Publications

@article{Juez-Gil2021bb,

title = {Approx-SMOTE: Fast SMOTE for Big Data on Apache Spark},

author = {Mario Juez-Gil and Álvar Arnaiz-González and Juan José Rodríguez and Carlos López-Nozal and César García-Osorio},

url = {https://www.sciencedirect.com/science/article/pii/S0925231221012832},

doi = {https://doi.org/10.1016/j.neucom.2021.08.086},

issn = {0925-2312},

year  = {2021},

date = {2021-11-13},

journal = {Neurocomputing},

volume = {464},

pages = {432-437},

abstract = {One of the main goals of Big Data research, is to find new data mining methods that are able to process large amounts of data in acceptable times. In Big Data classification, as in traditional classification, class imbalance is a common problem that must be addressed, in the case of Big Data also looking for a solution that can be applied in an acceptable execution time. In this paper we present Approx-SMOTE, a parallel implementation of the SMOTE algorithm for the Apache Spark framework. The key difference with the original SMOTE, besides parallelism, is that it uses an approximated version of k-Nearest Neighbor which makes it highly scalable. Although an implementation of SMOTE for Big Data already exists (SMOTE-BD), it uses an exact Nearest Neighbor search, which does not make it entirely scalable. Approx-SMOTE on the other hand is able to achieve up to 30 times faster run times without sacrificing the improved classification performance offered by the original SMOTE.},

keywords = {Big data, Data Mining, imbalance, SMOTE, Spark},

pubstate = {published},

tppubtype = {article}

}

@article{Güemes-Peña2018,

title = {Emerging topics in mining software repositories},

author = {Diego Güemes-Peña and Carlos López-Nozal and Raúl Marticorena-Sánchez and Jesús Maudes-Raedo},

url = {https://link.springer.com/content/pdf/10.1007/s13748-018-0147-7.pdf},

doi = {10.1007/s13748-018-0147-7},

issn = {2192-6360},

year  = {2018},

date = {2018-01-01},

journal = {Progress in Artificial Intelligence},

pages = {1-11},

abstract = {A software process is a set of related activities that culminates in the production of a software package: specification, design, implementation, testing, evolution into new versions, and maintenance. There are also other supporting activities such as configuration and change management, quality assurance, project management, evaluation of user experience, etc. Software repositories are infrastructures to support all these activities. They can be composed with several systems that include code change management, bug tracking, code review, build system, release binaries, wikis, forums, etc. This position paper on mining software repositories presents a review and a discussion of research in this field over the past decade. We also identify applied machine learning strategies, current working topics, and future challenges for the improvement of company decision-making systems. Machine learning is defined as the process of discovering patterns in data. It can be applied to software repositories, since every change is recorded as data. Companies can then use these patterns as the basis for their decision-making systems and for knowledge discovery.},

keywords = {Data Mining, Machine learning, Software engineering, Software process, Software repository},

pubstate = {published},

tppubtype = {article}

}

@article{Maudes2017,

title = {Random Forest ensemble prediction of stent dimensions in microfabrication processes},

author = {Jesus Maudes and Andrés Bustillo and Antonio J Guerra and Joaquim Ciurana},

url = {https://doi.org/10.1007/s00170-016-9695-9},

doi = {10.1007/s00170-016-9695-9},

issn = {1433-3015},

year  = {2017},

date = {2017-07-01},

journal = {The International Journal of Advanced Manufacturing Technology},

volume = {91},

number = {1},

pages = {879–893},

abstract = {The recent development of new laser machine tools for the manufacture of micro-scale metallic components has boosted demand in the field of medical applications. However, the optimization of this process encounters a major problem: a knowledge gap concerning the relation between the controllable parameters of these machine tools and the quality of the machined components. Our research proposes a two-step strategy to approach this problem for the manufacture of stents. First, a screening test identifies good and bad performance conditions for the laser process and generates useful information on cutting performance; then, a stent is manufactured under different cutting conditions and the most accurate machine learning technique to model this process is identified. This strategy is validated with the performance of experiments that vary pulse duration, laser power, and cutting speed, and measure two geometrical characteristics of the stent geometry. The results showed that linear Support Vector Machines can identify good and bad cutting conditions, while Random Forest ensembles of regression trees can predict with high accuracy the two characteristics of the stent geometry under study. Besides, this technique can extract useful information from the screening test that improves its final accuracy. In view of the small dataset size, an alternative based on the leave-one-out technique was used, instead of standard cross validation, so as to assure the generalization capability of the models.},

keywords = {Data Mining, Ensembles of regressors, Random forest, Regression trees, Stents Laser machining},

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{ArnaizGonzálezLSHIS2016,

title = {Instance selection of linear complexity for big data},

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/S0950705116301617},

doi = {10.1016/j.knosys.2016.05.056},

issn = {0950-7051},

year  = {2016},

date = {2016-01-01},

journal = {Knowledge-Based Systems},

volume = {107},

pages = {83–95},

abstract = {Abstract Over recent decades, database sizes have grown considerably. Larger sizes present new challenges, because machine learning algorithms are not prepared to process such large volumes of information. Instance selection methods can alleviate this problem when the size of the data set is medium to large. However, even these methods face similar problems with very large-to-massive data sets. In this paper, two new algorithms with linear complexity for instance selection purposes are presented. Both algorithms use locality-sensitive hashing to find similarities between instances. While the complexity of conventional methods (usually quadratic, O ( n 2 ) , or log-linear, O ( n log n ) ) means that they are unable to process large-sized data sets, the new proposal shows competitive results in terms of accuracy. Even more remarkably, it shortens execution time, as the proposal manages to reduce complexity and make it linear with respect to the data set size. The new proposal has been compared with some of the best known instance selection methods for testing and has also been evaluated on large data sets (up to a million instances).},

keywords = {Big data, Data Mining, Data reduction, Hashing, Instance selection, Nearest neighbors, SELECTED},

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{RandomBalance,

title = {Random Balance: Ensembles of variable priors classifiers for imbalanced data},

author = {José Francisco Díez-Pastor and Juan José Rodríguez and César García-Osorio and Ludmila I Kuncheva},

url = {http://www.sciencedirect.com/science/article/pii/S0950705115001720},

doi = {10.1016/j.knosys.2015.04.022},

issn = {0950-7051},

year  = {2015},

date = {2015-01-01},

journal = {Knowledge-Based Systems},

volume = {85},

pages = {96-111},

abstract = {Abstract In Machine Learning, a data set is imbalanced when the class proportions are highly skewed. Class-imbalanced problems sets arise routinely in many application domains and pose a challenge to traditional classifiers. We propose a new approach to building ensembles of classifiers for two-class imbalanced data sets, called Random Balance. Each member of the Random Balance ensemble is trained with data sampled from the training set and augmented by artificial instances obtained using SMOTE. The novelty in the approach is that the proportions of the classes for each ensemble member are chosen randomly. The intuition behind the method is that the proposed diversity heuristic will ensure that the ensemble contains classifiers that are specialized for different operating points on the ROC space, thereby leading to larger AUC compared to other ensembles of classifiers. Experiments have been carried out to test the Random Balance approach by itself, and also in combination with standard ensemble methods. As a result, we propose a new ensemble creation method called RB-Boost which combines Random Balance with AdaBoost.M2. This combination involves enforcing random class proportions in addition to instance re-weighting. Experiments with 86 imbalanced data sets from two well known repositories demonstrate the advantage of the Random Balance approach.},

keywords = {AdaBoost, Bagging, Class-imbalanced problems, Classifier ensembles, Data Mining, Ensemble methods, SELECTED, SMOTE, Undersampling},

pubstate = {published},

tppubtype = {article}

}

@article{DiezPastor201598,

title = {Diversity techniques improve the performance of the best imbalance learning ensembles},

author = {José Francisco Díez-Pastor and Juan José Rodríguez and César García-Osorio and Ludmila I Kuncheva},

url = {http://www.sciencedirect.com/science/article/pii/S0020025515005186},

doi = {10.1016/j.ins.2015.07.025},

issn = {0020-0255},

year  = {2015},

date = {2015-01-01},

journal = {Information Sciences},

volume = {325},

pages = {98 - 117},

abstract = {Abstract Many real-life problems can be described as unbalanced, where the number of instances belonging to one of the classes is much larger than the numbers in other classes. Examples are spam detection, credit card fraud detection or medical diagnosis. Ensembles of classifiers have acquired popularity in this kind of problems for their ability to obtain better results than individual classifiers. The most commonly used techniques by those ensembles especially designed to deal with imbalanced problems are for example Re-weighting, Oversampling and Undersampling. Other techniques, originally intended to increase the ensemble diversity, have not been systematically studied for their effect on imbalanced problems. Among these are Random Oracles, Disturbing Neighbors, Random Feature Weights or Rotation Forest. This paper presents an overview and an experimental study of various ensemble-based methods for imbalanced problems, the methods have been tested in its original form and in conjunction with several diversity-increasing techniques, using 84 imbalanced data sets from two well known repositories. This paper shows that these diversity-increasing techniques significantly improve the performance of ensemble methods for imbalanced problems and provides some ideas about when it is more convenient to use these diversifying techniques.},

keywords = {Class-imbalanced problems, Classifier ensembles, Data Mining, Diversity, Ensemble methods, Rotation forest, SELECTED, SMOTE, Undersampling},

pubstate = {published},

tppubtype = {article}

}

@article{DiezPastor2014,

title = {Tree ensemble construction using a GRASP-based heuristic and annealed randomness},

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

url = {http://www.sciencedirect.com/science/article/pii/S1566253514000141},

doi = {10.1016/j.inffus.2014.01.009},

issn = {1566-2535},

year  = {2014},

date = {2014-01-01},

journal = {Information Fusion},

volume = {20},

number = {0},

pages = {189–202},

abstract = {Abstract Two new methods for tree ensemble construction are presented: G-Forest and GAR-Forest. In a similar way to Random Forest, the tree construction process entails a degree of randomness. The same strategy used in the GRASP metaheuristic for generating random and adaptive solutions is used at each node of the trees. The source of diversity of the ensemble is the randomness of the solution generation method of GRASP. A further key feature of the tree construction method for GAR-Forest is a decreasing level of randomness during the process of constructing the tree: maximum randomness at the root and minimum randomness at the leaves. The method is therefore named ``GAR'', GRASP with annealed randomness. The results conclusively demonstrate that G-Forest and GAR-Forest outperform Bagging, AdaBoost, MultiBoost, Random Forest and Random Subspaces. The results are even more convincing in the presence of noise, demonstrating the robustness of the method. The relationship between base classifier accuracy and their diversity is analysed by application of kappa-error diagrams and a variant of these called kappa-error relative movement diagrams.},

keywords = {Boosting, Classifier ensembles, Data Mining, Decision trees, Ensemble methods, GRASP metahuristic, Random forest},

pubstate = {published},

tppubtype = {article}

}

@article{PedrajasOsorio2013,

title = {Boosting for class-imbalanced datasets using genetically evolved supervised non-linear projections},

author = {Nicolás García-Pedrajas and César García-Osorio},

url = {http://dx.doi.org/10.1007/s13748-012-0028-4},

doi = {10.1007/s13748-012-0028-4},

issn = {2192-6352},

year  = {2013},

date = {2013-01-01},

journal = {Progress in Artificial Intelligence},

volume = {2},

number = {1},

pages = {29-44},

publisher = {Springer-Verlag},

keywords = {Boosting, Class-imbalanced problems, Data Mining, Real-coded genetic algorithms},

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}

}

@article{RFW2012,

title = {Random Feature Weights for Decision Tree Ensemble Construction},

author = {Jesús Maudes and Juan José Rodríguez and César García-Osorio and Nicolás García-Pedrajas},

doi = {10.1016/j.inffus.2010.11.004},

issn = {1566-2535},

year  = {2012},

date = {2012-01-01},

journal = {Information Fusion},

volume = {13},

number = {1},

pages = {20-30},

keywords = {Bagging, Boosting, Classifier ensembles, Data Mining, Decision trees, Ensemble methods, Random forest},

pubstate = {published},

tppubtype = {article}

}

@article{BPforIndustrialData2012,

title = {Boosting Projections to improve surface roughness prediction in high-torque milling operations},

author = {José Francisco Díez-Pastor and Andrés Bustillo and Guillem Quintana and César García-Osorio},

url = {http://dx.doi.org/10.1007/s00500-012-0846-0},

doi = {10.1007/s00500-012-0846-0},

issn = {1432-7643 (Print) 1433-7479 (Online)},

year  = {2012},

date = {2012-01-01},

journal = {Soft Computing},

volume = {16},

number = {8},

pages = {1427-1437},

keywords = {Applied Machine Learning, Business intelligence, Data Mining, Ensemble methods},

pubstate = {published},

tppubtype = {article}

}

@article{ensemblesProjections2011,

title = {Constructing ensembles of classifiers using supervised projection methods based on misclassified instances},

author = {Nicolás García-Pedrajas and César García-Osorio},

url = {http://www.sciencedirect.com/science/article/B6V03-50GJ2J0-7/2/6b1890282b8bfb900f1174dc7a027a9c},

doi = {10.1016/j.eswa.2010.06.072},

issn = {0957-4174},

year  = {2011},

date = {2011-01-01},

journal = {Expert Systems with Applications},

volume = {38},

number = {1},

pages = {343–359},

keywords = {Boosting, Classification, Data Mining, Linear projections, Subspace methods},

pubstate = {published},

tppubtype = {article}

}

@article{RandomProjectionsLinearSVMs,

title = {Random projections for linear SVM ensembles},

author = {Jesús Maudes and Juan José Rodríguez and César García-Osorio and Carlos Pardo},

url = {http://dx.doi.org/10.1007/s10489-011-0283-2},

doi = {10.1007/s10489-011-0283-2},

issn = {0924-669X, 1573-7497},

year  = {2011},

date = {2011-01-01},

journal = {Applied Intelligence},

volume = {34},

pages = {347-359},

publisher = {Springer Netherlands},

note = {10.1007/s10489-011-0283-2},

keywords = {Data Mining, Ensemble methods, Support vector machines},

pubstate = {published},

tppubtype = {article}

}

@article{1746771,

title = {Democratic instance selection: A linear complexity instance selection algorithm based on classifier ensemble concepts},

author = {César García-Osorio and Aida Haro-García and Nicolás García-Pedrajas},

doi = {10.1016/j.artint.2010.01.001},

issn = {0004-3702},

year  = {2010},

date = {2010-01-01},

journal = {Artif. Intell.},

volume = {174},

number = {5-6},

pages = {410–441},

publisher = {Elsevier Science Publishers Ltd.},

address = {Essex, UK},

keywords = {Big data, Data Mining, Instance selection},

pubstate = {published},

tppubtype = {article}

}

@article{RGM10,

title = {Forests of Nested Dichotomies},

author = {Juan José Rodríguez and César García-Osorio and Jesús Maudes},

doi = {10.1016/j.patrec.2009.09.015},

issn = {0167-8655},

year  = {2010},

date = {2010-01-01},

journal = {Pattern Recognition Letters},

volume = {31},

number = {2},

pages = {125-132},

keywords = {Data Mining, Decision trees, Ensemble methods},

pubstate = {published},

tppubtype = {article}

}

@article{cgosorio07boosting,

title = {Nonlinear ``boosting'' projections for ensemble construction},

author = {Nicolás García-Pedrajas and César García-Osorio and Colin Fyfe},

url = {http://jmlr.csail.mit.edu/papers/volume8/garcia-pedrajas07a/garcia-pedrajas07a.pdf},

issn = {1532-4435},

year  = {2007},

date = {2007-01-01},

journal = {Journal of Machine Learning Research},

volume = {8},

pages = {1–33},

abstract = {In this paper we propose a novel approach for ensemble construction based on the use of nonlinear 

projections to achieve both accuracy and diversity of individual classifiers. The proposed approach 

combines the philosophy of boosting, putting more effort on difficult instances, with the basis of 

the random subspace method. Our main contribution is that instead of using a random subspace, 

we construct a projection taking into account the instances which have posed most difficulties to 

previous classifiers. In this way, consecutive nonlinear projections are created by a neural network 

trained using only incorrectly classified instances. The feature subspace induced by the hidden layer 

of this network is used as the input space to a new classifier. The method is compared with bagging 

and boosting techniques, showing an improved performance on a large set of 44 problems from the 

UCI Machine Learning Repository. An additional study showed that the proposed approach is less 

sensitive to noise in the data than boosting methods.},

keywords = {Boosting, Classifier ensembles, Data Mining, Ensemble methods, Neural networks, Nonlinear projections},

pubstate = {published},

tppubtype = {article}

}

@article{cgosorio04skpca,

title = {Regaining Sparsity in Kernel Principal Components},

author = {César García-Osorio and Colin Fyfe},

issn = {0925-2312},

year  = {2005},

date = {2005-08-01},

journal = {Neurocomputing},

volume = {67},

pages = {398–402},

abstract = {Support Vector Machines are supervised regression and classification machines which have the nice property of automatically identifying which of the data points are most important in creating the machine. Kernel Principal Component Analysis (KPCA) is a related technique in that it also relies on linear operations in a feature space but does not have this ability to identify important points. Sparse KPCA goes too far in that it identifies a single data point as most important. We show how, by bagging the data, we may create a compromise which gives us a sparse but not grandmother representation for KPCA.},

keywords = {Data Mining, Kernel methods, Kernel Principal Components},

pubstate = {published},

tppubtype = {article}

}

@article{cgosorio05AndrewsSOM,

title = {The Combined Use of Self-organizing Maps and Andrews' Curves},

author = {César García-Osorio and Colin Fyfe},

doi = {10.1142/S0129065705000207},

issn = {0129-0657},

year  = {2005},

date = {2005-01-01},

journal = {International Journal of Neural Systems},

volume = {15},

number = {3},

pages = {1-10},

keywords = {Andrews curves, Data Mining, Data visualization, Neural networks, Self organizing maps},

pubstate = {published},

tppubtype = {article}

}