@article {781, title = {ClEnDAE: A classifier based on ensembles with built-in dimensionality reduction through denoising autoencoders}, journal = {Information Sciences}, volume = {565}, year = {2021}, note = {TIN2015-68454-R; PID2019-107793GB-I00 / AEI /10.13039/501100011033}, pages = {146-176}, abstract = {High dimensionality is an issue that affects most classification algorithms. This factor implies that the predictive performance of many traditional classifiers decreases considerably as the number of features increases. Therefore, there are numerous proposals that try to mitigate the effects of this issue. This study proposes ClEnDAE, a new classifier based on ensembles whose components incorporate denoising autoencoders (DAEs) to reduce the dimensionality of the input space. On the one hand, the use of ensembles improves the predictive performance by using several components that work jointly. On the other hand, the use of DAEs allows a new higher-level, smaller-sized feature space to be generated, reducing high dimensionality effects. Finally, an experimentation is conducted with the goal of evaluating the behavior of ClEnDAE. The first part of the test compares the performance of ClEnDAE to a model based on basic DAE and to the original untreated data. The second part analyzes the results of ClEnDAE and other traditional methods of dimensionality reduction in order to determine the improvement achieved with the proposed algorithm. In both parts of the experimentation, conclusions show that ClEnDAE offers better predictive performance than the other analyzed models. The main advantage of the ClEnDAE method is the combination of the potential of the ensemble-based methodology, where several components work in parallel, and DAEs, which generate new low-dimensional features that provide more relevant information. Therefore, the classification performance is better than with other classic proposals.}, keywords = {classification, Deep learning, Denoising autoencoders, Dimensionality reduction, Ensembles feature fusion}, doi = {https://doi.org/10.1016/j.ins.2021.02.060}, author = {Pulgar, Francisco J. and Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus} } @conference {780, title = {A Preliminary Study on Crop Classification with Unsupervised Algorithms for Time Series on Images with Olive Trees and Cereal Crops }, booktitle = {15th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2020)}, year = {2020}, note = {PID2019-107793GB-I00}, month = {08/2020}, pages = {276-285}, abstract = {Satellite imagery has been consolidated as an accurate option to monitor or classify crops. This is due to the continuous increase in spatial-temporal resolution and the availability of free access to this kind of services. In order to generate crop type maps (a valuable preprocessing step to most remote agriculture monitoring application), time series are built from remote sensing images, and supervised techniques are widely used to classify them. However, one of the main drawbacks of these methods is the lack of labelled data sets to carry out the training process. Unsupervised classification has been less frequently used in this research field. The paper presents an experimental study comparing traditional clustering algorithms (with different dissimilarity measures) for the classification of olive trees and cereal crops from time series remote sensing data. The results obtained provide crucial information for developing novel and more accurate crop mapping algorithms.}, keywords = {Clustering Crop mappings, Satellite imagery, Time series classification, Unsupervised learning}, doi = {https://doi.org/10.1007/978-3-030-57802-2_27}, author = {A.J. Rivera-Rivas and M.D. P{\'e}rez-Godoy and D. Elizondo and Lipika Deka and M. J. del Jesus} } @article {774, title = {Choosing the proper autoencoder for feature fusion based on data complexity and classifiers: Analysis, tips and guidelines}, journal = {Information Fusion}, volume = {54}, year = {2020}, note = {TIN2015-68454-R}, month = {02/2020}, pages = {44-60}, abstract = {Classifying data patterns is one of the most recurrent applications in machine learning. The number of input features influences the predictive performance of many classification models. Most classifiers work with high-dimensional spaces. Therefore, there is a great interest in facing the task of reducing the input space. Manifold learning has been shown to perform better than classical dimensionality reduction approaches, such as Principal Component Analysis and Linear Discriminant Analysis. In this sense, Autoencoders (AEs) provide an automated way of performing feature fusion, finding the best manifold to reconstruct the data. There are several models and architectures of AEs. For this reason, in this study an exhaustive analysis of the predictive performance of different AEs models with a large number of datasets is proposed, aiming to provide a set of useful guidelines. These will allow users to choose the appropriate AE model for each case, depending on data traits and the classifier to be used. A thorough empirical analysis is conducted including four AE models, four classification paradigms and a group of datasets with a variety of traits. A convenient set of rules to follow is obtained as a result.}, keywords = {Autoencoders, classification, Deep learning, Dimensionality reduction, Feature fusion}, doi = {https://doi.org/10.1016/j.inffus.2019.07.004}, author = {Pulgar, Francisco J. and Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus} } @article {779, title = {El ecosistema de aprendizaje del estudiante universitario en la post-pandemia. Metodolog{\'\i}as y herramientas}, journal = {Ense{\~n}anza y Aprendizaje de Ingenier{\'\i}a de Computadores}, number = {10}, year = {2020}, abstract = {La transici{\'o}n de una modalidad de ense{\~n}anza tradicional y presencial a una de tipo remoto, provocada por el confinamiento a ra{\'\i}z del coronavirus SARS-CoV-2, ha implicado cambios que han debido realizarse de manera acelerada y que afectan no solo al desarrollo de las clases, sino tambi{\'e}n a las actividades pr{\'a}cticas en laboratorio, de comunicaci{\'o}n y de evaluaci{\'o}n de las competencias de los estudiantes. En este trabajo exponemos c{\'o}mo hemos afrontado dicha transici{\'o}n en asignaturas del {\'a}rea Arquitectura y tecnolog{\'\i}a de computadores en la Universidad de Ja{\'e}n, as{\'\i} como la planificaci{\'o}n que hemos llevado a cabo para el pr{\'o}ximo curso 2020/2021 ante el nivel de incertidumbre sobre c{\'o}mo se desarrollar{\'a}.}, keywords = {Aprendizaje activo, Aprendizaje basado en proyectos, Metodolog{\'\i}as de aprendizaje, Modelos de evaluaci{\'o}n}, doi = {http://dx.doi.org/10.30827/Digibug.64779}, author = {Francisco Charte and A.J. Rivera-Rivas and Medina, J. and Espinilla, Macarena} } @article {773, title = {EvoAAA: An evolutionary methodology for automated neural autoencoder architecture search}, journal = {Integrated Computer-Aided Engineering}, volume = {27}, number = {3}, year = {2020}, month = {05/2020}, pages = {211-231}, abstract = {Machine learning models work better when curated features are provided to them. Feature engineering methods have been usually used as a preprocessing step to obtain or build a proper feature set. In late years, autoencoders (a specific type of symmetrical neural network) have been widely used to perform representation learning, proving their competitiveness against classical feature engineering algorithms. The main obstacle in the use of autoencoders is finding a good architecture, a process that most experts confront manually. An automated autoencoder symmetrical architecture search procedure, based on evolutionary methods, is proposed in this paper. The methodology is tested against nine heterogeneous data sets. The obtained results show the ability of this approach to find better architectures, able to concentrate most of the useful information in a minimized encoding, in a reduced time. }, keywords = {Autoencoder, evolutionary methods, Representation learning}, doi = {https://doi.org/10.3233/ICA-200619}, author = {Francisco Charte and A.J. Rivera-Rivas and Francisco Mart{\'\i}nez and M. J. del Jesus} } @conference {772, title = {A First Approximation to the Effects of Classical Time Series Preprocessing Methods on LSTM Accuracy}, booktitle = {International Work-Conference on Artificial Neural Networks}, year = {2019}, note = {TIN2015-68454-R}, month = {05/2019}, pages = {270-280}, abstract = {A convenient data preprocessing has proven to be crucial in order to achieve high levels of accuracy, time series being no exception. For this kind of forecasting tasks, several specialized preprocessing methods have been described, being trend analysis and seasonal analysis some of them. Several have been formally grouped around a methodology that is always applied to state of the art time series forecasting models, like the well known ARIMA. LSTM is a relatively novel architecture which has been specifically designed to get rid of the vanishing gradient problem. In these models, great results have been seen when applied for time series forecasting. Still, little is known about the impact of these traditional preprocessing methods on the accuracy of LSTM. In this work an empirical analysis on how classical time series preprocessing methods influence LSTM results is conducted. That all considered ones can potentially improve LSTM performance is concluded, being the seasonal component removal the filter that achieves better, most robust accuracy gain.}, keywords = {LSTM, Preprocessing, time series}, doi = {https://doi.org/10.1007/978-3-030-20521-8_23}, author = {Daniel Trujillo Viedma and A.J. Rivera-Rivas and Francisco Charte and M. J. del Jesus} } @conference {776, title = {Automatic Time Series Forecasting with GRNN: A Comparison with Other Models}, booktitle = {International Work-Conference on Artificial Neural Networks}, year = {2019}, note = {TIN2015-68454-R}, month = {05/2019}, pages = {198-209}, abstract = {In this paper a methodology based on general regression neural networks for forecasting time series in an automatic way is presented. The methodology is aimed at achieving an efficient and fast tool so that a large amount of time series can be automatically predicted. In this sense, general regression neural networks present some interesting features, they have a fast single-pass learning and produce deterministic results. The methodology has been implemented in the R environment. A study of packages in R for automatic time series forecasting, including well-known statistical and computational intelligence models such as exponential smoothing, ARIMA or multilayer perceptron, is also done, together with an experimentation on running time and forecast accuracy based on data from the NN3 forecasting competition.}, keywords = {Automatic forecasting, General regression neural networks, time series forecasting}, doi = {https://doi.org/10.1007/978-3-030-20521-8_17}, author = {Francisco Mart{\'\i}nez and Francisco Charte and A.J. Rivera-Rivas and Fr{\'\i}as, Mar{\'\i}a Pilar} } @conference {771, title = {Automating Autoencoder Architecture Configuration: An Evolutionary Approach}, booktitle = {International Work-Conference on the Interplay Between Natural and Artificial Computation}, year = {2019}, note = {TIN2015-68454-R}, month = {05/2019}, pages = {339-349}, abstract = {Learning from existing data allows building models able to classify patterns, infer association rules, predict future values in time series and much more. Choosing the right features is a vital step of the learning process, specially while dealing with high-dimensional spaces. Autoencoders (AEs) have shown ability to conduct manifold learning, compressing the original feature space without losing useful information. However, there is no optimal AE architecture for all datasets. In this paper we show how to use evolutionary approaches to automate AE architecture configuration. First, a coding to embed the AE configuration in a chromosome is proposed. Then, two evolutionary alternatives are compared against exhaustive search. The results show the great superiority of the evolutionary way.}, keywords = {Autoencoder, Deep learning, Evolutionary, Optimization}, doi = {https://doi.org/10.1007/978-3-030-19591-5_35}, author = {Francisco Charte and A.J. Rivera-Rivas and Francisco Mart{\'\i}nez and M. J. del Jesus} } @article {292, title = {Dealing with difficult minority labels in imbalanced mutilabel data sets}, journal = {Neurocomputing}, volume = {326}, year = {2019}, note = {TIN2014-57251-P,TIN2015-68454-R,P11-TIC-7765}, pages = {39{\textendash}53}, abstract = {Multilabel classification is an emergent data mining task with a broad range of real world applications. Learning from imbalanced multilabel data is being deeply studied latterly, and several resampling methods have been proposed in the literature. The unequal label distribution in most multilabel datasets, with disparate imbalance levels, could be a handicap while learning new classifiers. In addition, this characteristic challenges many of the existent preprocessing algorithms. Furthermore, the concurrence between imbalanced labels can make harder the learning from certain labels. These are what we call difficult labels. In this work, the problem of difficult labels is deeply analyzed, its influence in multilabel classifiers is studied, and a novel way to solve this problem is proposed. Specific metrics to assess this trait in multilabel datasets, called SCUMBLE (Score of ConcUrrence among iMBalanced LabEls) and SCUMBLELbl, are presented along with REMEDIAL (REsampling MultilabEl datasets by Decoupling highly ImbAlanced Labels), a new algorithm aimed to relax label concurrence. How to deal with this problem using the R mldr package is also outlined.}, doi = {10.1016/j.neucom.2016.08.158}, author = {Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @article {777, title = {predtoolsTS: R package for streamlining time series forecasting}, journal = {Progress in Artificial Intelligence}, volume = {8}, year = {2019}, note = {TIN2015-68854-R}, month = {06/2019}, pages = {505{\textendash}510}, abstract = {Time series forecasting is a field of interest in many areas. Classically, statistical methods have been used to address this problem. In recent years, machine learning (ML) algorithms have been also applied with satisfactory results. However, ML software packages are not skilled to deal with raw sequences of temporal data, and therefore, it is necessary to transform these time series. This paper presents predtoolsTS, an R package that provides a uniform interface for applying both statistical and ML methods to time series forecasting. predtoolsTS comprises four modules: preprocessing, modeling, prediction and postprocessing, in order to deal with the whole process of time series forecasting.}, keywords = {machine learning, R, time series forecasting}, doi = {https://doi.org/10.1007/s13748-019-00193-z}, author = {Francisco Charte and Alberto Vico and M.D. P{\'e}rez-Godoy and A.J. Rivera-Rivas} } @article {293, title = {REMEDIAL-HwR: Tackling multilabel imbalance through label decoupling and data resampling hybridization}, journal = {Neurocomputing}, volume = {326}, year = {2019}, note = {TIN2014-57251-P,TIN2015-68454-R,P11-TIC-7765}, pages = {110{\textendash}122}, abstract = {The learning from imbalanced data is a deeply studied problem in standard classification and, in recent times, also in multilabel classification. A handful of multilabel resampling methods have been proposed in late years, aiming to balance the labels distribution. However, these methods have to face a new obstacle, specific for multilabel data, as is the joint appearance of minority and majority labels in the same data patterns. We presented recently a new algorithm designed to decouple imbalanced labels concurring in the same instance, called REMEDIAL (REsampling MultilabEl datasets by Decoupling highly ImbAlanced Labels). The goal of this work is to propose REMEDIAL-HwR (REMEDIAL Hybridization with Resampling), a procedure to hybridize this method with some of the best resampling algorithms available in the literature, including random oversampling, heuristic undersampling and synthetic sample generation techniques. These hybrid methods are then empirically analyzed, determining how their behavior is influenced by the label decoupling process. The analysis of results shows that the proposed method improves certain classifiers performance when it is applied over imbalanced datasets with label concurrence. In addition, a noteworthy set of guidelines on the combined use of these techniques can be drawn from the conducted experimentation.}, doi = {10.1016/j.neucom.2017.01.118}, author = {Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @article {778, title = {Time Series Forecasting with KNN in R: the tsfknn Package}, journal = {The R Journal}, volume = {11}, number = {2}, year = {2019}, note = {TIN2015-68854-R}, month = {12/2019}, pages = {229-242}, abstract = {In this paper the tsfknn package for time series forecasting using k-nearest neighbor regression is described. This package allows users to specify a KNN model and to generate its forecasts. The user can choose among different multi-step ahead strategies and among different functions to aggregate the targets of the nearest neighbors. It is also possible to assess the forecast accuracy of the KNN model.}, doi = {https://doi.org/10.32614/RJ-2019-004}, author = {Francisco Mart{\'\i}nez and Fr{\'\i}as, Mar{\'\i}a Pilar and Francisco Charte and A.J. Rivera-Rivas} } @conference {307, title = {A First Approach to Face Dimensionality Reduction Through Denoising Autoencoders}, booktitle = {19th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2018}, year = {2018}, note = {TIN2015-68854-R; FPU16/00324}, month = {11}, pages = {439{\textendash}447}, address = {Madrid (Spain)}, abstract = {The problem of high dimensionality is a challenge when facing machine learning tasks. A high dimensional space has a negative effect on the predictive performance of many methods, specifically, classification algorithms. There are different proposals that arise to mitigate the effects of this phenomenon. In this sense, models based on deep learning have emerged.}, isbn = {978-3-030-03493-1}, doi = {10.1007/978-3-030-03493-1_46}, author = {F. Pulgar-Rubio and Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus} } @article {386, title = {AEkNN: An AutoEncoder kNN-Based Classifier With Built-in Dimensionality Reduction}, journal = {International Journal of Computational Intelligence Systems}, volume = {12}, year = {2018}, note = {TIN2015-68854-R; FPU16/00324}, month = {11/2018}, pages = {436-452}, abstract = {High dimensionality tends to be a challenge for most machine learning tasks, including classification. There are different classification methodologies, of which instance-based learning is one. One of the best known members of this family is the k-nearest neighbors (kNNs) algorithm. Its strategy relies on searching a set of nearest instances. In high-dimensional spaces, the distances between examples lose significance. Therefore, kNN, in the same way as many other classifiers, tends to worsen its performance as the number of input variables grows. In this study, AEkNN, a new kNN-based algorithm with built-in dimensionality reduction, is presented. Aiming to obtain a new representation of the data, having a lower dimensionality but with more informational features, AEkNN internally uses autoencoders. From this new vector of features the computed distances should be more significant, thus providing a way to choose better neighbors. An experimental evaluation of the new proposal is conducted, analyzing several configurations and comparing them against the original kNN algorithm and classical dimensionality reduction methods. The obtained conclusions demonstrate that AEkNN offers better results in predictive and runtime performance.}, issn = {1875-6883}, doi = {10.2991/ijcis.2019.0025}, url = {https://www.atlantis-press.com/article/125905686}, author = {F. Pulgar-Rubio and Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus} } @conference {306, title = {An Approximation to Deep Learning Touristic-Related Time Series Forecasting}, booktitle = {19th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2018}, year = {2018}, note = {TIN2015-68854-R}, month = {11}, pages = {448{\textendash}456}, address = {Madrid (Spain)}, abstract = {Tourism is one of the biggest economic activities around the world. This means that an adequate planning of existing resources becomes crucial. Precise demand-related forecasting greatly improves this planning. Deep Learning models are showing an greatly improvement on time-series forecasting, particularly the LSTM, which is designed for this kind of tasks. This article introduces the touristic time-series forecasting using LSTM, and compares its accuracy against well known models RandomForest and ARIMA. Our results shows that new LSTM models achieve the best accuracy.}, isbn = {978-3-030-03493-1}, doi = {10.1007/978-3-030-03493-1_47}, author = {Daniel Trujillo and A.J. Rivera-Rivas and Francisco Charte and M. J. del Jesus} } @conference {331, title = {An{\'a}lisis del impacto de datos desbalanceados en el rendimiento predictivo de redes neuronales convolucionales}, booktitle = {XVIII Conferencia de la Asociaci{\'o}n Espa{\~n}ola para la Inteligencia Artificial (CAEPIA 2018)}, year = {2018}, note = {TIN2015-68454-R; FPU16/00324}, month = {10}, pages = {1213{\textendash}1218}, address = {Granada (Spain)}, abstract = {En los {\'u}ltimos a{\~n}os han surgido nuevas propuestas basadas en Deep Learning para afrontar la tarea de clasificaci{\'o}n. Estas propuestas han obtenido buenos resultados en algunos campos, por ejemplo, en reconocimiento de im{\'a}genes. Sin embargo, existen factores que deben ser analizados para valorar su influencia en los resultados obtenidos con estos nuevos modelos. En este trabajo se analiza la clasificaci{\'o}n de datos desbalanceados con redes neuronales convolucionales (Convolutional Neural Networks-CNNs). Para hacerlo, se han llevado a cabo una serie de tests donde se reconocen im{\'a}genes mediante CNNs. As{\'\i}mismo, se utilizan conjuntos de datos con diferente grado de desbalanceo. Los resultados demuestran que el desequilibrio afecta negativamente al rendimiento predictivo.}, isbn = {978-88-61970-00-7}, author = {F. Pulgar-Rubio and A.J. Rivera-Rivas and Francisco Charte and Mar{\'\i}a J del Jesu D{\'\i}az} } @article {MARTINEZ201838, title = {Dealing with seasonality by narrowing the training set in time series forecasting with kNN}, journal = {Expert Systems with Applications}, volume = {103}, year = {2018}, pages = {38 - 48}, abstract = {In this paper, a new strategy for dealing with time series exhibiting a seasonal pattern is proposed. The strategy is applied in the context of time series forecasting using kNN regression. The key idea is to forecast every different season using a different specialized kNN learner. Each learner is specialized because its training set only contains examples whose targets belong to the season that is able to forecast. This way, the forecast of a specialized kNN learner is an aggregation of target values of the same season, reducing the likelihood of misleading forecasts. Although the strategy is applied to kNN, we think that other computational intelligence approaches could take advantage of it.}, keywords = {NN regression, Seasonal time series, time series forecasting}, issn = {0957-4174}, doi = {https://doi.org/10.1016/j.eswa.2018.03.005}, url = {http://www.sciencedirect.com/science/article/pii/S0957417418301441}, author = {Francisco Mart{\'\i}nez and Mar{\'\i}a Pilar Fr{\'\i}as and M.D. P{\'e}rez-Godoy and A.J. Rivera-Rivas} } @article {298, title = {Nuevas arquitecturas hardware de procesamiento de alto rendimiento para aprendizaje profundo}, journal = {Ense{\~n}anza y aprendizaje de ingenier{\'\i}a de computadores. Revista de experiencias docentes en ingenier{\'\i}a de computadores}, volume = {8}, year = {2018}, note = {-}, pages = {67{\textendash}83}, abstract = {The design and manufacture of hardware is expensive, both in time and in economic investment, which is why integrated circuits are always manufactured in large volume, to take advantage of economies of scale. For this reason, the majority of processors manufactured are general purpose, thus expanding its range of applications. In recent years, however, more and more processors are being manufactured for specific applications, including those aimed at accelerating work with deep neural networks. This article introduces the need for this type of specialized hardware, describing its purpose, operation and current implementations.}, issn = {2173-8688}, author = {A.J. Rivera-Rivas and Francisco Charte and Espinilla, Macarena and M.D. P{\'e}rez-Godoy} } @article {291, title = {Tips, guidelines and tools for managing multi-label datasets: The mldr.datasets R package and the Cometa data repository}, journal = {Neurocomputing}, volume = {289}, year = {2018}, note = {TIN2014-57251-P,TIN2015-68454-R,BigDaP-TOOLS}, pages = {68{\textendash}85}, abstract = {New proposals in the field of multi-label learning algorithms have been growing in number steadily over the last few years. The experimentation associated with each of them always goes through the same phases: selection of datasets, partitioning, training, analysis of results and, finally, comparison with existing methods. This last step is often hampered since it involves using exactly the same datasets, partitioned in the same way and using the same validation strategy. In this paper we present a set of tools whose objective is to facilitate the management of multi-label datasets, aiming to standardize the experimentation procedure. The two main tools are an R package, mldr.datasets, and a web repository with datasets, Cometa. Together, these tools will simplify the collection of datasets, their partitioning, documentation and export to multiple formats, among other functions. Some tips, recommendations and guidelines for a good experimental analysis of multi-label methods are also presented.}, doi = {10.1016/j.neucom.2018.02.011}, author = {Francisco Charte and A.J. Rivera-Rivas and David Charte and M. J. del Jesus and F. Herrera} } @conference {332, title = {Una primera aproximaci{\'o}n a la predicci{\'o}n de variables tur{\'\i}sticas con Deep Learning}, booktitle = {XVIII Conferencia de la Asociaci{\'o}n Espa{\~n}ola para la Inteligencia Artificial (CAEPIA 2018)}, year = {2018}, note = {TIN2015-68454-R}, month = {10}, pages = {939{\textendash}943}, address = {Granada (Spain)}, abstract = {El turismo es una de las actividades econ{\'o}micas m{\'a}s importantes a nivel mundial, por lo que una correcta planificaci{\'o}n de los recursos existentes en funci{\'o}n de la demanda es fundamental. En este sentido, el trabajo desarrollado permite comparar la bondad de un nuevo modelo de deep learning, LSTM, frente a un modelo cl{\'a}sico ampliamente reconocido, ARIMA. Se ha llevado a cabo un proceso de entrenamiento para obtener los modelos LSTM y ARIMA que, posteriormente se han validado utilizando datos no disponibles durante el aprendizaje. Nuestros resultados muestran que los nuevos modelos LSTM obtienen una precisi{\'o}n mayor que el cl{\'a}sico ARIMA, tanto en la validaci{\'o}n a priori como en la predicci{\'o}n posterior.}, isbn = {978-88-61970-00-7}, author = {Daniel Trujillo Viedma and A.J. Rivera-Rivas and Francisco Charte and Mar{\'\i}a J del Jesu D{\'\i}az} } @article {Mart{\'\i}nez2017, title = {A methodology for applying k-nearest neighbor to time series forecasting}, journal = {Artificial Intelligence Review}, year = {2017}, month = {Nov}, abstract = {In this paper a methodology for applying k-nearest neighbor regression on a time series forecasting context is developed. The goal is to devise an automatic tool, i.e., a tool that can work without human intervention; furthermore, the methodology should be effective and efficient, so that it can be applied to accurately forecast a great number of time series. In order to be incorporated into our methodology, several modeling and preprocessing techniques are analyzed and assessed using the N3 competition data set. One interesting feature of the proposed methodology is that it resolves the selection of important modeling parameters, such as k or the input variables, combining several models with different parameters. In spite of the simplicity of k-NN regression, our methodology seems to be quite effective.}, issn = {1573-7462}, doi = {10.1007/s10462-017-9593-z}, url = {https://doi.org/10.1007/s10462-017-9593-z}, author = {Francisco Mart{\'\i}nez and Fr{\'\i}as, Mar{\'\i}a Pilar and M.D. P{\'e}rez-Godoy and A.J. Rivera-Rivas} } @conference {308, title = {A specialized lazy learner for time series forecasting}, booktitle = {17th International Conference on Computational and Mathematical Methods in Science and Engineering, CMMSE 2017}, year = {2017}, note = {TIN2015-68854-R}, month = {7}, pages = {1397{\textendash}1403}, address = {Costa Ballena, Rota, C{\'a}adiz (Spain)}, abstract = {In a time series context the nearest neighbour algorithm looks for the historical observations most similar to the latest observations of the time series. However, some nearest neighbours can be misleading. In this paper we propose that, if prior information about the structure of the time series is known, the search space of possible neighbours can be narrowed so that some possibly misleading neighbours are avoided. This way a more effective forecasting method can be obtained.}, isbn = {978-84-617-8694-7}, author = {Francisco Mart{\'\i}nez and M.P. Fr{\'\i}as and Francisco Charte and A.J. Rivera-Rivas} } @conference {309, title = {A Transformation Approach Towards Big Data Multilabel Decision Trees}, booktitle = {14th International Work-Conference on Artificial Neural Networks (IWANN 2017)}, year = {2017}, note = {TIN2015-68454-R}, month = {6}, pages = {73{\textendash}84}, address = {C{\'a}diz (Spain)}, abstract = {A large amount of the data processed nowadays is multilabel in nature. This means that every pattern usually belongs to several categories at once. Multilabel data are abundant, and most multilabel datasets are quite large. This causes that many multilabel classification methods struggle with their processing. Tackling this task by means of big data methods seems a logical choice. However, this approach has been scarcely explored by now. The present work introduces several big data multilabel classifiers, all of them based on decision trees. After detailing how they have been designed, their predictive performance, as well as the execution time, are analyzed.}, isbn = {978-3-319-59152-0}, doi = {10.1007/978-3-319-59153-7_7}, author = {A.J. Rivera-Rivas and Francisco Charte and F. Pulgar-Rubio and M. J. del Jesus} } @article {289, title = {Comparative analysis of data mining and response surface methodology predictive models for enzymatic hydrolysis of pretreated olive tree biomass}, journal = {Computers \& Chemical Engineering}, volume = {101}, year = {2017}, note = {ENE2014-60090-C2-2-R,TIN2015-68454-R}, pages = {23{\textendash}30}, abstract = {The production of biofuels is a process that requires the adjustment of multiple parameters. Performing experiments in which these parameters are changed and the outputs are analyzed is imperative, but the cost of these tests limits their number. For this reason, it is important to design models that can predict the different outputs with changing inputs, reducing the number of actual experiments to be completed. Response Surface Methodology (RSM) is one of the most common methods for this task, but machine learning algorithms represent an interesting alternative. In the present study the predictive performance of multiple models built from the same problem data are compared: the production of bioethanol from lignocellulosic materials. Four machine learning algorithms, including two neural networks, a support vector machine and a fuzzy system, together with the RSM method, are analyzed. Results show that Reg-CO2RBFN, the method designed by the authors, improves the results of all other alternatives.}, doi = {10.1016/j.compchemeng.2017.02.008}, author = {Francisco Charte and Inmaculada Romero and M.D. P{\'e}rez-Godoy and A.J. Rivera-Rivas and Eulogio Castro} } @article {299, title = {Evoluci{\'o}n tecnol{\'o}gica del hardware de v{\'\i}deo y las GPU en los ordenadores personales}, journal = {Ense{\~n}anza y aprendizaje de ingenier{\'\i}a de computadores. Revista de experiencias docentes en ingenier{\'\i}a de computadores}, volume = {7}, year = {2017}, note = {-}, pages = {111{\textendash}128}, abstract = {This article provides a review of the most important milestones in the evolution of graphics hardware. Communication between computers and people has been advancing over time, reaching interactivity with the emergence of timesharing systems in the early 1960s. Personal computers, whose expansion began almost two decades later, used the visualization of information on a screen as the main means of communication with the user from the very beginning. The hardware in charge of this task has gradually evolved to become an indispensable part of the computer architecture, to such an extent that a large part of laptops and desktop computers incorporate the graphic hardware into the same integrated circuit that houses the microprocessor.}, issn = {2173-8688}, author = {Francisco Charte and Rueda, Antonio J. and Espinilla, Macarena and A.J. Rivera-Rivas} } @article {602, title = {MEFASD-BD: Multi-Objective Evolutionary Algorithm for Subgroup Discovery in Big Data Environments - A MapReduce Solution}, journal = {Knowledge-Based Systems}, volume = {117}, year = {2017}, note = {TIN2015-68454-R}, pages = {70-78}, doi = {http://dx.doi.org/10.1016/j.knosys.2016.08.021}, author = {F. Pulgar-Rubio and A.J. Rivera-Rivas and M.D. P{\'e}rez-Godoy and P. Gonz{\'a}lez and C. J. Carmona and M. J. del Jesus} } @conference {310, title = {Modeling the Transformation of Olive Tree Biomass into Bioethanol with Reg-CO2RBFN}, booktitle = {14th International Work-Conference on Artificial Neural Networks (IWANN 2017)}, year = {2017}, note = {TIN2015-68454-R}, month = {6}, pages = {733{\textendash}744}, address = {C{\'a}diz (Spain)}, abstract = {Research in renewable energies is a global trend. One remarkable area is the biomass transformation into biotehanol, a fuel that can replace fossil fuels. A key step in this process is the pretreatment stage, where several variables are involved. The experimentation for determining the optimal values of these variables is expensive, therefore it is necessary to model this process. This paper focus on modeling the production of biotehanol from olive tree biomass by data mining methods. Notably, the authors present Reg-CO2RBFN, an adaptation of a cooperative-competitive designing method for radial basis function networks. One of the main drawbacks in this modeling is the low number of instances in the data sets. To compare the results obtained by Reg-CO2RBFN, other well-known data mining regression methods are used to model the transformation process.}, isbn = {978-3-319-59152-0}, doi = {10.1007/978-3-319-59153-7_63}, author = {Francisco Charte and Inmaculada Romero and A.J. Rivera-Rivas and Eulogio Castro} } @conference {311, title = {On the Impact of Imbalanced Data in Convolutional Neural Networks Performance}, booktitle = {12th International Conference on Hybrid Artificial Intelligent Systems, HAIS 2017}, year = {2017}, note = {TIN2015-68454-R}, month = {6}, pages = {220{\textendash}232}, address = {La Rioja (Spain)}, abstract = {In recent years, new proposals have emerged for tackling the classification problem based on Deep Learning (DL) techniques. These proposals have shown good results in certain fields, such as image recognition. However, there are factors that must be analyzed to determine how they influence the results obtained by these new algorithms. In this paper, the classification of imbalanced data with convolutional neural networks (CNNs) is analyzed. To do this, a series of tests will be performed in which the classification of real images of traffic signals by CNNs will be performed based on data with different imbalance levels.}, isbn = {978-3-319-59650-1}, doi = {10.1007/978-3-319-59650-1_19}, author = {F. Pulgar-Rubio and A.J. Rivera-Rivas and Francisco Charte and M. J. del Jesus} } @article {300, title = {Uso de dispositivos FPGA como apoyo a la ense{\~n}anza de asignaturas de arquitectura de computadores}, journal = {Ense{\~n}anza y aprendizaje de ingenier{\'\i}a de computadores. Revista de experiencias docentes en ingenier{\'\i}a de computadores}, volume = {7}, year = {2017}, note = {-}, pages = {37{\textendash}52}, abstract = {Computer Engineering students in Spanish universities have to take one or more courses devoted to theur learning of computer architecture. The theoretical part of these subjects are usually focused on describing the architecture itself, while practical sessions are used to introduce assembly programming by means of a certain instruction set which runs into a software emulator. This paper proposes to supplement practical sessions, so that students learn to design a microprocessor by themselves from its basic components, by introducing the use of FPGA devices.}, issn = {2173-8688}, author = {Francisco Charte and Espinilla, Macarena and A.J. Rivera-Rivas and F. Pulgar-Rubio} } @conference {600, title = {Estimating the Maximum Power Delivered by Concentrating Photovoltaics Technology Through Atmospheric Conditions Using a Differential Evolution Approach}, booktitle = {Proceedings of the Eleventh International Conference on Hybrid Artificial Intelligence Systems (HAIS)}, year = {2016}, note = {ENE2009-08302, P09-TEP-5045, TIN2015-68454-R}, month = {April}, pages = {273-282}, publisher = {Springer}, organization = {Springer}, address = {Sevilla (Spain)}, author = {C. J. Carmona and F. Pulgar-Rubio and A.J. Rivera-Rivas and M. J. del Jesus and J. Aguilera} } @article {301, title = {Explotaci{\'o}n de la potencia de procesamiento mediante paralelismo: un recorrido hist{\'o}rico hasta la GPGPU}, journal = {Ense{\~n}anza y aprendizaje de ingenier{\'\i}a de computadores. Revista de experiencias docentes en ingenier{\'\i}a de computadores}, volume = {6}, year = {2016}, note = {-}, pages = {19{\textendash}33}, abstract = {Due to the improvement of semiconductor manufacturing technologies, and higher integration scales in the last decades, the power of computing devices has experienced an impressive growth. However, some obstacles have been also found along the way. As a consequence, the battle for reaching higher clock frequencies almost ended a few years ago. Nowadays, the power of processors is not measured exclusively using GHz. Other factors, as the number of cores and their inner design, also have a large impact. This paper provides an historical review on how parallelism techniques have been adapted over time to overcome these changes aiming to better exploit the available hardware.}, issn = {2173-8688}, author = {Francisco Charte and A.J. Rivera-Rivas and F. Pulgar-Rubio and Mar{\'\i}a J del Jesu D{\'\i}az} } @article {554, title = {Gamificaci{\'o}n en procesos de autoentrenamiento y autoevaluaci{\'o}n. Experiencia en la asignatura de Arquitectura de Computadores}, volume = {6}, year = {2016}, pages = {55-65}, abstract = {En la educaci{\'o}n, la gamificaci{\'o}n de procesos est{\'a} suponiendo una excelente soluci{\'o}n para aumentar la motivaci{\'o}n del alumnado para desempe{\~n}ar las actividades de su aprendizaje. As{\'\i}, en dicho entorno, la gamificaci{\'o}n se traduce en brindar a los estudiantes una motivaci{\'o}n adicional inmediata que les permita alcanzar una tarea a largo plazo. Nuestro inter{\'e}s en este trabajo se enfoca en compartir la experiencia del uso de din{\'a}micas y mecanismos de juego para incentivar el proceso de aprendizaje aut{\'o}nomo del alumno a trav{\'e}s de los procesos de autoentrenamiento y autoevaluaci{\'o}n en la preparaci{\'o}n de una prueba objetiva para la asignatura de Arquitectura de Computadores en los estudios de Ingenier{\'\i}a en Inform{\'a}tica de la Universidad de Ja{\'e}n.}, issn = {2173-8688}, author = {Espinilla, M. and Santamar{\'\i}a, J and A.J. Rivera-Rivas} } @conference {330, title = {MLSMOTE: Approaching imbalanced multilabel learning through synthetic instance generation}, booktitle = {XVII Conferencia de la Asociaci{\'o}n Espa{\~n}ola para la Inteligencia Artificial (CAEPIA 2016)}, year = {2016}, note = {-}, month = {9}, pages = {821{\textendash}822}, address = {Salamanca (Spain)}, abstract = {This is a summary of our article published in Knowledge-Based Systems to be part of the MultiConference CAEPIA{\textquoteright}16 Key-Works.}, isbn = {978-84-9012-632-5}, author = {Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @book {303, title = {Multilabel Classification: Problem Analysis, Metrics and Techniques}, year = {2016}, publisher = {Springer}, organization = {Springer}, abstract = {This book offers a comprehensive review of multilabel techniques widely used to classify and label texts, pictures, videos and music in the Internet. A deep review of the specialized literature on the field includes the available software needed to work with this kind of data. It provides the user with the software tools needed to deal with multilabel data, as well as step by step instruction on how to use them. The main topics covered are: - The special characteristics of multi-labeled data and the metrics available to measure them. - The importance of taking advantage of label correlations to improve the results. - The different approaches followed to face multi-label classification. - The preprocessing techniques applicable to multi-label datasets. - The available software tools to work with multi-label data. This book is beneficial for professionals and researchers in a variety of fields because of the wide range of potential applications for multilabel classification. Besides its multiple applications to classify different types of online information, it is also useful in many other areas, such as genomics and biology. No previous knowledge about the subject is required. The book introduces all the needed concepts to understand multilabel data characterization, treatment and evaluation.}, isbn = {978-3-319-41111-8}, doi = {10.1007/978-3-319-41111-8}, author = {F. Herrera and Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus} } @conference {314, title = {On the Impact of Dataset Complexity and Sampling Strategy in Multilabel Classifiers Performance}, booktitle = {11th International Conference on Hybrid Artificial Intelligent Systems, HAIS 2016}, year = {2016}, note = {TIN2014-57251-P,TIN2012-33856,P10-TIC-06858,P11-TIC-7765}, month = {4}, pages = {500{\textendash}511}, address = {Seville (Spain)}, abstract = {Multilabel classification (MLC) is an increasingly widespread data mining technique. Its goal is to categorize patterns in several non-exclusive groups, and it is applied in fields such as news categorization, image labeling and music classification. Comparatively speaking, MLC is a more complex task than multiclass and binary classification, since the classifier must learn the presence of various outputs at once from the same set of predictive variables. The own nature of the data the classifier has to deal with implies a certain complexity degree. How to measure this complexness level strictly from the data characteristics would be an interesting objective. At the same time, the strategy used to partition the data also influences the sample patterns the algorithm has at its disposal to train the classifier. In MLC random sampling is commonly used to accomplish this task. This paper introduces TCS (Theoretical Complexity Score), a new characterization metric aimed to assess the intrinsic complexity of a multilabel dataset, as well as a novel stratified sampling method specifically designed to fit the traits of multilabeled data. A detailed description of both proposals is provided, along with empirical results of their suitability for their respective duties.}, isbn = {978-3-319-32033-5}, doi = {10.1007/978-3-319-32034-2_42}, author = {Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @conference {315, title = {R Ultimate Multilabel Dataset Repository}, booktitle = {11th International Conference on Hybrid Artificial Intelligent Systems, HAIS 2016}, year = {2016}, note = {TIN2014-57251-P,TIN2012-33856,P10-TIC-06858,P11-TIC-7765}, month = {4}, pages = {487{\textendash}499}, address = {Seville (Spain)}, abstract = {Multilabeled data is everywhere on the Internet. From news on digital media and entries published in blogs, to videos hosted in Youtube, every object is usually tagged with a set of labels. This way they can be categorized into several non-exclusive groups. However, publicly available multilabel datasets (MLDs) are not so common. There is a handful of websites providing a few of them, using disparate file formats. Finding proper MLDs, converting them into the correct format and locating the appropriate bibliographic data to cite them are some of the difficulties usually confronted by researchers and practitioners. In this paper RUMDR (R Ultimate Multilabel Dataset Repository), a new multilabel dataset repository aimed to fuse all public MLDs, is introduced, along with mldr.datasets, an R package which eases the process of retrieving MLDs and their bibliographic information, exporting them to the desired file formats and partitioning them.}, isbn = {978-3-319-32033-5}, doi = {10.1007/978-3-319-32034-2_41}, author = {Francisco Charte and David Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @conference {10.1007/978-3-319-48799-1_8, title = {Recognition of Activities in Resource Constrained Environments; Reducing the Computational Complexity}, booktitle = {Ubiquitous Computing and Ambient Intelligence}, year = {2016}, pages = {64{\textendash}74}, publisher = {Springer International Publishing}, organization = {Springer International Publishing}, address = {Cham}, abstract = {In our current work we propose a strategy to reduce the vast amounts of data produced within smart environments for sensor-based activity recognition through usage of the nearest neighbor (NN) approach. This approach has a number of disadvantages when deployed in resource constrained environments due to its high storage requirements and computational complexity. These requirements are closely related to the size of the data used as input to NN. A wide range of prototype generation (PG) algorithms, which are designed for use with the NN approach, have been proposed in the literature to reduce the size of the data set. In this work, we investigate the use of PG algorithms and their effect on binary sensor-based activity recognition when using a NN approach. To identify the most suitable PG algorithm four datasets were used consisting of binary sensor data and their associated class activities. The results obtained demonstrated the potential of three PG algorithms for sensor-based activity recognition that reduced the computational complexity by up~to 95~{\%} with an overall accuracy higher than 90~{\%}.}, isbn = {978-3-319-48799-1}, author = {Espinilla, M. and A.J. Rivera-Rivas and M.D. P{\'e}rez-Godoy and Medina, J. and Mart{\'\i}nez, L. and Nugent, C.}, editor = {Garc{\'\i}a, Carmelo R. and Caballero-Gil, Pino and Burmester, Mike and Quesada-Arencibia, Alexis} } @article {Gcrda15, title = {A differential evolution proposal for estimating the maximum power delivered by CPV modules under real outdoor conditions}, journal = {Expert Systems with Applications}, volume = {42}, number = {13}, year = {2015}, note = {ENE2009-08302, P09-TEP-5045, TIN2012-33856}, pages = {5452{\textendash}5462}, doi = {10.1016/j.eswa.2015.02.032}, author = {B. Garc{\'\i}a-Domingo and C. J. Carmona and A.J. Rivera-Rivas and M. J. del Jesus and J. Aguilera} } @article {287, title = {Addressing imbalance in multilabel classification: Measures and random resampling algorithms}, journal = {Neurocomputing}, volume = {163}, year = {2015}, note = {TIN2012-33856,TIN2011-28488,P10-TIC-6858,P11-TIC-7765}, pages = {3{\textendash}16}, chapter = {3}, abstract = {The purpose of this paper is to analyze the imbalanced learning task in the multilabel scenario, aiming to accomplish two different goals. The first one is to present specialized measures directed to assess the imbalance level in multilabel datasets (MLDs). Using these measures we will be able to conclude which MLDs are imbalanced, and therefore would need an appropriate treatment. The second objective is to propose several algorithms designed to reduce the imbalance in MLDs in a classifier-independent way, by means of resampling techniques. Two different approaches to divide the instances in minority and majority groups are studied. One of them considers each label combination as class identifier, whereas the other one performs an individual evaluation of each label imbalance level. A random undersampling and a random oversampling algorithm are proposed for each approach, giving as result four different algorithms. All of them are experimentally tested and their effectiveness is statistically evaluated. From the results obtained, a set of guidelines directed to show when these methods should be applied is also provided.}, doi = {10.1016/j.neucom.2014.08.091}, author = {Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @conference {317, title = {An ensemble strategy for forecasting the extra-virgin olive oil price in Spain}, booktitle = {International work-conference on Time Series, ITISE 2015}, year = {2015}, note = {TIN2012-33856}, month = {7}, pages = {506{\textendash}516}, address = {Granada (Spain)}, abstract = {Time series prediction is one of the key tasks in data mining, especially in areas such as science, engineering and business. It is possible to distinguish between fundamental analysis and technical analysis while dealing with time series in the business area. Fundamental analysis takes into account different exogenous variables such as expenses, assets or liabilities. Technical analysis summarizes information using technical indicators such as momentums, moving averages or oscillators. The most influential exogenous variables and technical indicators for the olive oil price have been already identified in previous studies. The objective of the present paper is to propose an ensemble strategy, based on dividing this set of exogenous variables and technical indicators into subsets of features for the base models. These base models use CO2RBFN, a cooperative competitive algorithm for RBFNs, as learning algorithm. The obtained results show that the ensemble strategy outperforms both the base models and other classical soft computing methods.}, isbn = {978-84-16292-20-2}, author = {A.J. Rivera-Rivas and M.D. P{\'e}rez-Godoy and Francisco Charte and F. Pulgar-Rubio and M. J. del Jesus} } @conference {316, title = {CO2RBFN-CS: First Approach Introducing Cost-Sensitivity in the Cooperative-Competitive RBFN Design}, booktitle = {13th International Work-Conference on Artificial Neural Networks (IWANN 2015)}, year = {2015}, note = {TIN2012-33856}, month = {6}, pages = {361{\textendash}373}, address = {Palma de Mallorca (Spain)}, abstract = {The interest in dealing with imbalanced datasets has grown in the last years, since they represent many real world scenarios. Different methods that address imbalance problems can be classified into three categories: data sampling, algorithmic modification and cost-sensitive learning. The fundamentals of the last methodology is to assign higher costs to wrong classification classes with the aim of reducing higher cost errors. In this paper, CO2RBFN-CS, a cooperative-competitive Radial Basis Function Network algorithm that implements cost-sensitivity is presented. Specifically, a cost parameter is introduced in the training stage of the algorithm. This parameter modifies the learning rate of the weights taking into account the right (or wrong) classification of the instance, the type of class (majority or minority) and the imbalance ratio of the data set.}, isbn = {978-3-319-19257-4}, doi = {10.1007/978-3-319-19258-1_31}, author = {M.D. P{\'e}rez-Godoy and A.J. Rivera-Rivas and Francisco Charte and M. J. del Jesus} } @article {288, title = {MLSMOTE: Approaching imbalanced multilabel learning through synthetic instance generation}, journal = {Knowledge-Based Systems}, volume = {89}, year = {2015}, note = {TIN2012-33856,TIN2011-28488,P10-TIC-6858,P11-TIC-7765}, pages = {385{\textendash}397}, chapter = {385}, abstract = {Learning from imbalanced data is a problem which arises in many real-world scenarios, so does the need to build classifiers able to predict more than one class label simultaneously (multilabel classification). Dealing with imbalance by means of resampling methods is an approach that has been deeply studied lately, primarily in the context of traditional (non-multilabel) classification. In this paper the process of synthetic instance generation for multilabel datasets (MLDs) is studied and MLSMOTE (Multilabel Synthetic Minority Over-sampling Technique), a new algorithm aimed to produce synthetic instances for imbalanced MLDs, is proposed. An extensive review on how imbalance in the multilabel context has been tackled in the past is provided, along with a thorough experimental study aimed to verify the benefits of the proposed algorithm. Several multilabel classification algorithms and other multilabel oversampling methods are considered, as well as ensemble-based algorithms for imbalanced multilabel classification. The empirical analysis shows that MLSMOTE is able to improve the classification results produced by existent proposals.}, doi = {10.1016/j.knosys.2015.07.019}, author = {Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @conference {318, title = {QUINTA: A question tagging assistant to improve the answering ratio in electronic forums}, booktitle = {IEEE International Conference on Computer as a Tool, EUROCON 2015}, year = {2015}, note = {TIN2014-57251-P,TIN2012-33856,P10-TIC-06858,P11-TIC-7765}, month = {9}, pages = {1-6}, address = {Salamanca (Spain)}, abstract = {The Web is broadly used nowadays to obtain information about almost any topic, from scientific procedures to cooking recipes. Electronic forums are very popular, with thousands of questions asked and answered every day. Correctly tagging the questions posted by users usually produces quicker and better answers by other users and experts. In this paper a prototype of a system aimed to assist the users while tagging their questions is proposed. To accomplish this task, firstly the text of each post is processed to produce a multilabel dataset, then a lazy nearest neighbor multilabel classification algorithm is used to predict the tags on new posts. The obtained results are promising, opening the door to the developing of a full automated system for this task.}, isbn = {978-1-4799-8569-2}, doi = {10.1109/EUROCON.2015.7313677}, author = {Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @conference {319, title = {Resampling Multilabel Datasets by Decoupling Highly Imbalanced Labels}, booktitle = {10th International Conference on Hybrid Artificial Intelligent Systems, HAIS 2015}, year = {2015}, note = {TIN2011-28488,TIN2012-33856,P10-TIC-06858,P11-TIC-7765}, month = {6}, pages = {489{\textendash}501}, address = {Bilbao (Spain)}, abstract = {Multilabel classification is a task that has been broadly studied in late years. However, how to face learning from imbalanced multilabel datasets (MLDs) has only been addressed latterly. In this regard, a few proposals can be found in the literature, most of them based on resampling techniques adapted from the traditional classification field. The success of these methods varies extraordinarily depending on the traits of the chosen MLDs. One of the characteristics which significantly influences the behavior of multilabel resampling algorithms is the joint appearance of minority and majority labels in the same instances. It was demonstrated that MLDs with a high level of concurrence among imbalanced labels could hardly benefit from resampling methods. This paper proposes an original resampling algorithm, called REMEDIAL, which is not based on removing majority instances nor creating minority ones, but on a procedure to decouple highly imbalanced labels. As will be experimentally demonstrated, this is an interesting approach for certain MLDs.}, isbn = {978-3-319-19643-5}, doi = {10.1007/978-3-319-19644-2_41}, author = {Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @conference {Pcagd15, title = {Una primera aproximaci{\'o}n al descubrimiento de subgrupos bajo el paradigma MapReduce}, booktitle = {1er Workshop en Big Data y An{\'a}lisis de Datos Escalable}, year = {2015}, note = {TIN2012-33856}, pages = {991-1000}, author = {F. Pulgar-Rubio and C. J. Carmona and A.J. Rivera-Rivas and P. Gonz{\'a}lez and M. J. del Jesus} } @conference {655, title = {An ensemble method for time series forecasting with simple exponential smoothing}, booktitle = {Conference Computational and Mathematical Methods in Science and Engineering}, year = {2014}, month = {07}, address = {Rota, C{\'a}diz (Spain)}, author = {M. J. del Jesus and Francisco Mart{\'\i}nez and M.D. P{\'e}rez-Godoy and A.J. Rivera-Rivas and Fr{\'\i}as, Mar{\'\i}a Pilar} } @conference {321, title = {Concurrence among Imbalanced Labels and Its Influence on Multilabel Resampling Algorithms}, booktitle = {9th International Conference on Hybrid Artificial Intelligent Systems (HAIS 2014)}, year = {2014}, note = {TIN2011-28488,TIN2012-33856,P10-TIC-06858,P11-TIC-9704}, month = {6}, pages = {110{\textendash}121}, address = {Salamanca (Spain)}, abstract = {In the context of multilabel classification, the learning from imbalanced data is getting considerable attention recently. Several algorithms to face this problem have been proposed in the late five years, as well as various measures to assess the imbalance level. Some of the proposed methods are based on resampling techniques, a very well-known approach whose utility in traditional classification has been proven. This paper aims to describe how a specific characteristic of multilabel datasets (MLDs), the level of concurrence among imbalanced labels, could have a great impact in resampling algorithms behavior. Towards this goal, a measure named SCUMBLE, designed to evaluate this concurrence level, is proposed and its usefulness is experimentally tested. As a result, a straightforward guideline on the effectiveness of multilabel resampling algorithms depending on MLDs characteristics can be inferred.}, isbn = {978-3-319-07616-4}, doi = {10.1007/978-3-319-07617-1_10}, author = {Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @article {286, title = {LI-MLC: A Label Inference Methodology for Addressing High Dimensionality in the Label Space for Multilabel Classification}, journal = {IEEE Transactions on Neural Networks and Learning Systems}, volume = {25}, number = {10}, year = {2014}, note = {TIN2012-33856,TIN2011-28488,TIC-3928,P10-TIC-6858}, pages = {1842-1854}, chapter = {1842}, abstract = {Multilabel classification (MLC) has generated considerable research interest in recent years, as a technique that can be applied to many real-world scenarios. To process them with binary or multiclass classifiers, methods for transforming multilabel data sets (MLDs) have been proposed, as well as adapted algorithms able to work with this type of data sets. However, until now, few studies have addressed the problem of how to deal with MLDs having a large number of labels. This characteristic can be defined as high dimensionality in the label space (output attributes), in contrast to the traditional high dimensionality problem, which is usually focused on the feature space (by means of feature selection) or sample space (by means of instance selection). The purpose of this paper is to analyze dimensionality in the label space in MLDs, and to present a transformation methodology based on the use of association rules to discover label dependencies. These dependencies are used to reduce the label space, to ease the work of any MLC algorithm, and to infer the deleted labels in a final postprocessing stage. The proposed process is validated in an extensive experimentation with several MLDs and classification algorithms, resulting in a statistically significant improvement of performance in some cases, as will be shown.}, doi = {10.1109/TNNLS.2013.2296501}, author = {Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @conference {320, title = {MLeNN: A First Approach to Heuristic Multilabel Undersampling}, booktitle = {15th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2014}, year = {2014}, note = {TIN2011-28488,TIN2012-33856,P10-TIC-06858,P11-TIC-9704}, month = {9}, pages = {1-9}, address = {Salamanca (Spain)}, abstract = {Learning from imbalanced multilabel data is a challenging task that has attracted considerable attention lately. Some resampling algorithms used in traditional classification, such as random undersampling and random oversampling, have been already adapted in order to work with multilabel datasets. In this paper MLeNN (MultiLabel edited Nearest Neighbor), a heuristic multilabel undersampling algorithm based on the well-known Wilson{\textquoteright}s Edited Nearest Neighbor Rule, is proposed. The samples to be removed are heuristically selected, instead of randomly picked. The ability of MLeNN to improve classification results is experimentally tested, and its performance against multilabel random undersampling is analyzed. As will be shown, MLeNN is a competitive multilabel undersampling alternative, able to enhance significantly classification results.}, isbn = {978-3-319-10839-1}, doi = {10.1007/978-3-319-10840-7_1}, author = {Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @article {302, title = {Propuesta de una asignatura de Dise{\~n}o de Servidores para la especialidad de Tecnolog{\'\i}as de Informaci{\'o}n}, journal = {Ense{\~n}anza y aprendizaje de ingenier{\'\i}a de computadores. Revista de experiencias docentes en ingenier{\'\i}a de computadores}, volume = {4}, year = {2014}, note = {-}, pages = {15{\textendash}24}, abstract = {This paper presents the subject Design and Deployment of Servers belonging to the Information Technologies of the Computer Science Engineering at the University of Ja{\'e}n. The objective of this subject is to provide the training established in the different competences related to the development and deployment of hardware infrastructures that supports the currently information systems. These information systems have characteristics such as ubiquitous access, high computational costs or high availability, among others. Thus, the subject addresses concepts from design of systems, monitoring, benchmarking or evaluation, to high availability, scalability or load balancing.}, issn = {2173-8688}, author = {A.J. Rivera-Rivas and Espinilla, Macarena and A. Fern{\'a}ndez and Santamar{\'\i}a L{\'o}pez, Jos{\'e} and Francisco Charte} } @article {543, title = {Training algorithms for Radial Basis Function Networks to tackle learning processes with imbalanced data-sets}, journal = {Applied Soft Computing}, volume = {25}, year = {2014}, note = {TIN2012-33856}, pages = {26-39}, doi = {10.1016/j.asoc.2014.09.011}, author = {M.D. P{\'e}rez-Godoy and A.J. Rivera-Rivas and C. J. Carmona and M. J. del Jesus} } @conference {6706973, title = {A first analysis of the effect of local and global optimization weights methods in the cooperative-competitive design of RBFN for imbalanced environments}, booktitle = {The 2013 International Joint Conference on Neural Networks (IJCNN)}, year = {2013}, month = {Aug}, pages = {1-8}, abstract = {Many real applications are composed of data sets where the distribution of the classes is significantly different. These data sets are commonly known as imbalanced data sets. Proposed approaches that address this problem can be categorized into two types: data-based, which resample problem data in a preprocessing phase and algorithm-based which modify or create new methods to address the imbalance problem. In this paper, CO2 RBFN a cooperative-competitive design method for Radial Basis Function Networks that has previously demonstrated a good behaviour tackling imbalanced data sets, is tested using two different training weights algorithms, local and global, in order to gain knowledge about this problem. As conclusions we can outline that a more global optimizer training algorithm obtains worse results.}, keywords = {Accuracy, Algorithm design and analysis, algorithm-based approach, CO2RBFN, cooperative-competitive design method for radial basis function networks, data-based approach, global optimization weights methods, global optimizer training algorithm, imbalanced data sets, learning (artificial intelligence), Least squares approximations, local optimization weights methods, Neurons, optimisation, radial basis function networks, Sociology, Training, training weights algorithms}, issn = {2161-4407}, doi = {10.1109/IJCNN.2013.6706973}, author = {M.D. P{\'e}rez-Godoy and A.J. Rivera-Rivas and M. J. del Jesus and Francisco Mart{\'\i}nez} } @conference {322, title = {A First Approach to Deal with Imbalance in Multi-label Datasets}, booktitle = {8th International Conference on Hybrid Artificial Intelligent Systems (HAIS 2013)}, year = {2013}, note = {TIN2012-33856,TIN2011-28488,TIC-3928,P10-TIC-6858}, month = {9}, pages = {150-160}, address = {Salamanca (Spain)}, abstract = {The process of learning from imbalanced datasets has been deeply studied for binary and multi-class classification. This problem also affects to multi-label datasets. Actually, the imbalance level in multi-label datasets uses to be much larger than in binary or multi-class datasets. Notwithstanding, the proposals on how to measure and deal with imbalanced datasets in multi-label classification are scarce. In this paper, we introduce two measures aimed to obtain information about the imbalance level in multi-label datasets. Furthermore, two preprocessing methods designed to reduce the imbalance level in multi-label datasets are proposed, and their effectiveness is validated experimentally. Finally, an analysis for determining when these methods have to be applied depending on the dataset characteristics is provided.}, isbn = {978-3-642-40845-8}, doi = {10.1007/978-3-642-40846-5_16}, author = {Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @conference {10.1007/978-3-642-32922-7_45, title = {A Performance Study of Concentrating Photovoltaic Modules Using Neural Networks: An Application with CO2RBFN}, booktitle = {Soft Computing Models in Industrial and Environmental Applications}, year = {2013}, pages = {439{\textendash}448}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, address = {Berlin, Heidelberg}, abstract = {Concentrating Photovoltaic (CPV) technology attempts to optimize the efficiency of solar energy production systems and models for determining the exact module performance are needed. In this paper, a CPV module is studied by means of atmospheric conditions obtained using an automatic test and measuring system. CO2RBFN, a cooperative-competitive algorithm for the design of radial basis neural networks, is adapted and applied to these data obtaining a model with a good level of accuracy on test data, improving the results obtained by other methods considered in the experimental comparison. These initial results are promising and the obtained model could be used to work out the maximum power at the CPV reporting conditions and to analyze the performance of the module under any conditions and at any moment.}, isbn = {978-3-642-32922-7}, author = {A.J. Rivera-Rivas and B. Garc{\'\i}a-Domingo and M. J. del Jesus and J. Aguilera}, editor = {Sn{\'a}{\v s}el, V{\'a}clav and Abraham, Ajith and Corchado, Emilio S.} } @conference {323, title = {Alternative OVA Proposals for Cooperative Competitive RBFN Design in Classification Tasks}, booktitle = {12th International Work-Conference on Artificial Neural Networks (IWANN 2013)}, year = {2013}, note = {TIN2012-33856,TIC-3928}, pages = {331-338}, address = {Tenerife (Spain)}, abstract = {In the Machine Learning field when the multi-class classification problem is addressed, one possibility is to transform the data set in binary data sets using techniques such as One-Versus-All. One classifier must be trained for each binary data set and their outputs combined in order to obtain the final predicted class. The determination of the strategy used to combine the output of the binary classifiers is an interesting research area. In this paper different OVA strategies are developed and tested using as base classifier a cooperative-competitive RBFN design algorithm, CO2RBFN. One advantage of the obtained models is that they obtain as output for a given class a continuous value proportional to its level of confidence. Concretely three OVA strategies have been tested: the classical one, one based on the difference among outputs and another one based in a voting scheme, that has obtained the best results.}, isbn = {978-3-642-38678-7}, doi = {10.1007/978-3-642-38679-4_32}, author = {Francisco Charte and A.J. Rivera-Rivas and M.D. P{\'e}rez-Godoy and M. J. del Jesus} } @conference {324, title = {Improving Multi-label Classifiers via Label Reduction with Association Rules}, booktitle = {7th International Conference on Hybrid Artificial Intelligent Systems (HAIS 2012)}, year = {2012}, note = {TIN2008-06681-C06-02,TIC-3928}, month = {9}, pages = {188{\textendash}199}, address = {Salamanca (Spain)}, abstract = {Multi-label classification is a generalization of well known problems, such as binary or multi-class classification, in a way that each processed instance is associated not with a class (label) but with a subset of these. In recent years different techniques have appeared which, through the transformation of the data or the adaptation of classic algorithms, aim to provide a solution to this relatively recent type of classification problem. This paper presents a new transformation technique for multi-label classification based on the use of association rules aimed at the reduction of the label space to deal with this problem.}, isbn = {978-3-642-28930-9}, doi = {10.1007/978-3-642-28931-6_18}, author = {Francisco Charte and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @inbook {simidat230, title = {PRESETEMP: Predicci{\'o}n de Series Temporales mediante t{\'e}cnicas de Miner{\'\i}a de Datos}, booktitle = {Proyectos de Investigaci{\'o}n 2009-10}, year = {2012}, isbn = {978-84-8439-642-0}, author = {V. M. Rivas and E. Parras-Guti{\'e}rrez and M.D. P{\'e}rez-Godoy and A.J. Rivera-Rivas and M. J. Olmo and M.G. Arenas and A. Fernandez-Montoya and M. Cillero}, editor = {Eulogio Castro Galiano} } @article {Rivera2011, title = {A study on the medium-term forecasting using exogenous variable selection of the extra-virgin olive oil with soft computing methods}, journal = {Applied Intelligence}, volume = {34}, number = {3}, year = {2011}, month = {Jun}, pages = {331{\textendash}346}, abstract = {Time series forecasting is an important task for the business sector. Agents involved in the olive oil sector consider that, for the olive oil price, medium-term predictions are more important than short-term predictions. In collaboration with these agents the forecasting of the price of extra-virgin olive oil six months ahead has been established as the aim of this work. According to expert opinion, the use of exogenous variables and technical indicators can help in this task and must be included in the forecasting process. The amount of variables that can be considered makes necessary the use of feature selection algorithms in order to reduce the number of variables and to increase the interpretability and usefulness of the obtained forecasting system. Thus, in this paper CO2RBFN, a cooperative-competitive algorithm for Radial Basis Function Network design, and other soft computing methods have been applied to the data sets with the whole set of input variables and to the data sets with the selected set of input variables. The experimentation carried out shows that CO2RBFN obtains the best results in medium term forecasting for olive oil prices with the whole and with the selected set of input variables. Moreover, the feature selection methods applied to the data sets highlighted some influential variables which could be considered not only for the prediction but also for the description of the complex process involved in the medium-term forecasting of the olive oil price.}, issn = {0924-669x}, doi = {10.1007/s10489-011-0284-1}, url = {https://doi.org/10.1007/s10489-011-0284-1}, author = {A.J. Rivera-Rivas and P{\'e}rez-Recuerda, Pedro and M.D. P{\'e}rez-Godoy and M. J. del Jesus and Fr{\'\i}as, Mar{\'\i}a Pilar and Parras, Manuel} } @conference {10.1007/978-3-642-25274-7_27, title = {A Summary on the Study of the Medium-Term Forecasting of the Extra-Virgen Olive Oil Price}, booktitle = {Advances in Artificial Intelligence}, year = {2011}, pages = {263{\textendash}272}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, address = {Berlin, Heidelberg}, abstract = {In this paper we present a summary of the application of CO2RBFN, a evolutionary cooperative-competitive algorithm for Radial Basis Function Networks design, to the medium-term forecasting of the extra-virgen olive price, carry out by the SIMIDAT research group. The forecast is about the price at source of the extra-virgin olive oil six months ahead. The influential of the feature selection algorithms over the forecasting of the extra-virgin olive oil price has been analysed in this study and the results obtained with CO2RBFN have been compared with those obtained by different soft computing methods.}, isbn = {978-3-642-25274-7}, author = {A.J. Rivera-Rivas and M.D. P{\'e}rez-Godoy and M. J. del Jesus and P{\'e}rez-Recuerda, Pedro and Fr{\'\i}as, Mar{\'\i}a Pilar and Parras, Manuel}, editor = {Lozano, Jose A. and G{\'a}mez, Jos{\'e} A. and Moreno, Jos{\'e} A.} } @conference {325, title = {Multi-label Testing for CO2RBFN: A First Approach to the Problem Transformation Methodology for Multi-label Classification}, booktitle = {11th International Work-Conference on Artificial Neural Networks, IWANN 2011}, year = {2011}, note = {TIN2008-06681-C06-02,TIC-3928}, month = {6}, pages = {41{\textendash}48}, address = {Torremolinos-M{\'a}laga (Spain)}, abstract = {While in traditional classification an instance of the data set is only associated with one class, in multi-label classification this instance can be associated with more than one class or label. Examples of applications in this growing area are text categorization, functional genomics and association of semantic information to audio or video content. One way to address these applications is the Problem Transformation methodology that transforms the multi-label problem into one single-label classification problem, in order to apply traditional classification methods. The aim of this contribution is to test the performance of CO2RBFN, a cooperative-competitive evolutionary model for the design of RBFNs, in a multi-label environment, using the problem transformation methodology. The results obtained by CO2RBFN, and by other classical data mining methods, show that no algorithm outperforms the other on all the data.}, isbn = {978-3-642-21501-8}, doi = {10.1007/978-3-642-21501-8_6}, author = {A.J. Rivera-Rivas and Francisco Charte and M.D. P{\'e}rez-Godoy and M. J. del Jesus} } @conference {586, title = {A Preliminary Study on Mutation Operators in Cooperative Competitive Algorithms for RBFN Design}, booktitle = {IEEE World Congress on Computational Intelligence (WCCI)}, year = {2010}, note = {TIN2008-06681-C06-02, TIC-3928}, pages = {349{\textendash}355}, author = {M.D. P{\'e}rez-Godoy and A.J. Rivera-Rivas and C. J. Carmona and M. J. del Jesus} } @inbook {587, title = {CO2RBFN for Short and Medium Term Forecasting of the Extra Virgin Olive Oil Price}, booktitle = {Studies in Computational Intelligence}, volume = {284}, year = {2010}, note = {TIN2008-06681-C06-02, TIC-3928, UJA-08-16-30.}, pages = {113-125}, issn = {978-3-642-12538-6}, author = {M.D. P{\'e}rez-Godoy and P. P{\'e}rez and M.P. Fr{\'\i}as and A.J. Rivera-Rivas and C. J. Carmona and M. Parras} } @article {582, title = {CO2RBFN for short-term forecasting of the extra virgin olive oil price in the Spanish market}, journal = {International Journal of Hybrid Intelligent Systems}, year = {2010}, note = {TIN2008-06681-C06-02, TIC-3928, UJA-08-16-30}, pages = {75-87}, doi = {10.3233/HIS-2010-0106}, author = {M.D. P{\'e}rez-Godoy and P. P{\'e}rez and A.J. Rivera-Rivas and M. J. del Jesus and C. J. Carmona and M.P. Fr{\'\i}as and M. Parras} } @article {BERLANGA20101183, title = {GP-COACH: Genetic Programming-based learning of Compact and ACcurate fuzzy rule-based classification systems for High-dimensional problems}, journal = {Information Sciences}, volume = {180}, number = {8}, year = {2010}, pages = {1183 - 1200}, abstract = {In this paper we propose GP-COACH, a Genetic Programming-based method for the learning of COmpact and ACcurate fuzzy rule-based classification systems for High-dimensional problems. GP-COACH learns disjunctive normal form rules (generated by means of a context-free grammar) coded as one rule per tree. The population constitutes the rule base, so it is a genetic cooperative-competitive learning approach. GP-COACH uses a token competition mechanism to maintain the diversity of the population and this obliges the rules to compete and cooperate among themselves and allows the obtaining of a compact set of fuzzy rules. The results obtained have been validated by the use of non-parametric statistical tests, showing a good performance in terms of accuracy and interpretability.}, keywords = {classification, Fuzzy rule-based systems, Genetic Fuzzy Systems, Genetic programming, High-dimensional problems, Interpretability-accuracy trade-off}, issn = {0020-0255}, doi = {https://doi.org/10.1016/j.ins.2009.12.020}, url = {http://www.sciencedirect.com/science/article/pii/S0020025509005635}, author = {F.J. Berlanga and A.J. Rivera-Rivas and M. J. del Jesus and F. Herrera} } @conference {10.1007/978-3-642-13022-9_21, title = {Intelligent Systems in Long-Term Forecasting of the Extra-Virgin Olive Oil Price in the Spanish Market}, booktitle = {Trends in Applied Intelligent Systems}, year = {2010}, pages = {205{\textendash}214}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, address = {Berlin, Heidelberg}, abstract = {In this paper the problem of estimating forecasts, for the Official Market of future contracts for olive oil in Spain, is addressed. Time series analysis and their applications is an emerging research line in the Intelligent Systems field. Among the reasons for carry out time series analysis and forecasting, the associated increment in the benefits of the implied organizations must be highlighted. In this paper an adaptation of CO2RBFN, evolutionary COoperative-COmpetitive algorithm for Radial Basis Function Networks design, applied to the long-term prediction of the extra-virgin olive oil price is presented. This long-term horizon has been fixed to six months. The results of CO2RBFN have been compared with other data mining methods, typically used in time series forecasting, such as other neural networks models, a support vector machine method and a fuzzy system.}, isbn = {978-3-642-13022-9}, author = {M.D. P{\'e}rez-Godoy and P{\'e}rez, Pedro and A.J. Rivera-Rivas and M. J. del Jesus and Fr{\'\i}as, Mar{\'\i}a Pilar and Parras, Manuel}, editor = {Garc{\'\i}a-Pedrajas, Nicol{\'a}s and F. Herrera and Fyfe, Colin and Ben{\'\i}tez, Jos{\'e} Manuel and Ali, Moonis} } @conference {583, title = {Mejoras en el Dise{\~n}o Multiobjetivo de Redes de Funciones de Base Radial}, booktitle = {Congreso Espa{\~n}ol sobre Tecnolog{\'\i}as y L{\'o}gica Fuzzy (ESTYLF)}, year = {2010}, note = {TIN2008-06681-C06-02, TIC-3928.}, pages = {441-446}, author = {P.L. L{\'o}pez and A.J. Rivera-Rivas and C. J. Carmona and M.D. P{\'e}rez-Godoy} } @conference {10.1007/978-3-642-02478-8_8, title = {A Preliminar Analysis of CO2RBFN in Imbalanced Problems}, booktitle = {Bio-Inspired Systems: Computational and Ambient Intelligence}, year = {2009}, pages = {57{\textendash}64}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, address = {Berlin, Heidelberg}, abstract = {In many real classification problems the data are imbalanced, i.e., the number of instances for some classes are much higher than that of the other classes. Solving a classification task using such an imbalanced data-set is difficult due to the bias of the training towards the majority classes. The aim of this contribution is to analyse the performance of CO2RBFN, a cooperative-competitive evolutionary model for the design of RBFNs applied to classification problems on imbalanced domains and to study the cooperation of a well known preprocessing method, the {\textquoteleft}{\textquoteleft}Synthetic Minority Over-sampling Technique{\textquoteright}{\textquoteright} (SMOTE) with our algorithm. The good performance of CO2RBFN is shown through an experimental study carried out over a large collection of imbalanced data-sets.}, isbn = {978-3-642-02478-8}, author = {M.D. P{\'e}rez-Godoy and A.J. Rivera-Rivas and Fern{\'a}ndez, A. and M. J. del Jesus and F. Herrera}, editor = {Cabestany, Joan and Sandoval, Francisco and Prieto, Alberto and Corchado, Juan M.} } @conference {584, title = {Adaptaci{\'o}n de una asignatura avanzada de redes de computadores al modelo de docencia virtual dentro del marco del Espacio Europeo de Educaci{\'o}n Superior}, booktitle = {International Conference on Development and Innovation with New Technologies in Engineering Education}, year = {2009}, pages = {15-21}, author = {A.J. Rivera-Rivas and C. J. Carmona and M.D. P{\'e}rez-Godoy and M. J. del Jesus} } @conference {585, title = {EMORBFN: An Evolutionary Multiobjetive Optimization Algorithm for RBFN Design}, booktitle = {International Work-Conference on Artificial Neural Networks (IWANN)}, number = {2009}, year = {2009}, note = {TIN2008-06681-C06-02, TIN2007-60587}, pages = {752{\textendash}759}, publisher = {Lecture Notes in Computer Science 5517}, organization = {Lecture Notes in Computer Science 5517}, author = {P.L. L{\'o}pez and A.J. Rivera-Rivas and M.D. P{\'e}rez-Godoy and M. J. del Jesus and C. J. Carmona} } @conference {4626756, title = {An Study on Data Mining Methods for Short-Term Forecasting of the Extra Virgin Olive Oil Price in the Spanish Market}, booktitle = {2008 Eighth International Conference on Hybrid Intelligent Systems}, year = {2008}, month = {Sep.}, pages = {943-946}, abstract = {This paper presents the adaptation of an evolutionary cooperative competitive RBFN learning algorithm, CO2RBFN, for short-term forecasting of extra virgin olive oil price. The olive oil time series has been analyzed with a new evolutionary proposal for the design of RBFNs, CO2RBFN. Results obtained has been compared with ARIMA models and other data mining methods such as a fuzzy system developed with a GA-P algorithm, a multilayer perceptron trained with a conjugate gradient algorithm and a radial basis function network trained with a LMS algorithm. The experimentation shows the high efficacy reached for the applied methods, specially for data mining methods which have slightly outperformed ARIMA methodology.}, keywords = {Algorithm design and analysis, ARIMA, ARIMA models, Artificial neural networks, autoregressive moving average processes, CO2RBFN, conjugate gradient algorithm, conjugate gradient methods, data mining, data mining methods, evolutionary cooperative competitive, extra virgin olive oil price, Forecasting, fuzzy system, Fuzzy systems, GA-P algorithm, genetic algorithms, least mean squares methods, LMS algorithm, multilayer perceptron, multilayer perceptrons, Olive Oil Price, olive oil time series, Petroleum, pricing, radial basis function network, radial basis function networks, RBFN learning algorithm, short-term forecasting, Spanish market, time series, Time series analysis, time series forecasting, Training, vegetable oils}, doi = {10.1109/HIS.2008.132}, author = {P. P{\'e}rez and M. P. Fr{\'\i}as and M.D. P{\'e}rez-Godoy and A.J. Rivera-Rivas and M. J. d. Jesus and M. Parras and F. J. Torres} } @article {Rivera2007, title = {A new hybrid methodology for cooperative-coevolutionary optimization of radial basis function networks}, journal = {Soft Computing}, volume = {11}, number = {7}, year = {2007}, month = {May}, pages = {655{\textendash}668}, abstract = {This paper presents a new multiobjective cooperative{\textendash}coevolutive hybrid algorithm for the design of a Radial Basis Function Network (RBFN). This approach codifies a population of Radial Basis Functions (RBFs) (hidden neurons), which evolve by means of cooperation and competition to obtain a compact and accurate RBFN. To evaluate the significance of a given RBF in the whole network, three factors have been proposed: the basis function{\textquoteright}s contribution to the network{\textquoteright}s output, the error produced in the basis function radius, and the overlapping among RBFs. To achieve an RBFN composed of RBFs with proper values for these quality factors our algorithm follows a multiobjective approach in the selection process. In the design process, a Fuzzy Rule Based System (FRBS) is used to determine the possibility of applying operators to a certain RBF. As the time required by our evolutionary algorithm to converge is relatively small, it is possible to get a further improvement of the solution found by using a local minimization algorithm (for example, the Levenberg{\textendash}Marquardt method). In this paper the results of applying our methodology to function approximation and time series prediction problems are also presented and compared with other alternatives proposed in the bibliography.}, issn = {1432-7643}, doi = {10.1007/s00500-006-0128-9}, url = {https://doi.org/10.1007/s00500-006-0128-9}, author = {A.J. Rivera-Rivas and Rojas, I. and Ortega, J. and M. J. del Jesus} } @conference {simidat17, title = {Estudio de las Fases de un Algoritmo de Optimizaci{\'o}n para Redes de Funciones de Base Radial}, booktitle = {Actas del Simposio de Inteligencia Computacional (SICO)}, year = {2005}, month = {September}, pages = {237-244}, address = {Granada. Spain}, author = {A.J. Rivera-Rivas and I. Rojas and J. Ortega Lopera} } @conference {simidat10, title = {Predicci{\'o}n de series temporales mediante la coevoluci{\'o}n de funciones base}, booktitle = {Tercer Congreso Espa{\~n}ol de Metaheur{\'\i}sticas, Algoritmos Evolutivos y Bioinspirados MAEB}, year = {2004}, month = {February}, pages = {585-592}, author = {A.J. Rivera-Rivas and I. Rojas and J. Ortega Lopera} } @conference {simidat9, title = {Una estrategia difusa para la aplicaci{\'o}n de operadores en un algoritmo evolutivo}, booktitle = {XII Congreso Espa{\~n}ol sobre Tecnolog{\'\i}as y L{\'o}gica Fuzzy(ESTYLF)}, year = {2004}, month = {September}, pages = {593-598}, address = {Ja{\'e}n}, author = {A.J. Rivera-Rivas and I. Rojas and J. Ortega Lopera and M. J. del Jesus} } @conference {simidat2, title = {Optimizaci{\'o}n de redes de RBFs mediante cooperaci{\'o}n-competici{\'o}n de neuronas y algoritmos de minimizaci{\'o}n de error}, booktitle = {MAEB}, year = {2003}, month = {February}, pages = {499-508}, author = {A.J. Rivera-Rivas and I. Rojas and J. Ortega Lopera and M. J. del Jesus} } @conference {743, title = {Aproximaciones de Evoluci{\'o}n con Funciones Difusas Mediante Cooperacion y Competici{\'o}n de RBFs}, booktitle = {Congreso Espa{\~n}ol de Algoritmos Evolutivos y Bioinspirados AEB-02}, year = {2002}, month = {01}, address = {M{\'e}rida, (Espa{\~n}a)}, author = {A.J. Rivera-Rivas and Ortega, Julio and del Jesus D{\'\i}az, Mar{\'\i}a Jos{\'e} and Gonz{\'a}lez-Pe{\~n}alvez, Jes{\'u}s} } @conference {719, title = {La asignatura de planificaci{\'o}n de sistemas inform{\'a}ticos en ingenier{\'\i}a t{\'e}cnica en inform{\'a}tica de gesti{\'o}n.}, booktitle = {Jenui}, year = {2000}, month = {01}, address = {Alcala de Henares (Espa{\~n}a)}, author = {P. Gonz{\'a}lez and M.D. P{\'e}rez-Godoy and A.J. Rivera-Rivas} } @conference {731, title = {Un sistema coordinador de recursos distribuidos}, booktitle = {Jornadas cient{\'\i}ficas en tecnolog{\'\i}as de la informaci{\'o}n}, year = {2000}, month = {11}, address = {C{\'a}diz (Espa{\~n}a)}, author = {L{\'o}pez, Juan Antonio and Jos{\'e} R. Balsas and A.J. Rivera-Rivas} } @conference {730, title = {Una propuesta para la formaci{\'o}n en las tecnolog{\'\i}as Web}, booktitle = {Nuevas tecnolog{\'\i}as aplicadas a la educaci{\'o}n}, year = {2000}, month = {11}, author = {A.J. Rivera-Rivas and Jos{\'e} R. Balsas} } @conference {712, title = {Presentaci{\'o}n de TCL-TK para el desarrollo de aplicaciones por parte de usuarios no expertos en programaci{\'o}n}, booktitle = {Jornadas cient{\'\i}ficas andaluzas en tecnolog{\'\i}a de la informaci{\'o}n}, year = {1998}, address = {C{\'a}diz (Espa{\~n}a)}, author = {P. Gonz{\'a}lez and A.J. Rivera-Rivas and M.D. P{\'e}rez-Godoy} } @conference {710, title = {Herramientas para el desarrollo de pr{\'a}cticas en una asignatura de redes de computadores de una ingenier{\'\i}a t{\'e}cnica}, booktitle = {Jornadas de inform{\'a}tica}, year = {1997}, address = {C{\'a}diz (Espa{\~n}a)}, author = {A.J. Rivera-Rivas and M.D. P{\'e}rez-Godoy} }