Publications

@article{Rodríguez2020,

title = {An experimental evaluation of mixup regression forests},

author = {Juan José Rodríguez and Mario Juez-Gil and Álvar Arnaiz-González and Ludmila I Kuncheva},

url = {https://www.sciencedirect.com/science/article/abs/pii/S0957417420302013?via%3Dihub},

doi = {10.1016/j.eswa.2020.113376},

issn = {0957-4174},

year  = {2020},

date = {2020-08-01},

journal = {Expert Systems with Applications},

volume = {151},

number = {113376},

abstract = {Over the past few decades, the remarkable prediction capabilities of ensemble methods have been used within a wide range of applications. Maximization of base-model ensemble accuracy and diversity are the keys to the heightened performance of these methods. One way to achieve diversity for training the base models is to generate artificial/synthetic instances for their incorporation with the original instances. Recently, the mixup method was proposed for improving the classification power of deep neural networks (Zhang, Cissé, Dauphin, and Lopez-Paz, 2017). Mixup method generates artificial instances by combining pairs of instances and their labels, these new instances are used for training the neural networks promoting its regularization. In this paper, new regression tree ensembles trained with mixup, which we will refer to as Mixup Regression Forest, are presented and tested. The experimental study with 61 datasets showed that the mixup approach improved the results of both Random Forest and Rotation Forest.},

keywords = {Mixup, Random forest, Regression, Rotation forest, SELECTED},

pubstate = {published},

tppubtype = {article}

}

@article{Kordos2019,

title = {Evolutionary prototype selection for multi-output regression},

author = {Mirosław Kordos and Álvar Arnaiz-González and César García-Osorio},

url = {https://www.sciencedirect.com/science/article/pii/S0925231219307611?fbclid=IwAR1qb5kLk1-PyqfAPprRnb6Jv75rMgJS3dY1rDqWF610G2lCttEW3QIBU4c},

doi = {10.1016/j.neucom.2019.05.055},

issn = {0925-2312},

year  = {2019},

date = {2019-09-17},

journal = {Neurocomputing},

volume = {358},

pages = {309-320},

abstract = {A novel approach to prototype selection for multi-output regression data sets is presented. A multi-objective evolutionary algorithm is used to evaluate the selections using two criteria: training data set compression and prediction quality expressed in terms of root mean squared error. A multi-target regressor based on k-NN was used for that purpose during the training to evaluate the error, while the tests were performed using four different multi-target predictive models. The distance matrices used by the multi-target regressor were cached to accelerate operational performance. Multiple Pareto fronts were also used to prevent overfitting and to obtain a broader range of solutions, by using different probabilities in the initialization of populations and different evolutionary parameters in each one. The results obtained with the benchmark data sets showed that the proposed method greatly reduced data set size and, at the same time, improved the predictive capabilities of the multi-output regressors trained on the reduced data set.},

keywords = {Multi-output, Multi-target, Prototype selection, Regression, SELECTED},

pubstate = {published},

tppubtype = {article}

}

@article{ArnaizGonzalez201669,

title = {Fusion of instance selection methods in regression tasks},

author = {Álvar Arnaiz-González and Marcin Blachnik and Mirosław Kordos and César García-Osorio},

url = {http://www.sciencedirect.com/science/article/pii/S1566253515001141},

doi = {10.1016/j.inffus.2015.12.002},

issn = {1566-2535},

year  = {2016},

date = {2016-01-01},

journal = {Information Fusion},

volume = {30},

pages = {69 - 79},

abstract = {Abstract Data pre-processing is a very important aspect of data mining. In this paper we discuss instance selection used for prediction algorithms, which is one of the pre-processing approaches. The purpose of instance selection is to improve the data quality by data size reduction and noise elimination. Until recently, instance selection has been applied mainly to classification problems. Very few recent papers address instance selection for regression tasks. This paper proposes fusion of instance selection algorithms for regression tasks to improve the selection performance. As the members of the ensemble two different families of instance selection methods are evaluated: one based on distance threshold and the other one on converting the regression task into a multiple class classification task. Extensive experimental evaluation performed on the two regression versions of the Edited Nearest Neighbor (ENN) and Condensed Nearest Neighbor (CNN) methods showed that the best performance measured by the error value and data size reduction are in most cases obtained for the ensemble methods.},

keywords = {Data Mining, Ensemble methods, Instance selection, Regression, SELECTED},

pubstate = {published},

tppubtype = {article}

}

@article{ArnaizGonzalez201669b,

title = {Instance selection for regression by discretization},

author = {Álvar Arnaiz-González and José Francisco Díez-Pastor and Juan José Rodríguez and César García-Osorio},

doi = {10.1016/j.eswa.2015.12.046},

issn = {0957-4174},

year  = {2016},

date = {2016-01-01},

journal = {Expert Systems With Applications},

keywords = {Data Mining, Instance selection, Regression},

pubstate = {published},

tppubtype = {article}

}

@article{ArnaizGonzález2016,

title = {Instance selection for regression: Adapting DROP},

author = {Álvar Arnaiz-González and José Francisco Díez-Pastor and Juan José Rodríguez and César García-Osorio},

url = {http://www.sciencedirect.com/science/article/pii/S0925231216301953},

doi = {10.1016/j.neucom.2016.04.003},

issn = {0925-2312},

year  = {2016},

date = {2016-01-01},

journal = {Neurocomputing},

volume = {201},

pages = {66–81},

abstract = {Abstract Machine Learning has two central processes of interest that captivate the scientific community: classification and regression. Although instance selection for classification has shown its usefulness and has been researched in depth, instance selection for regression has not followed the same path and there are few published algorithms on the subject. In this paper, we propose that various adaptations of DROP, a well-known family of instance selection methods for classification, be applied to regression. Their behaviour is analysed using a broad range of datasets. The results are presented of the analysis of four new proposals for the reduction of dataset size, the effect on error when several classifiers are trained with the reduced dataset, and their robustness against noise. This last aspect is especially important, since in real life, it is frequent that the registered data be inexact and present distortions due to different causes: errors in the measurement tools, typos when writing results, existence of outliers and spurious readings, corruption in files, etc. When the datasets are small it is possible to manually correct these problems, but for big and huge datasets is better to have automatic methods to deal with these problems. In the experimental part, the proposed methods are found to be quite robust to noise.},

keywords = {Data Mining, DROP, Instance selection, Noise filtering, Regression},

pubstate = {published},

tppubtype = {article}

}

@article{Arnaiz-González2016,

title = {Random feature weights for regression trees},

author = {Álvar Arnaiz-González and José Francisco Díez-Pastor and César García-Osorio and Juan José Rodríguez},

url = {http://dx.doi.org/10.1007/s13748-016-0081-5},

doi = {10.1007/s13748-016-0081-5},

issn = {2192-6360},

year  = {2016},

date = {2016-01-01},

journal = {Progress in Artificial Intelligence},

volume = {5},

number = {2},

pages = {91–103},

abstract = {Ensembles are learning methods the operation of which relies on a combination of different base models. The diversity of ensembles is a fundamental aspect that conditions their operation. Random Feature Weights RFW was proposed as a classification-tree ensemble construction method in which diversity is introduced into each tree by means of a random weight associated with each attribute. These weights vary from one tree to another in the ensemble. In this article, the idea of RFW is adapted to decision-tree regression. A comparison is drawn with other ensemble construction methods: Bagging, Random Forest, Iterated Bagging, Random Subspaces and AdaBoost.R2 obtaining competitive results.},

keywords = {Data Mining, Ensemble methods, Regression},

pubstate = {published},

tppubtype = {article}

}

@article{amcPardoDGR13,

title = {Rotation Forests for regression},

author = {Carlos Pardo and José Francisco Díez-Pastor and César García-Osorio and Juan José Rodríguez},

doi = {10.1016/j.amc.2013.03.139},

issn = {0096-3003},

year  = {2013},

date = {2013-01-01},

journal = {Applied Mathematics and Computation},

volume = {219},

number = {19},

pages = {9914-9924},

keywords = {Data Mining, Regression, Rotation forest},

pubstate = {published},

tppubtype = {article}

}