Publications

@article{REYES2016108,

title = {Comparison between Utsu's and Vere-Jones' aftershocks model by means of a computer simulation based on the acceptance-rejection sampling of von Neumann},

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

url = {http://www.sciencedirect.com/science/article/pii/S0040195116302098},

doi = {10.1016/j.tecto.2016.06.005},

year  = {2016},

date = {2016-01-01},

journal = {Tectonophysics},

volume = {682},

pages = {108-119},

abstract = {In this research, a new algorithm for generating a stochastic earthquake catalog is presented. The algorithm is based on the acceptance–rejection sampling of von Neumann. The result is a computer simulation of earthquakes based on the calculated statistical properties of each zone. Vere-Jones states that an earthquake sequence can be modeled as a series of random events. This is the model used in the proposed simulation. Contrariwise, Utsu indicates that the mainshocks are special geophysical events. The algorithm has been applied to zones of Chile, China, Spain, Japan, and the USA. This allows classifying the zones according to Vere-Jones' or Utsu's model. The results have been quantified relating the mainshock with the largest aftershock within the next 5days (which has been named as Bath event). The results show that some zones fit Utsu's model and others Vere-Jones'. Finally, the fraction of seismic events that satisfy certain properties of magnitude and occurrence is analyzed.},

keywords = {natural disasters},

pubstate = {published},

tppubtype = {article}

}

@article{IS:GT-2016,

title = {High-dimensional feature selection via feature grouping: A Variable neighborhood Search approach},

author = {M. García-Torres and F. Gómez-Vela and B. Melián-Batista and J. Marcos Moreno-Vega},

url = {https://www.sciencedirect.com/science/article/pii/S0020025515005460},

doi = {10.1016/j.ins.2015.07.041},

year  = {2016},

date = {2016-01-01},

journal = {Information Sciences},

volume = {326},

pages = {102-118},

keywords = {feature selection},

pubstate = {published},

tppubtype = {article}

}

@article{AA:Gaia-2016a,

title = {The Gaia Mission},

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

url = {https://www.aanda.org/articles/aa/abs/2016/11/aa29272-16/aa29272-16.html},

doi = {10.1051/0004-6361/201629272},

year  = {2016},

date = {2016-01-01},

journal = {Astronomy & Astrophysics},

volume = {595},

number = {A1},

keywords = {astrostatistics},

pubstate = {published},

tppubtype = {article}

}

@article{AA:Gaia-2016b,

title = {Gaia Data Release 1. Summary of the astrometric, photometric, and survey properties},

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

url = {https://www.aanda.org/articles/aa/abs/2016/11/aa29512-16/aa29512-16.html},

doi = {10.1051/0004-6361/201629512},

year  = {2016},

date = {2016-01-01},

journal = {Astronomy & Astrophysics},

volume = {595},

number = {A2},

keywords = {astrostatistics},

pubstate = {published},

tppubtype = {article}

}

@article{NEUCOM2016,

title = {Obtaining optimal quality measures for 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/S0925231215005688},

doi = {10.1016/j.neucom.2014.10.100},

year  = {2016},

date = {2016-01-01},

journal = {Neurocomputing},

volume = {176},

pages = {36-47},

abstract = {There exist several works in the literature in which fitness functions based on a combination of weighted measures for the discovery of association rules have been proposed. Nevertheless, some differences in the measures used to assess the quality of association rules could be obtained according to the values of the weights of the measures included in the fitness function. Therefore, user׳s decision is very important in order to specify the weights of the measures involved in the optimization process. This paper presents a study of well-known quality measures with regard to the weights of the measures that appear in a fitness function. In particular, the fitness function of an existing evolutionary algorithm called QARGA has been considered with the purpose of suggesting the values that should be assigned to the weights, depending on the set of measures to be optimized. As initial step, several experiments have been carried out from 35 public datasets in order to show how the weights for confidence, support, amplitude and number of attributes measures included in the fitness function have an influence on different quality measures according to several minimum support thresholds. Second, statistical tests have been conducted for evaluating when the differences in measures of the rules obtained by QARGA are significative, and thus, to provide the best weights to be considered depending on the group of measures to be optimized. Finally, the results obtained when using the recommended weights for two real-world applications related to ozone and earthquakes are reported.},

keywords = {association rules},

pubstate = {published},

tppubtype = {article}

}

@article{Energies2016,

title = {A new methodology based on imbalanced classification for predicting outliers in electricity demand time series},

author = {F. J. Duque-Pintor and M. J. Fernández-Gómez and A. Troncoso and F. Martínez-Álvarez},

url = {https://www.mdpi.com/1996-1073/9/9/752},

doi = {10.3390/en9090752},

year  = {2016},

date = {2016-01-01},

journal = {Energies},

volume = {9},

number = {9},

pages = {752},

abstract = {The occurrence of outliers in real-world phenomena is quite usual. If these anomalous data are not properly treated, unreliable models can be generated. Many approaches in the literature are focused on a posteriori detection of outliers. However, a new methodology to a priori predict the occurrence of such data is proposed here. Thus, the main goal of this work is to predict the occurrence of outliers in time series, by using, for the first time, imbalanced classification techniques. In this sense, the problem of forecasting outlying data has been transformed into a binary classification problem, in which the positive class represents the occurrence of outliers. Given that the number of outliers is much lower than the number of common values, the resultant classification problem is imbalanced. To create training and test sets, robust statistical methods have been used to detect outliers in both sets. Once the outliers have been detected, the instances of the dataset are labeled accordingly. Namely, if any of the samples composing the next instance are detected as an outlier, the label is set to one. As a study case, the methodology has been tested on electricity demand time series in the Spanish electricity market, in which most of the outliers were properly forecast.},

keywords = {energy, time series},

pubstate = {published},

tppubtype = {article}

}

@article{SOFTCO2016,

title = {A novel methodology to predict urban traffic congestion with ensemble learning},

author = {G. Asencio-Cortés and E. Florido and A. Troncoso and F. Martínez-Álvarez},

url = {https://link.springer.com/article/10.1007/s00500-016-2288-6},

doi = {10.1007/s00500-016-2288-6},

year  = {2016},

date = {2016-01-01},

journal = {Soft Computing},

volume = {20},

number = {11},

pages = {4205-4216},

abstract = {Urban traffic congestion prediction is a very hot topic due to the environmental and economical impacts that currently implies. In this sense, to be able to predict bottlenecks and to provide alternatives to the circulation of vehicles becomes an essential task for traffic management. A novel methodology, based on ensembles of machine learning algorithms, is proposed to predict traffic congestion in this paper. In particular, a set of seven algorithms of machine learning has been selected to prove their effectiveness in the traffic congestion prediction. Since all the seven algorithms are able to address supervised classification, the methodology has been developed to be used as a binary classification problem. Thus, collected data from sensors located at the Spanish city of Seville are analyzed and models reaching up to 83 % are generated.},

keywords = {time series},

pubstate = {published},

tppubtype = {article}

}

@article{Bokde2016,

title = {R package imputeTestbench to compare imputations methods for univariate time series},

author = {N. Bokde and K. Kulat and M. Beck W and G. Asencio-Cortes},

issn = {2073-4859},

year  = {2016},

date = {2016-01-01},

journal = {R Journal},

abstract = {This paper describes the R package imputeTestbench that provides a testbench for comparing imputation methods for missing data in univariate time series. The imputeTestbench package can be used to simulate the amount and type of missing data in a complete dataset and compare filled data using different imputation methods. The user has the option to simulate missing data by removing observations completely at random or in blocks of different sizes. Several default imputation methods are included with the package, including historical means, linear interpolation, and last observation carried forward. The testbench is not limited to the default functions and users can add or remove additional methods using a simple two-step process. The testbench compares the actual missing and imputed data for each method with different error metrics, including RMSE, MAE, and MAPE. Alternative error metrics can also be supplied by the user. The simplicity of use and significant reduction in time to compare imputation methods for missing data in univariate time series is a significant advantage of the package. This paper provides an overview of the core functions, including a demonstration with examples.},

keywords = {time series},

pubstate = {published},

tppubtype = {article}

}

@article{Asencio-Cortes2016,

title = {A sensitivity study of seismicity indicators in supervised learning to improve earthquake prediction},

author = {G. Asencio-Cortes and F. Martinez-Alvarez and A. Morales-Esteban and J. Reyes},

doi = {10.1016/j.knosys.2016.02.014},

issn = {0950-7051},

year  = {2016},

date = {2016-01-01},

journal = {Knowledge-Based Systems},

number = {101},

pages = {15-30},

abstract = {The use of different seismicity indicators as input for systems to predict earthquakes is becoming increasingly popular. Nevertheless, the values of these indicators have not been systematically obtained so far. This is mainly due to the gap of knowledge existing between seismologists and data mining experts. In this work, the effect of using different parameterizations for inputs in supervised learning algorithms has been thoroughly analyzed by means of a new methodology. Five different analyses have been conducted, mainly related to the shape of training and test sets, to the calculation of the b-value, and to the adjustment of most collected indicators. Outputs sensitivity has been determined when any of these factors is not properly taken into consideration. The methodology has been applied to four Chilean zones. Given its general-purpose design, it can be extended to any location. Similar conclusions have been drawn for all the cases: a proper selection of the sets length and a careful parameterization of certain indicators leads to significantly better results, in terms of prediction accuracy.},

keywords = {natural disasters, time series},

pubstate = {published},

tppubtype = {article}

}

@article{martinez2015,

title = {A Novel Method for Seismogenic Zoning Based on Triclustering: Application to the Iberian Peninsula},

author = {F. Martínez-Álvarez and D. Gutiérrez-Avilés and A. Morales-Esteban and J. Reyes and J. L. Amaro-Mellado and C. Rubio-Escudero},

url = {https://www.mdpi.com/1099-4300/17/7/5000},

doi = {10.3390/e17075000},

year  = {2015},

date = {2015-01-01},

journal = {Entropy},

volume = {17},

number = {7},

pages = {5000-5021},

abstract = {A previous definition of seismogenic zones is required to do a probabilistic seismic hazard analysis for areas of spread and low seismic activity. Traditional zoning methods are based on the availabl seismic catalog and the geological structures. It is admitted that thermal and resistant parameters of the crust provide better criteria for zoning. Nonetheless, the working out of the rheological profiles causes a great uncertainty. This has generated inconsistencies, as different zones have been proposed for the same area. A new method for seismogenic zoning by means of triclustering is proposed in this research. The main advantage is that it is solely based on seismic data. Almost no human decision is made, and therefore, the method is nearly non-biased. To assess its performance, the method has been applied to the Iberian Peninsula, which is characterized by the occurrence of small to moderate magnitude earthquakes. The catalog of the National Geographic Institute of Spain has been used. The output map is checked for validity with the geology. Moreover, a geographic information system has been used for two purposes. First, the obtained zones have been depicted within it. Second, the data have been used to calculate the seismic parameters (b-value, annual rate). Finally, the results have been compared to Kohonen’s self-organizing maps.},

keywords = {natural disasters},

pubstate = {published},

tppubtype = {article}

}

@article{FLORIDO2015112,

title = {Detecting precursory patterns to enhance earthquake prediction in Chile},

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

url = {http://www.sciencedirect.com/science/article/pii/S0098300414002805},

doi = {10.1016/j.cageo.2014.12.002},

year  = {2015},

date = {2015-01-01},

journal = {Computers & Geosciences},

volume = {76},

pages = {112-120},

abstract = {The prediction of earthquakes is a task of utmost difficulty that has been widely addressed by using many different strategies, with no particular good results thus far. Seismic time series of the four most active Chilean zones, the country with largest seismic activity, are analyzed in this study in order to discover precursory patterns for large earthquakes. First, raw data are transformed by removing aftershocks and foreshocks, since the goal is to only predict main shocks. New attributes, based on the well-known b-value, are also generated. Later, these data are labeled, and consequently discretized, by the application of a clustering algorithm, following the suggestions found in recent literature. Earthquakes with magnitude larger than 4.4 are identified in the time series. Finally, the sequence of labels acting as precursory patterns for such earthquakes are searched for within the datasets. Results verging on 70% on average are reported, leading to conclude that the methodology proposed is suitable to be applied in other zones with similar seismicity.},

keywords = {natural disasters},

pubstate = {published},

tppubtype = {article}

}

@article{MORALESESTEBAN201528,

title = {Stability analysis of a slope subject to real accelerograms by finite elements. Application to San Pedro cliff at the Alhambra in Granada},

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

url = {http://www.sciencedirect.com/science/article/pii/S0267726114002255},

doi = {10.1016/j.soildyn.2014.10.023},

year  = {2015},

date = {2015-01-01},

journal = {Soil Dynamics and Earthquake Engineering},

volume = {69},

pages = {28-45},

abstract = {The dynamic stability analysis of slopes is often conducted by the traditional method of slices, using pseudo-static calculations. However, the response of a geotechnical structure subjected to seismic loads can be studied through a dynamic finite element analysis, which can be considered one of the most complete available tools, as information about the stress distribution and the deformations can be obtained. The dynamic analysis of the stability of San Pedro cliff at the Alhambra in Granada is studied in this paper. The results have been compared with pseudo-static calculations worked out with the method of slices. Real accelerograms have been selected for the dynamic tests. Thorough in situ and laboratory tests have been conducted in order to properly characterize the cliff. The soil constitutive model is also explained in this paper. Finally, the influence of the sources of energy dissipation has been studied through the material damping, the integration scheme and the boundary conditions.},

keywords = {natural disasters},

pubstate = {published},

tppubtype = {article}

}

@article{Gutierrez-Aviles2015,

title = {MSL: A Measure to Evaluate Three-dimensional Patterns in Gene Expression Data},

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

url = {https://journals.sagepub.com/doi/10.4137/EBO.S25822},

doi = {10.4137/EBO.S25822},

year  = {2015},

date = {2015-01-01},

journal = {Evolutionary Bioinformatics},

volume = {11},

pages = {121—135},

abstract = {icroarray technology is highly used in biological research environments due to its ability to monitor the RNA concentration levels. The analysis of the data generated 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. Biclustering relaxes the constraints for grouping, allowing genes to be evaluated only under a subset of the conditions. Triclustering appears for the analysis of longitudinal experiments in which the genes are evaluated under certain conditions at several time points. These triclusters provide hidden information in the form of behavior patterns from temporal experiments with microarrays relating subsets of genes, experimental conditions, and time points. We present an evaluation measure for triclusters called Multi Slope Measure, based on the similarity among the angles of the slopes formed by each profile formed by the genes, conditions, and times of the tricluster.},

keywords = {bioinformatics, time series},

pubstate = {published},

tppubtype = {article}

}

@article{NEUCOM2015,

title = {A multi-scale smoothing kernel for measuring time-series similarity},

author = {A. Troncoso and M. Arias and J. C. Riquelme},

url = {https://www.sciencedirect.com/science/article/pii/S0925231215005585},

doi = {10.1016/j.neucom.2014.08.099},

year  = {2015},

date = {2015-01-01},

journal = {Neurocomputing},

volume = {167},

pages = {8-17},

abstract = {In this paper a kernel for time-series data is introduced so that it can be used for any data mining task that relies on a similarity or distance metric. The main idea of our kernel is that it should recognize as highly similar time-series that are essentially the same but may be slightly perturbed from each other: for example, if one series is shifted with respect to the other or if it slightly misaligned. Namely, our kernel tries to focus on the shape of the time-series and ignores small perturbations such as misalignments or shifts. First, a recursive formulation of the kernel directly based on its definition is proposed. Then it is shown how to efficiently compute the kernel using an equivalent matrix-based formulation. To validate the proposed kernel three experiments have been carried out. As an initial step, several synthetic datasets have been generated from UCR time-series repository and the KDD challenge of 2007 with the purpose of validating the kernel-derived distance over shifted time-series. Also, the kernel has been applied to the original UCR time-series to analyze its potential in time-series classification in conjunction with Support Vector Machines. Finally, two real-world applications related to ozone concentration in atmosphere and electricity demand have been considered.},

keywords = {time series},

pubstate = {published},

tppubtype = {article}

}

@article{ICAE2015,

title = {Mining Enhancing the scalability of a genetic algorithm to discover quantitative association rules in large-scale datasets},

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

url = {https://content.iospress.com/articles/integrated-computer-aided-engineering/ica00479},

doi = {10.3233/ICA-140479},

year  = {2015},

date = {2015-01-01},

journal = {Integrated Computer-Aided Engineering},

volume = {22},

number = {1},

pages = {21-39},

abstract = {Association rule mining is a well-known methodology to discover significant and apparently hidden relations among attributes in a subspace of instances from datasets. Genetic algorithms have been extensively used to find interesting association rules. However, the rule-matching task of such techniques usually requires high computational and memory requirements. The use of efficient computational techniques has become a task of the utmost importance due to the high volume of generated data nowadays. Hence, this paper aims at improving the scalability of quantitative association rule mining techniques based on genetic algorithms to handle large-scale datasets without quality loss in the results obtained. For this purpose, a new representation of the individuals, new genetic operators and a windowing-based learning scheme are proposed to achieve successfully such challenging task. Specifically, the proposed techniques are integrated into the multi-objective evolutionary algorithm named QARGA-M to assess their performances. Both the standard version and the enhanced one of QARGA-M have been tested in several datasets that present different number of attributes and instances. Furthermore, the proposed methodologies have been integrated into other existing techniques based in genetic algorithms to discover quantitative association rules. The comparative analysis performed shows significant improvements of QARGA-M and other existing genetic algorithms in terms of computational costs without losing quality in the results when the proposed techniques are applied.},

keywords = {association rules},

pubstate = {published},

tppubtype = {article}

}

@article{RENE2015,

title = {Local models regression trees for very short-term wind speed predictions},

author = {A. Troncoso and S. Salcedo-Sanz and C. Casanova-Mateo and J. C. Riquelme and L. Prieto},

url = {https://www.sciencedirect.com/science/article/pii/S0960148115002530},

doi = {10.1016/j.renene.2015.03.071},

year  = {2015},

date = {2015-01-01},

journal = {Renewable Energy},

volume = {81},

pages = {589-598},

abstract = {This paper evaluates the performance of different types of Regression Trees (RTs) in a real problem of very short-term wind speed prediction from measuring data in wind farms. RT is a solidly established methodology that, contrary to other soft-computing approaches, has been under-explored in problems of wind speed prediction in wind farms. In this paper we comparatively evaluate eight different types of RTs algorithms, and we show that they are able obtain excellent results in real problems of very short-term wind speed prediction, improving existing classical and soft-computing approaches such as multi-linear regression approaches, different types of neural networks and support vector regression algorithms in this problem. We also show that RTs have a very small computation time, that allows the retraining of the algorithms whenever new wind speed data are collected from the measuring towers.},

keywords = {energy, time series},

pubstate = {published},

tppubtype = {article}

}

@article{NEUCOM2015b,

title = {A comparison of machine learning regression techniques for LiDAR-derived estimation of forest variables},

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

url = {https://www.sciencedirect.com/science/article/pii/S0925231215005524},

doi = {10.1016/j.neucom.2014.09.091},

year  = {2015},

date = {2015-01-01},

journal = {Neurocomputing},

volume = {167},

pages = {24-31},

abstract = {Light Detection and Ranging (LiDAR) is a remote sensor able to extract three-dimensional information. Environmental models in forest areas have been benefited by the use of LiDAR-derived information in the last years. A multiple linear regression (MLR) with previous stepwise feature selection is the most common method in the literature to develop those models. MLR defines the relation between the set of field measurements and the statistics extracted from a LiDAR flight. Machine learning has emerged as a suitable tool to improve classic stepwise MLR results on LiDAR. Unfortunately, few studies have been proposed to compare the quality of the multiple machine learning approaches. This paper presents a comparison between the classic MLR-based methodology and regression techniques in machine learning (neural networks, support vector machines, nearest neighbour, ensembles such as random forests) with special emphasis on regression trees. The selected techniques are applied to real LiDAR data from two areas in the province of Lugo (Galizia, Spain). The results confirm that classic MLR is outperformed by machine learning techniques and concretely, our experiments suggest that Support Vector Regression with Gaussian kernels statistically outperforms the rest of the techniques.},

keywords = {time series},

pubstate = {published},

tppubtype = {article}

}

@article{ASC2015,

title = {Scatter Search-based identification of local patterns with positive and negative correlations in gene expression data},

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

url = {https://www.sciencedirect.com/science/article/pii/S1568494615003683},

doi = {10.1016/j.asoc.2015.06.019},

year  = {2015},

date = {2015-01-01},

journal = {Applied Soft Computing},

volume = {35},

pages = {637-651},

abstract = {This paper presents a scatter search approach based on linear correlations among genes to find biclusters, which include both shifting and scaling patterns and negatively correlated patterns contrarily to most of correlation-based algorithms published in the literature. The methodology established here for comparison is based on a priori biological information stored in the well-known repository Gene Ontology (GO). In particular, the three existing categories in GO, Biological Process, Cellular Components and Molecular Function, have been used. The performance of the proposed algorithm has been compared to other benchmark biclustering algorithms, specifically a group of classical biclustering algorithms and two algorithms that use correlation-based merit functions. The proposed algorithm outperforms the benchmark algorithms and finds patterns based on negative correlations. Although these patterns contain important relationship among genes, they are not found by most of biclustering algorithms. The experimental study also shows the importance of the size in a bicluster in addition to the value of its correlation. In particular, the size of a bicluster has an influence over its enrichment in a GO term.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{Energies2015,

title = {A Survey on Data Mining Techniques Applied To Electricity-Related Time Series Forecasting},

author = {F. Martínez-Álvarez and A. Troncoso and G. Asencio-Cortés and J. C. Riquelme},

url = {https://www.mdpi.com/1996-1073/8/11/12361},

doi = {10.3390/en81112361},

year  = {2015},

date = {2015-01-01},

journal = {Energies},

volume = {8},

number = {11},

pages = {13162-13193},

abstract = {Data mining has become an essential tool during the last decade to analyze large sets of data. The variety of techniques it includes and the successful results obtained in many application fields, make this family of approaches powerful and widely used. In particular, this work explores the application of these techniques to time series forecasting. Although classical statistical-based methods provides reasonably good results, the result of the application of data mining outperforms those of classical ones. Hence, this work faces two main challenges: (i) to provide a compact mathematical formulation of the mainly used techniques; (ii) to review the latest works of time series forecasting and, as case study, those related to electricity price and demand markets.},

keywords = {energy, time series},

pubstate = {published},

tppubtype = {article}

}

@article{Marquez-Chamorro2015,

title = {Soft computing methods for the prediction of protein tertiary structures: A survey},

author = {A. E. Marquez-Chamorro and G. Asencio-Cortes and C. E. Santiesteban-Toca and J. S. Aguilar-Ruiz},

doi = {10.1016/j.asoc.2015.06.024},

issn = {1568-4946},

year  = {2015},

date = {2015-01-01},

journal = {Applied Soft Computing},

number = {35},

pages = {398-410},

abstract = {The problem of protein structure prediction (PSP) represents one of the most important challenges in computational biology. Determining the three dimensional structure of proteins is necessary to understand their functions at molecular level. The most representative soft computing approaches for solving the protein tertiary structure prediction problem are summarized in this paper. These approaches have been categorized following the type of methodology. A total of 90 relevant works published in last 15 years in the field of protein structure prediction have been reported, including the best competitors in last CASP editions. However, despite large research effort in last decades, a considerable scope for further improvement still remains in this area.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{CMPB2015,

title = {Integrating biological knowledge based on functional annotations for biclustering of gene expression data},

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

url = {https://www.sciencedirect.com/science/article/pii/S0169260715000450},

doi = {10.1016/j.cmpb.2015.02.010},

year  = {2015},

date = {2015-00-00},

journal = {Computers Methods and Programs in Biomedicine},

volume = {119},

number = {3},

pages = {163-180},

abstract = {Gene expression data analysis is based on the assumption that co-expressed genes imply co-regulated genes. This assumption is being reformulated because the co-expression of a group of genes may be the result of an independent activation with respect to the same experimental condition and not due to the same regulatory regime. For this reason, traditional techniques are recently being improved with the use of prior biological knowledge from open-access repositories together with gene expression data. Biclustering is an unsupervised machine learning technique that searches patterns in gene expression data matrices. A scatter search-based biclustering algorithm that integrates biological information is proposed in this paper. In addition to the gene expression data matrix, the input of the algorithm is only a direct annotation file that relates each gene to a set of terms from a biological repository where genes are annotated. Two different biological measures, FracGO and SimNTO, are proposed to integrate this information by means of its addition to-be-optimized fitness function in the scatter search scheme. The measure FracGO is based on the biological enrichment and SimNTO is based on the overlapping among GO annotations of pairs of genes. Experimental results evaluate the proposed algorithm for two datasets and show the algorithm performs better when biological knowledge is integrated. Moreover, the analysis and comparison between the two different biological measures is presented and it is concluded that the differences depend on both the data source and how the annotation file has been built in the case GO is used. It is also shown that the proposed algorithm obtains a greater number of enriched biclusters than other classical biclustering algorithms typically used as benchmark and an analysis of the overlapping among biclusters reveals that the biclusters obtained present a low overlapping. The proposed methodology is a general-purpose algorithm which allows the integration of biological information from several sources and can be extended to other biclustering algorithms based on the optimization of a merit function.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{KNOSYS2015,

title = {A factorization approach to evaluate open-response assignments in MOOCs using preference learning on peer assessments},

author = {O. Luaces and J. Díez and A. Alonso-Betanzos and A. Troncoso and A. Bahamonde},

url = {https://www.sciencedirect.com/science/article/abs/pii/S0950705115002051},

doi = {10.1016/j.knosys.2015.05.019},

year  = {2015},

date = {2015-00-00},

journal = {Knowledge-Based Systems},

volume = {85},

pages = {322-328},

abstract = {Evaluating open-response assignments in Massive Open Online Courses is a difficult task because of the huge number of students involved. Peer grading is an effective method to address this problem. There are two basic approaches in the literature: cardinal and ordinal. The first case uses grades assigned by student-graders to a set of assignments of other colleagues. In the ordinal approach, the raw materials used by grading systems are the relative orders that graders appreciate in the assignments that they evaluate. In this paper we present a factorization method that seeks a trade-off between cardinal and ordinal approaches. The algorithm learns from preference judgments to avoid the subjectivity of the numeric grades. But in addition to preferences expressed by student-graders, we include other preferences: those induced from assignments with significantly different average grades. The paper includes a report of the results obtained using this approach in a real world dataset collected in 3 Universities of Spain, A Coruña, Pablo de Olavide at Sevilla, and Oviedo at Gijón. Additionally, we studied the sensitivity of the method with respect to the number of assignments graded by each student. Our method achieves similar or better scores than staff instructors when we measure the discrepancies with other instructor’s grades.},

keywords = {big data},

pubstate = {published},

tppubtype = {article}

}

@article{MORALESESTEBAN2014132,

title = {A fast partitioning algorithm using adaptive Mahalanobis clustering with application to seismic zoning},

author = {A. Morales-Esteban and F. Martínez-Álvarez and S. Scitovski and R. Scitovski},

url = {http://www.sciencedirect.com/science/article/pii/S0098300414002143},

doi = {10.1016/j.cageo.2014.09.003},

year  = {2014},

date = {2014-01-01},

journal = {Computers & Geosciences},

volume = {73},

pages = {132-141},

abstract = {In this paper we construct an efficient adaptive Mahalanobis k-means algorithm. In addition, we propose a new efficient algorithm to search for a globally optimal partition obtained by using the adoptive Mahalanobis distance-like function. The algorithm is a generalization of the previously proposed incremental algorithm (Scitovski and Scitovski, 2013). It successively finds optimal partitions with clusters. Therefore, it can also be used for the estimation of the most appropriate number of clusters in a partition by using various validity indexes. The algorithm has been applied to the seismic catalogues of Croatia and the Iberian Peninsula. Both regions are characterized by a moderate seismic activity. One of the main advantages of the algorithm is its ability to discover not only circular but also elliptical shapes, whose geometry fits the faults better. Three seismogenic zonings are proposed for Croatia and two for the Iberian Peninsula and adjacent areas, according to the clusters discovered by the algorithm.},

keywords = {natural disasters},

pubstate = {published},

tppubtype = {article}

}

@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}

}