Publications

@article{GUTIERREZAVILES201442,

title = {TriGen: A genetic algorithm to mine triclusters in temporal gene expression data},

author = {D. Gutiérrez-Avilés and C. Rubio-Escudero and F. Martínez-Álvarez and J.C. Riquelme},

url = {http://www.sciencedirect.com/science/article/pii/S0925231213011004},

doi = {10.1016/j.neucom.2013.03.061},

year  = {2014},

date = {2014-01-01},

journal = {Neurocomputing},

volume = {132},

pages = {42-53},

abstract = {Analyzing microarray data represents a computational challenge due to the characteristics of these data. Clustering techniques are widely applied to create groups of genes that exhibit a similar behavior under the conditions tested. Biclustering emerges as an improvement of classical clustering since it relaxes the constraints for grouping genes to be evaluated only under a subset of the conditions and not under all of them. However, this technique is not appropriate for the analysis of longitudinal experiments in which the genes are evaluated under certain conditions at several time points. We present the TriGen algorithm, a genetic algorithm that finds triclusters of gene expression that take into account the experimental conditions and the time points simultaneously. We have used TriGen to mine datasets related to synthetic data, yeast (Saccharomyces cerevisiae) cell cycle and human inflammation and host response to injury experiments. TriGen has proved to be capable of extracting groups of genes with similar patterns in subsets of conditions and times, and these groups have shown to be related in terms of their functional annotations extracted from the Gene Ontology.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{Gutierrez-Aviles2014,

title = {Mining 3D Patterns from Gene Expression Temporal Data: A New Tricluster Evaluation Measure},

author = {D. Gutiérrez-Avilés and C. Rubio-Escudero},

url = {http://www.hindawi.com/journals/tswj/2014/624371/},

doi = {10.1155/2014/624371},

year  = {2014},

date = {2014-01-01},

journal = {The Scientific World Journal},

volume = {2014},

pages = {1-16},

abstract = {Microarrays have revolutionized biotechnological research. The analysis of new data generated represents a computational challenge due to the characteristics of these data. Clustering techniques are applied to create groups of genes that exhibit a similar behavior. Biclustering emerges as a valuable tool for microarray data analysis since it relaxes the constraints for grouping, allowing genes to be evaluated only under a subset of the conditions. However, if a third dimension appears in the data, triclustering is the appropriate tool for the analysis. This occurs in longitudinal experiments in which the genes are evaluated under conditions at several time points. All clustering, biclustering, and triclustering techniques guide their search for solutions by a measure that evaluates the quality of clusters. We present an evaluation measure for triclusters called Mean Square Residue 3D. This measure is based on the classic biclustering measure Mean Square Residue. Mean Square Residue 3D has been applied to both synthetic and real data and it has proved to be capable of extracting groups of genes with homogeneous patterns in subsets of conditions and times, and these groups have shown a high correlation level and they are also related to their functional annotations extracted from the Gene Ontology project.},

keywords = {bioinformatics, time series},

pubstate = {published},

tppubtype = {article}

}

@article{NEUCOM2014,

title = {Selecting the Best Measures to Discover Quantitative Association Rules},

author = {M. Martínez-Ballesteros and F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme},

url = {https://www.sciencedirect.com/science/article/pii/S0925231213007029},

doi = {10.1016/j.neucom.2013.01.056},

year  = {2014},

date = {2014-01-01},

journal = {Neurocomputing},

volume = {126},

pages = {3-14},

abstract = {The majority of the existing techniques to mine association rules typically use the support and the confidence to evaluate the quality of the rules obtained. However, these two measures may not be sufficient to properly assess their quality due to some inherent drawbacks they present. A review of the literature reveals that there exist many measures to evaluate the quality of the rules, but that the simultaneous optimization of all measures is complex and might lead to poor results. In this work, a principal components analysis is applied to a set of measures that evaluate quantitative association rules' quality. From this analysis, a reduced subset of measures has been selected to be included in the fitness function in order to obtain better values for the whole set of quality measures, and not only for those included in the fitness function. This is a general-purpose methodology and can, therefore, be applied to the fitness function of any algorithm. To validate if better results are obtained when using the function fitness composed of the subset of measures proposed here, the existing QARGA algorithm has been applied to a wide variety of datasets. Finally, a comparative analysis of the results obtained by means of the application of QARGA with the original fitness function is provided, showing a remarkable improvement when the new one is used.},

keywords = {association rules},

pubstate = {published},

tppubtype = {article}

}

@article{Marquez-Chamorro2014,

title = {Evolutionary decision rules for predicting protein contact maps},

author = {A. E. Marquez-Chamorro and G. Asencio-Cortes and F. Divina and J. S. Aguilar-Ruiz},

doi = {10.1007/s10044-012-0297-3},

issn = {1433-7541},

year  = {2014},

date = {2014-01-01},

journal = {Pattern Analysis and Applications},

volume = {4},

number = {17},

pages = {725-737},

abstract = {Protein structure prediction is currently one of the main open challenges in Bioinformatics. The protein contact map is an useful, and commonly used, representation for protein 3D structure and represents binary proximities (contact or non-contact) between each pair of amino acids of a protein. In this work, we propose a multi-objective evolutionary approach for contact map prediction based on physico-chemical properties of amino acids. The evolutionary algorithm produces a set of decision rules that identifies contacts between amino acids. The rules obtained by the algorithm impose a set of conditions based on amino acid properties to predict contacts. We present results obtained by our approach on four different protein data sets. A statistical study was also performed to extract valid conclusions from the set of prediction rules generated by our algorithm. Results obtained confirm the validity of our proposal.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{MARTINEZALVAREZ2013198,

title = {Determining the best set of seismicity indicators to predict earthquakes. Two case studies: Chile and the Iberian Peninsula},

author = {F. Martínez-Álvarez and J. Reyes and A. Morales-Esteban and C. Rubio-Escudero},

url = {http://www.sciencedirect.com/science/article/pii/S0950705113001871},

doi = {10.1016/j.knosys.2013.06.011},

year  = {2013},

date = {2013-01-01},

journal = {Knowledge-Based Systems},

volume = {50},

pages = {198-210},

abstract = {This work explores the use of different seismicity indicators as inputs for artificial neural networks. The combination of multiple indicators that have already been successfully used in different seismic zones by the application of feature selection techniques is proposed. These techniques evaluate every input and propose the best combination of them in terms of information gain. Once these sets have been obtained, artificial neural networks are applied to four Chilean zones (the most seismic country in the world) and to two zones of the Iberian Peninsula (a moderate seismicity area). To make the comparison to other models possible, the prediction problem has been turned into one of classification, thus allowing the application of other machine learning classifiers. Comparisons with original sets of inputs and different classifiers are reported to support the degree of success achieved. Statistical tests have also been applied to confirm that the results are significantly different than those of other classifiers. The main novelty of this work stems from the use of feature selection techniques for improving earthquake prediction methods. So, the information gain of different seismic indicators has been determined. Low ranked or null contribution seismic indicators have been removed, optimizing the method. The optimized prediction method proposed has a high performance. Finally, four Chilean zones and two zones of the Iberian Peninsula have been characterized by means of an information gain analysis obtained from different seismic indicators. The results confirm the methodology proposed as the best features in terms of information gain are the same for both regions.},

keywords = {natural disasters, time series},

pubstate = {published},

tppubtype = {article}

}

@article{MORALESESTEBAN2013121,

title = {Earthquake prediction in seismogenic areas of the Iberian Peninsula based on computational intelligence},

author = {A. Morales-Esteban and F. Martínez-Álvarez and J. Reyes},

url = {http://www.sciencedirect.com/science/article/pii/S0040195113001467},

doi = {10.1016/j.tecto.2013.02.036},

year  = {2013},

date = {2013-01-01},

journal = {Tectonophysics},

volume = {593},

pages = {121-134},

abstract = {A method to predict earthquakes in two of the seismogenic areas of the Iberian Peninsula, based on Artificial Neural Networks (ANNs), is presented in this paper. ANNs have been widely used in many fields but only very few and very recent studies have been conducted on earthquake prediction. Two kinds of predictions are provided in this study: a) the probability of an earthquake, of magnitude equal or larger than a preset threshold magnitude, within the next 7 days, to happen; b) the probability of an earthquake of a limited magnitude interval to happen, during the next 7 days. First, the physical fundamentals related to earthquake occurrence are explained. Second, the mathematical model underlying ANNs is explained and the configuration chosen is justified. Then, the ANNs have been trained in both areas: The Alborán Sea and the Western Azores–Gibraltar fault. Later, the ANNs have been tested in both areas for a period of time immediately subsequent to the training period. Statistical tests are provided showing meaningful results. Finally, ANNs were compared to other well known classifiers showing quantitatively and qualitatively better results. The authors expect that the results obtained will encourage researchers to conduct further research on this topic.},

keywords = {natural disasters},

pubstate = {published},

tppubtype = {article}

}

@article{REYES20131314,

title = {Neural networks to predict earthquakes in Chile},

author = {J. Reyes and A. Morales-Esteban and F. Martínez-Álvarez},

url = {http://www.sciencedirect.com/science/article/pii/S1568494612004656},

doi = {10.1016/j.asoc.2012.10.014},

year  = {2013},

date = {2013-01-01},

journal = {Applied Soft Computing},

volume = {13},

number = {2},

pages = {1314-1328},

abstract = {A new earthquake prediction system is presented in this work. This method, based on the application of artificial neural networks, has been used to predict earthquakes in Chile, one of the countries with larger seismic activity. The input values are related to the b-value, the Bath's law, and the Omori–Utsu's law, parameters that are strongly correlated with seismicity, as shown in solid previous works. Two kind of prediction are provided in this study: The probability that an earthquake of magnitude larger than a threshold value happens, and the probability that an earthquake of a limited magnitude interval might occur, both during the next five days in the areas analyzed. For the four Chile's seismic regions examined, with epicenters placed on meshes with dimensions varying from 0.5° × 0.5° to 1° × 1°, a prototype of neuronal network is presented. The prototypes predict an earthquake every time the probability of an earthquake of magnitude larger than a threshold is sufficiently high. The threshold values have been adjusted with the aim of obtaining as few false positives as possible. The accuracy of the method has been assessed in retrospective experiments by means of statistical tests and compared with well-known machine learning classifiers. The high success rate achieved supports the suitability of applying soft computing in this field and poses new challenges to be addressed.},

keywords = {natural disasters},

pubstate = {published},

tppubtype = {article}

}

@article{IS:GT-2013,

title = {Comparison of metaheuristic strategies for peakbin selection in proteomic mass spectrometry data},

author = {M. García-Torres and R. Arma{~n}anzas and C. Bielza and P. Larra~naga},

url = {https://www.sciencedirect.com/science/article/pii/S0020025510006195},

doi = {10.1016/j.ins.2010.12.013},

year  = {2013},

date = {2013-01-01},

journal = {Information Sciences},

volume = {222},

pages = {229-246},

keywords = {bioinformatics, feature selection},

pubstate = {published},

tppubtype = {article}

}

@article{AA:Cor-2013,

title = {The Gaia astrophysical parameters inference system (Apsis). Pre-launch description},

author = {M. García-Torres and Gaia Collaboration},

url = {https://www.aanda.org/articles/aa/abs/2013/11/aa22344-13/aa22344-13.html},

doi = {10.1051/0004-6361/201322344},

year  = {2013},

date = {2013-01-01},

journal = {Astronomy & Astrophysics},

volume = {559},

number = {A74},

keywords = {astrostatistics},

pubstate = {published},

tppubtype = {article}

}

@article{MORALESESTEBAN2012174,

title = {Probabilistic method to select calculation accelerograms based on uniform seismic hazard acceleration response spectra},

author = {A. Morales-Esteban and J. L. de Justo and F. Martínez-Álvarez and J. M. Azañón},

url = {http://www.sciencedirect.com/science/article/pii/S0267726112001601},

doi = {10.1016/j.soildyn.2012.07.003},

year  = {2012},

date = {2012-01-01},

journal = {Soil Dynamics and Earthquake Engineering},

volume = {43},

number = {3},

pages = {174-185},

abstract = {A dynamic analysis of a structure requires the previous definition of the accelerograms and the structure characteristics. The response of a structure subject to a seismic movement can be determined by two methods: either using the accelerograms recorded near the site, or using visco-elastic response spectra. The first method should only be used for locations where many accelerograms have been recorded, and needs a probabilistic calculation to ascertain the design accelerograms. The use of visco-elastic response spectra is based upon the fact that the response spectrum is the soil movement parameter better related to the structural response and is more adequate to obtain accelerograms in regions where the number of records is insufficient. This is the most commonly used method as the response of structures, in the elastic linear range, can be obtained as the superposition of a few modes of vibration. A probabilistic method for selecting calculation accelerograms is presented in this paper. First, the probabilistic hazard equation is solved. Based on the hazard curves obtained, the uniform seismic hazard acceleration response spectrum (USHARS) is constructed for the location, according to the type of soil and the required hazard level (exposure time and exceedance probability). Then, calculation accelerograms are selected. Based on this methodology, real accelerograms, for a return period of 975 years, have been obtained for San Pedro Cliff (Spain) at the Alhambra in Granada.},

keywords = {natural disasters},

pubstate = {published},

tppubtype = {article}

}

@article{ESA:Rod-2012,

title = {Fast feature selection aimed at high dimensional data via hybrid-sequential-ranked searches},

author = {R. Ruíz and J. Riquelme and J. Aguilar-Ruíz and M. García-Torres},

url = {https://www.sciencedirect.com/science/article/abs/pii/S0957417412005842},

doi = {10.1016/j.eswa.2012.03.061},

year  = {2012},

date = {2012-01-01},

journal = {Expert Systems with Applications},

volume = {39},

number = {12},

pages = {11094-11102},

keywords = {feature selection},

pubstate = {published},

tppubtype = {article}

}

@article{martinez2011,

title = {Clustering Preprocessing to Improve Time Series Forecasting},

author = {F. Martínez-Álvarez},

url = {http://dl.acm.org/citation.cfm?id=1937696.1937702},

year  = {2011},

date = {2011-01-01},

journal = {AI Commun.},

volume = {24},

number = {1},

pages = {97-98},

abstract = {This work proposes a novel general-purpose forecasting algorithm. It first extracts patterns from time series using the information provided by certain clustering techniques, which are applied as a first step of the approach. Moreover, the occurrence of data with especially unexpected values (outliers) is also addressed in this work. To deal with these outliers, a new hybrid methodology has been proposed, by inserting and adapting an existing approach based on the discovery of frequent episodes in sequences in the general scheme of prediction.},

keywords = {time series},

pubstate = {published},

tppubtype = {article}

}

@article{TCBB:Arm-2011,

title = {Peakbin selection in mass spectrometry data using a consensus approach with estimation of distribution algorithms},

author = {R. Arma{~n}anzas and Y. Saeys and I. Inza and M. García-Torres and C. Bielza and Y. {van~de~Peer} and P. Larra~naga},

url = {https://ieeexplore.ieee.org/document/5438984},

doi = {10.1109/TCBB.2010.18},

year  = {2011},

date = {2011-01-01},

journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics},

volume = {8},

number = {3},

pages = {760-774},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{AA:Ore-2011,

title = {A search for new hot subdwarf stars by means of Virtual Observatory tools},

author = {R. Oreiro and C. Rodríguez-López and E. Solano and A. Ulla and R. Ostensen and M. García-Torres},

url = {https://www.aanda.org/articles/aa/abs/2011/06/aa16324-10/aa16324-10.html},

doi = {10.1051/0004-6361/201016324},

year  = {2011},

date = {2011-01-01},

journal = {Astronomy & Astrophysics},

volume = {530},

number = {A2},

keywords = {astrostatistics},

pubstate = {published},

tppubtype = {article}

}

@article{TKDE2011,

title = {Energy Time Series Forecasting Based on Pattern Sequence Similarity},

author = {F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme and J. S. Aguilar-Ruiz},

url = {https://ieeexplore.ieee.org/document/5620917},

doi = {10.1109/TKDE.2010.227},

year  = {2011},

date = {2011-01-01},

journal = {IEEE Transactions on Knowledge and Data Engineering},

volume = {23},

number = {8},

pages = {1230-1243},

abstract = {This paper presents a new approach to forecast the behavior of time series based on similarity of pattern sequences. First, clustering techniques are used with the aim of grouping and labeling the samples from a data set. Thus, the prediction of a data point is provided as follows: first, the pattern sequence prior to the day to be predicted is extracted. Then, this sequence is searched in the historical data and the prediction is calculated by averaging all the samples immediately after the matched sequence. The main novelty is that only the labels associated with each pattern are considered to forecast the future behavior of the time series, avoiding the use of real values of the time series until the last step of the prediction process. Results from several energy time series are reported and the performance of the proposed method is compared to that of recently published techniques showing a remarkable improvement in the prediction.},

keywords = {energy, time series},

pubstate = {published},

tppubtype = {article}

}

@article{BIODM2011,

title = {Biclustering of Gene Expression Data by Correlation-Based Scatter Search},

author = {J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz},

url = {https://link.springer.com/article/10.1186/1756-0381-4-3},

doi = {10.1186/1756-0381-4-3},

year  = {2011},

date = {2011-01-01},

journal = {BioData Mining},

volume = {4},

number = {3},

abstract = {Background: The analysis of data generated by microarray technology is very useful to understand how the genetic information becomes functional gene products. Biclustering algorithms can determine a group of genes which are co-expressed under a set of experimental conditions. Recently, new biclustering methods based on metaheuristics have been proposed. Most of them use the Mean Squared Residue as merit function but interesting and relevant patterns from a biological point of view such as shifting and scaling patterns may not be detected using this measure. However, it is important to discover this type of patterns since commonly the genes can present a similar behavior although their expression levels vary in different ranges or magnitudes. Methods: Scatter Search is an evolutionary technique that is based on the evolution of a small set of solutions which are chosen according to quality and diversity criteria. This paper presents a Scatter Search with the aim of finding biclusters from gene expression data. In this algorithm the proposed fitness function is based on the linear correlation among genes to detect shifting and scaling patterns from genes and an improvement method is included in order to select just positively correlated genes. Results: The proposed algorithm has been tested with three real data sets such as Yeast Cell Cycle dataset, human B-cells lymphoma dataset and Yeast Stress dataset, finding a remarkable number of biclusters with shifting and scaling patterns. In addition, the performance of the proposed method and fitness function are compared to that of CC, OPSM, ISA, BiMax, xMotifs and Samba using Gene the Ontology Database.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{SOFTCO2011,

title = {An Evolutionary Algorithm to Discover Quantitative Association Rules in Multidimensional Time Series},

author = {M. Martínez-Ballesteros and F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme},

url = {https://link.springer.com/article/10.1007/s00500-011-0705-4},

doi = {10.1007/s00500-011-0705-4},

year  = {2011},

date = {2011-01-01},

journal = {Soft Computing},

volume = {15},

number = {10},

pages = {2065-2084},

abstract = {An evolutionary approach for finding existing relationships among several variables of a multidimensional time series is presented in this work. The proposed model to discover these relationships is based on quantitative association rules. This algorithm, called QARGA (Quantitative Association Rules by Genetic Algorithm), uses a particular codification of the individuals that allows solving two basic problems. First, it does not perform a previous attribute discretization and, second, it is not necessary to set which variables belong to the antecedent or consequent. Therefore, it may discover all underlying dependencies among different variables. To evaluate the proposed algorithm three experiments have been carried out. As initial step, several public datasets have been analyzed with the purpose of comparing with other existing evolutionary approaches. Also, the algorithm has been applied to synthetic time series (where the relationships are known) to analyze its potential for discovering rules in time series. Finally, a real-world multidimensional time series composed by several climatological variables has been considered. All the results show a remarkable performance of QARGA.},

keywords = {association rules},

pubstate = {published},

tppubtype = {article}

}

@article{PRL2011,

title = {Discovery of Motifs for Forecast Outlier Occurrence in Time Series},

author = {F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme and J. S. Aguilar-Ruiz},

url = {https://www.sciencedirect.com/science/article/abs/pii/S0167865511001371},

doi = {10.1016/j.patrec.2011.05.002},

year  = {2011},

date = {2011-01-01},

journal = {Pattern Recognition Letters},

number = {32},

pages = {1652–1665},

abstract = {The forecasting process of real-world time series has to deal with especially unexpected values, commonly known as outliers. Outliers in time series can lead to unreliable modeling and poor forecasts. Therefore, the identification of future outlier occurrence is an essential task in time series analysis to reduce the average forecasting error. The main goal of this work is to predict the occurrence of outliers in time series, based on the discovery of motifs. In this sense, motifs will be those pattern sequences preceding certain data marked as anomalous by the proposed metaheuristic in a training set. Once the motifs are discovered, if data to be predicted are preceded by any of them, such data are identified as outliers, and treated separately from the rest of regular data. The forecasting of outlier occurrence has been added as an additional step in an existing time series forecasting algorithm (PSF), which was based on pattern sequence similarities. Robust statistical methods have been used to evaluate the accuracy of the proposed approach regarding the forecasting of both occurrence of outliers and their corresponding values. Finally, the methodology has been tested on six electricity-related time series, in which most of the outliers were properly found and forecasted.},

keywords = {energy, time series},

pubstate = {published},

tppubtype = {article}

}