnan Al-bar and Naif R. Aljohani and J. R. Cano and S. Garc{\'\i}a} } @article {Garc{{\'\i}a2015, title = {MoNGEL: monotonic nested generalized exemplar learning}, journal = {Pattern Analysis and Applications}, year = {2015}, pages = {1{\textendash}12}, issn = {1433-755X}, doi = {10.1007/s10044-015-0506-y}, author = {Javier Garc{\'\i}a and Fardoun, Habib M. and Alghazzawi, Daniyal M. and J. R. Cano and S. Garc{\'\i}a} } @article {Cano13, title = {Analysis of data complexity measures for classification}, journal = {Expert Systems with Applications}, volume = {40}, number = {12}, year = {2013}, pages = {4820{\textendash}4831}, doi = {10.1016/j.eswa.2013.02.025}, url = {http://dx.doi.org/10.1016/j.eswa.2013.02.025}, author = {J. R. Cano} } @article {Cano12, title = {Predictive-collaborative model as recovery and validation tool. Case of study: Psychiatric emergency department decision support}, journal = {Expert Systems with Applications}, volume = {39}, number = {4}, year = {2012}, pages = {4044{\textendash}4048}, doi = {10.1016/j.eswa.2011.09.098}, author = {J. R. Cano} } @article {GarciaDCH12, title = {Prototype Selection for Nearest Neighbor Classification: Taxonomy and Empirical Study}, journal = {IEEE Transactions Pattern Analysis and Machiche Intelligence}, volume = {34}, number = {3}, year = {2012}, pages = {417{\textendash}435}, doi = {10.1109/TPAMI.2011.142}, author = {S. Garc{\'\i}a and J. Derrac and J. R. Cano and F. Herrera} } @article {simidat59, title = {Replacement Strategies to Preserve Useful Diversity in Steady-State Genetic Algorithms}, journal = {Information Sciences}, year = {2012}, author = {M. Lozano and F. Herrera and J. R. Cano} } @inbook {GarciaCH10, title = {A Review on Evolutionary Prototype Selection}, booktitle = {Intelligent Systems for Automated Learning and Adaptation: Emerging Trends and Applications}, year = {2010}, pages = {92{\textendash}113}, doi = {10.4018/978-1-60566-798-0.ch005}, author = {S. Garc{\'\i}a and J. R. Cano and F. Herrera} } @article {simidat61, title = {Diagnose of Effective Evolutionary Prototype Selection using an Overlapping Measure}, journal = {International Journal of Pattern Recognition and Artificial Intelligence}, volume = {23}, number = {8}, year = {2009}, pages = {1527-1548}, author = {S. Garc{\'\i}a and J. R. Cano and E. Bernad{\'o}-Mansilla and F. Herrera} } @article {606, title = {Modelo predictivo colaborativo de apoyo al diagn{\'o}stico en servicio de urgencias psiqui{\'a}tricas}, journal = {Revista Ib{\'e}rica de Sistemas y Tecnolog{\'\i}as de la informaci{\'o}n}, volume = {4}, number = {4}, year = {2009}, pages = {29-42}, issn = {1646-9895}, author = {J. R. Cano and P. Gonz{\'a}lez and Jos{\'e} Aguilera and A.G. L{\'o}pez-Herrera and F. Herrera and M. Nav{\'\i}o and Jim{\'e}nez-Arriero Miguel Angel} } @article {simidat57, title = {A memetic algorithm for Evolutionary Prototype Selection: A Scaling Up Approach}, journal = {Pattern Recognition}, volume = {41}, number = {8}, year = {2008}, pages = {2693-2709}, author = {S. Garc{\'\i}a and J. R. Cano and F. Herrera} } @conference {simidat82, title = {Estudio de la influencia de las medidas de complejidad de los datos en los Sistemas de Clasifcaci{\'o}n Basados en Reglas Difusas: An{\'a}lisis de la Raz{\'o}n Discriminante de Fisher}, booktitle = {XIV Congreso Espa{\~n}ol sobre Tecnolog{\'\i}as y L{\'o}gica Fuzzy (ESTYLF)}, year = {2008}, month = {September}, pages = {257-263}, address = {Mieres (Spain)}, author = {J. Luengo and S. Garc{\'\i}a and J. R. Cano and F. Herrera} } @article {article, title = {Evolutionary Stratified Instance Selection applied to Training Set Selection for Extracting High Precise-Interpretable Classification Rules}, year = {2008}, month = {01}, author = {J. R. Cano and F. Herrera and Lozano, Manuel} } @article {610, title = {Making CN1 -SD Subgroup Discovery Algorithm Scalable to Large Size Data Sets Using Instance Selection}, journal = {Expert System with Applications}, volume = {35}, number = {4}, year = {2008}, pages = {1949-1965}, author = {J. R. Cano and F. Herrera and Lozano, Manuel and Garc{\'\i}a, Salvador} } @article {simidat58, title = {Making CN2-SD Subgroup Discovery Algorithm scalable to Large Size Data Sets using Instance Selection}, journal = {Expert Systems with Applications}, volume = {35}, year = {2008}, pages = {1949-1965}, author = {J. R. Cano and F. Herrera and M. Lozano and S. Garc{\'\i}a} } @article {LozanoHC08, title = {Replacement strategies to preserve useful diversity in steady-state genetic algorithms}, journal = {Information Sciences}, volume = {178}, number = {23}, year = {2008}, pages = {4421{\textendash}4433}, doi = {10.1016/j.ins.2008.07.031}, author = {M. Lozano and J. R. Cano and F. Herrera} } @article {simidat87, title = {Subgroup Discovery in Large Size Data Sets Preprocessed Using Stratified Instance Selection for Increasing the Presence of Minority Classes}, journal = {Pattern Recognition Letters}, volume = {29}, year = {2008}, pages = {2156-2164}, doi = {10.1016/j.patrec.2008.08.001}, author = {J. R. Cano and S. Garc{\'\i}a and F. Herrera} } @conference {simidat54, title = {An{\'a}lisis of Evolutionary Prototype Selection by means of a Data Complexity Measure based on Class Separabilty}, booktitle = {Actas del Taller de Miner{\'\i}a de Datos y Aprendizaje (TAMIDA)}, year = {2007}, pages = {145-152}, address = {Zaragoza}, author = {J. R. Cano and S. Garc{\'\i}a and F. Herrera and E. Bernad{\'o}-Mansilla} } @article {simidat56, title = {Evolutionary Stratified Training Set Selection for Extracting Classification Rules with trade off Precision-Interpretability}, journal = {Data \& Knowledge Engineering}, volume = {60}, number = {1}, year = {2007}, pages = {90-108}, author = {J. R. Cano and F. Herrera and M. Lozano} } @conference {simidat55, title = {Un algoritmo mem{\'e}tico para la selecci{\'o}n de prototipos: Una propuesta eficiente para problemas de tama{\~n}o medio}, booktitle = {Proceedings Congreso Espa{\~n}ol sobre Metaheur{\'\i}sticas, Algoritmos Evolutivos y Bioinspirados (MAEB)}, year = {2007}, address = {Tenerife}, author = {S. Garc{\'\i}a and J. R. Cano and F. Herrera} } @conference {simidat34, title = {A proposal of Evolutionary Prototype Selection for Class Imbalance Problems}, booktitle = {Proceedings of the 7th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL)}, series = {LNCS}, volume = {4224}, year = {2006}, pages = {1415-1423}, author = {S. Garc{\'\i}a and J. R. Cano and A. Fern{\'a}ndez and F. Herrera} } @conference {simidat33, title = {Incorporating Knowledge in Evolutionary Prototype Selection}, booktitle = {Proceedings of the 7th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL)}, series = {LNCS}, volume = {4224}, year = {2006}, pages = {1358-1366}, author = {S. Garc{\'\i}a and J. R. Cano and F. Herrera} } @article {simidat35, title = {On the Combination of Evolutionary Algorithms and Stratified Strategies for Training Set Selection in Data Mining}, journal = {Applied Soft Computing}, volume = {6}, year = {2006}, pages = {323-332}, author = {J. R. Cano and F. Herrera and M. Lozano} } @inbook {simidat26, title = {A Study on the Combination of Evolutionary Algorithms and Stratified Strategies for Training Set Selection in Data Mining}, booktitle = {Soft Computing: Methodologies and Applications}, year = {2005}, pages = {271-284}, publisher = {Springer-Verlag}, organization = {Springer-Verlag}, author = {J. R. Cano and F. Herrera and M. Lozano}, editor = {F. Hoffmann and M. K{\"o}ppen and F. Klawonn and R. Roy} } @inbook {689, title = {De la teor{\'\i}a a la pr{\'a}ctica: una reflexi{\'o}n sobre el EEES en aula}, booktitle = {Adaptaci{\'o}n del profesorado universitario al espacio europeo de educaci{\'o}n superior mediante el uso de nuevas tecnolog{\'\i}as}, number = {69-77}, year = {2005}, publisher = {Grupo Pafpu Formapro de la UCUA}, organization = {Grupo Pafpu Formapro de la UCUA}, address = {Ja{\'e}n (Espa{\~n}a)}, issn = {3-540-25726-8}, author = {Romero, Samuel and J. R. Cano and Prados-Suarez, Mar{\'\i}a Belen and Rivero-Cejudo, Maria Linarejos} } @inbook {Cano2005, title = {Instance Selection Using Evolutionary Algorithms: An Experimental Study}, booktitle = {Advanced Techniques in Knowledge Discovery and Data Mining}, year = {2005}, pages = {127{\textendash}152}, publisher = {Springer London}, organization = {Springer London}, address = {London}, abstract = {In this chapter, we carry out an empirical study of the performance of four representative evolutionary algorithm models considering two instance-selection perspectives, the prototype selection and the training set selection for data reduction in knowledge discovery. This study includes a comparison between these algorithms and other nonevolutionary instance-selection algorithms. The results show that the evolutionary instance-selection algorithms consistently outperform the nonevolutionary ones, offering two main advantages simultaneously, better instance-reduction rates and higher classification accuracy.}, isbn = {978-1-84628-183-9}, doi = {10.1007/1-84628-183-0_5}, url = {https://doi.org/10.1007/1-84628-183-0_5}, author = {J. R. Cano and F. Herrera and Lozano, Manuel}, editor = {Pal, Nikhil R. and Jain, Lakhmi} } @inbook {inbook, title = {Replacement Strategies to Maintain Useful Diversity in Steady-State Genetic Algorithms}, year = {2005}, month = {01}, pages = {85-96}, doi = {10.1007/3-540-32400-3_7}, author = {Lozano, Manuel and F. Herrera and J. R. Cano} } @inbook {Cano2005, title = {Strategies for Scaling Up Evolutionary Instance Reduction Algorithms for Data Mining}, booktitle = {Evolutionary Computation in Data Mining}, year = {2005}, pages = {21{\textendash}39}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, address = {Berlin, Heidelberg}, abstract = {Evolutionary algorithms are adaptive methods based on natural evolution that may be used for search and optimization. As instance selection can be viewed as a search problem, it could be solved using evolutionary algorithms.}, isbn = {978-3-540-32358-7}, doi = {10.1007/3-540-32358-9_2}, url = {https://doi.org/10.1007/3-540-32358-9_2}, author = {J. R. Cano and F. Herrera and Lozano, Manuel}, editor = {Ghosh, Ashish and Jain, Lakhmi C.} } @article {simidat24, title = {Stratification for Scaling Up Evolutionary Prototype Selection}, journal = {Pattern Recognition Letters}, volume = {26}, year = {2005}, pages = {953-963}, author = {J. R. Cano and F. Herrera and M. Lozano} } @inbook {691, title = {T{\'e}cnicas de reducci{\'o}n de datos en KDD}, booktitle = {Miner{\'\i}a de datos: T{\'e}cnicas y Aplicaciones}, number = {13-33}, year = {2005}, publisher = {Herrera F., Riguelme J.C. y Aguilar-Ruiz, JS}, organization = {Herrera F., Riguelme J.C. y Aguilar-Ruiz, JS}, address = {Sevilla (Espa{\~n}a)}, issn = {84-921873-7-9}, author = {J. R. Cano and F. Herrera} } @inbook {simidat15, title = {Selecci{\'o}n Evolutiva Estratificada de Conjuntos de Entrenamiento para la Obtenci{\'o}n de Bases de Reglas con un Alto Equilibrio entre Precisi{\'o}n e Interpretabilidad}, booktitle = {Tendencias de la Miner{\'\i}a de Datos en Spain.}, year = {2004}, pages = {263 - 274}, isbn = {84-688-8442-1}, author = {J. R. Cano and F. Herrera and M. Lozano}, editor = {R. Gir{\'a}ldez and J. C. Riquelme and J. S. Aguilar} } @conference {simidat7, title = {An Study on the Combination of Evolutionary Algorithms and Stratified Strategies for Training Set Selection in Data Mining}, booktitle = {Proceedings of the 8th Online World Conference on Soft Computing in Industrial Applications}, year = {2003}, month = {September}, author = {J. R. Cano and F. Herrera and M. Lozano} } @article {simidat5, title = {Linguistic Modeling with Hierarchical Systems of Weighted Linguistic Rules}, journal = {International Journal of Approximate Reasoning}, volume = {32}, number = {2-3}, year = {2003}, pages = {187-215}, author = {R. Alcal{\'a} and J. R. Cano and O. Cord{\'o}n and F. Herrera and P. Villar and I. Zwir} } @conference {simidat6, title = {Replacement Strategies to Maintain Useful Diversity in Steady-State Genetic Algorithms}, booktitle = {Proceedings of the 8th Online World Conference on Soft Computing in Industrial Applications}, year = {2003}, month = {September}, author = {M. Lozano and F. Herrera and J. R. Cano} } @article {simidat4, title = {Using Evolutionary Algorithms as Instance Selection for Data Reduction in KDD: an Experimental Study}, journal = {IEEE Transactions on Evolutionary Computation}, volume = {7}, number = {6}, year = {2003}, pages = {561-575}, author = {J. R. Cano and F. Herrera and M. Lozano} } @conference {CanoCHS02, title = {A GRASP Algorithm for Clustering}, booktitle = {Proceedings of the 8th Ibero-American Conference on Artifical Intelligence, Seville, Spain, November 12-15, 2002,}, year = {2002}, pages = {214{\textendash}223}, author = {J. R. Cano and O. Cord{\'o}n and F. Herrera and Luciano S{\'a}nchez} } @article {CanoCHS02, title = {A greedy randomized adaptive search procedure applied to the clustering problem as an initialization process using K-Means as a local search procedure}, journal = {Journal of Intelligent and Fuzzy Systems}, volume = {12}, number = {3-4}, year = {2002}, pages = {235{\textendash}242}, author = {J. R. Cano and O. Cord{\'o}n and F. Herrera and Luciano S{\'a}nchez} } @conference {742, title = {Scrae Web: Sistema de Correcci{\'o}n y Revisi{\'o}n Autom{\'a}tica de Ex{\'a}menes a Trav{\'e}s de la Web}, booktitle = {Jornadas de Ense{\~n}anza Universitaria de la Inform{\'a}tica Jenui }, year = {2002}, month = {01}, address = {C{\'a}ceres (Espa{\~n}a)}, author = {Sanchez Pulido, Alfredo and J. R. Cano and Pav{\'o}n-Pulido, Nieves} } @conference {739, title = {Selecci{\'o}n Evolutiva de Instancias en Miner{\'\i}a de Datos}, booktitle = {Workwhop de Miner{\'\i}a de Datos y Aprendizaje Autom{\'a}tico}, year = {2002}, month = {01}, address = {Santander (Espa{\~n}a)}, author = {J. R. Cano and F. Herrera and Lozano, Manuel} }