Publications

@article{JIMENEZ-NAVARRO24,

title = {Explaining deep learning models for ozone pollution prediction via embedded feature selection},

author = {M. J. Jiménez-Navarro and M. Martínez-Ballesteros and F. Martínez-Álvarez and G. Asencio-Cortés},

url = {https://www.sciencedirect.com/science/article/pii/S1568494624002783},

doi = {https://doi.org/10.1016/j.asoc.2024.111504},

year  = {2024},

date = {2024-04-04},

journal = {Applied Soft Computing},

volume = {157},

pages = {111504},

abstract = {Ambient air pollution is a pervasive global issue that poses significant health risks. Among pollutants, ozone (O3) is responsible for an estimated 1 to 1.2 million premature deaths yearly. Furthermore, O3 adversely affects climate warming, crop productivity, and more. Its formation occurs when nitrogen oxides and volatile organic compounds react with short-wavelength solar radiation. Consequently, urban areas with high traffic volume and elevated temperatures are particularly prone to elevated O3 levels, which pose a significant health risk to their inhabitants. In response to this problem, many countries have developed web and mobile applications that provide real-time air pollution information using sensor data. However, while these applications offer valuable insight into current pollution levels, predicting future pollutant behavior is crucial for effective planning and mitigation strategies. Therefore, our main objectives are to develop accurate and efficient prediction models and identify the key factors that influence O3 levels. We adopt a time series forecasting approach to address these objectives, which allows us to analyze and predict O3 future behavior. Additionally, we tackle the feature selection problem to identify the most relevant features and periods that contribute to prediction accuracy by introducing a novel method called the Time Selection Layer in Deep Learning models, which significantly improves model performance, reduces complexity, and enhances interpretability. Our study focuses on data collected from five representative areas in Seville, Cordova, and Jaen provinces in Spain, using multiple sensors to capture comprehensive pollution data. We compare the performance of three models: Lasso, Decision Tree, and Deep Learning with and without incorporating the Time Selection Layer. Our results demonstrate that including the Time Selection Layer significantly enhances the effectiveness and interpretability of Deep Learning models, achieving an average effectiveness improvement of 9% across all monitored areas.},

keywords = {deep learning, feature selection, time series, XAI},

pubstate = {published},

tppubtype = {article}

}

@article{garcia2024feature,

title = {Feature selection applied to QoS/QoE modeling on video and web-based mobile data services: An ordinal approach},

author = {M. García-Torres and D. P. Pinto-Roa and C. Núñez-Castillo and B. Quiñonez and G. Vázquez and M. Allegretti and M. E. García-Diaz},

url = {https://www.sciencedirect.com/science/article/pii/S0140366424000410},

doi = {10.1016/j.comcom.2024.02.004},

year  = {2024},

date = {2024-01-01},

journal = {Computer Communications},

publisher = {Elsevier},

abstract = {Nowadays, mobile service providers perceive the user experience as a reliable indicator of the quality associated to a service. Given a set of Quality of Service (QoS) factors, the aim is to predict the Quality of Experience (QoE), measured in terms of the Mean Opinion Score (MOS). Although this problem is receiving much attention, there are still some challenges that require more research in order to find effective solutions for meeting user’s expectation in terms of service quality. A core challenge in this topic refers to the analysis of the contribution of each factor to the QoS/QoE Model. In this work, we study the mapping between QoS and QoE on video and web-based services using a machine learning approach. For such purpose, we design a lab-testing methodology to emulate different cellular transmission network scenarios. Then, we address the problem of inducing a predictive model and identifying relevant QoS factors. Results suggest that bandwidth is a key factor when analyzing user’s perception of service quality.},

keywords = {feature selection},

pubstate = {published},

tppubtype = {article}

}

@article{garcia2023evolutionary,

title = {Evolutionary feature selection on high dimensional data using a search space reduction approach},

author = {M. García-Torres and R. Ruiz and F. Divina},

url = {https://www.sciencedirect.com/science/article/pii/S0952197622005462},

doi = {10.1016/j.engappai.2022.105556},

year  = {2023},

date = {2023-01-01},

journal = {Engineering Applications of Artificial Intelligence},

volume = {117},

pages = {105556},

publisher = {Elsevier},

abstract = {Feature selection is becoming more and more a challenging task due to the increase of the dimensionality of the data. The complexity of the interactions among features and the size of the search space make it unfeasible to find the optimal subset of features. In order to reduce the search space, feature grouping has arisen as an approach that allows to cluster feature according to the shared information about the class. On the other hand, metaheuristic algorithms have proven to achieve sub-optimal solutions within a reasonable time. In this work we propose a Scatter Search (SS) strategy that uses feature grouping to generate an initial population comprised of diverse and high quality solutions. Solutions are then evolved by applying random mechanisms in combination with the feature group structure, with the objective of maintaining during the search a population of good and, at the same time, as diverse as possible solutions. Not only does the proposed strategy provide the best subset of features found but it also reduces the redundancy structure of the data. We test the strategy on high dimensional data from biomedical and text-mining domains. The results are compared with those obtained by other adaptations of SS and other popular strategies. Results show that the proposed strategy can find, on average, the smallest subsets of features without degrading the performance of the classifier.},

keywords = {big data, feature selection},

pubstate = {published},

tppubtype = {article}

}

@article{Chacon2023,

title = {FS-Studio: An extensive and efficient feature selection experimentation tool for Weka Explorer},

author = {A. M. Chacón-Maldonado and G. Asencio-Cortés and F. Martínez-Álvarez and A. Troncoso},

url = {https://www.sciencedirect.com/science/article/pii/S2352711023000973},

doi = {https://doi.org/10.1016/j.softx.2023.101401},

year  = {2023},

date = {2023-01-01},

journal = {SoftwareX},

volume = {23},

pages = {101401},

keywords = {feature selection},

pubstate = {published},

tppubtype = {article}

}

@article{sosa2023feature,

title = {Feature selection: A perspective on inter-attribute cooperation},

author = {G. Sosa-Cabrera and S. Gómez-Guerrero and M. García-Torres and C. E. Schaerer},

url = {https://link.springer.com/article/10.1007/s41060-023-00439-z},

doi = {10.1007/s41060-023-00439-z},

year  = {2023},

date = {2023-01-01},

journal = {International Journal of Data Science and Analytics},

pages = {1--13},

publisher = {Springer},

abstract = {High-dimensional datasets depict a challenge for learning tasks in data mining and machine learning. Feature selection is an effective technique in dealing with dimensionality reduction. It is often an essential data processing step prior to applying a learning algorithm. Over the decades, filter feature selection methods have evolved from simple univariate relevance ranking algorithms to more sophisticated relevance-redundancy trade-offs and to multivariate dependencies-based approaches in recent years. This tendency to capture multivariate dependence aims at obtaining unique information about the class from the intercooperation among features. This paper presents a comprehensive survey of the state-of-the-art work on filter feature selection methods assisted by feature intercooperation, and summarizes the contributions of different approaches found in the literature. Furthermore, current issues and challenges are introduced to identify promising future research and development.},

keywords = {feature selection},

pubstate = {published},

tppubtype = {article}

}

@article{losada2022,

title = {Automatic Eligibility of Sellers in an Online Marketplace: A Case Study of Amazon Algorithm},

author = {A. Gómez-Losada and G. Asencio-Cortés and N. Duch-Brown},

url = {https://www.mdpi.com/2078-2489/13/2/44},

doi = {10.3390/info13020044},

year  = {2022},

date = {2022-01-01},

journal = {Information},

volume = {13},

number = {44},

pages = {1--16},

abstract = {Purchase processes on Amazon Marketplace begin at the Buy Box, which represents the buy click process through which numerous sellers compete. This study aimed to estimate empirically the relevant seller characteristics that Amazon could consider featuring in the Buy Box. To that end, 22 product categories from Italy’s Amazon web page were studied over a ten-month period, and the sellers were analyzed through their products featured in the Buy Box. Two different experiments were proposed and the results were analyzed using four classification algorithms (a neural network, random forest, support vector machine, and C5.0 decision trees) and a rule-based classification. The first experiment aimed to characterize sellers unspecifically by predicting their change at the Buy Box. The second one aimed to predict which seller would be featured in it. Both experiments revealed that the customer experience and the dynamics of the sellers’ prices were important features of the Buy Box. Additionally, we proposed a set of default features that Amazon could consider when no information about sellers was available. We also proposed the possible existence of a relationship or composition among important features that could be used for sellers to be featured in the Buy Box.},

keywords = {feature selection, time series},

pubstate = {published},

tppubtype = {article}

}

@article{gomez2022measuring,

title = {Measuring Interactions in Categorical Datasets Using Multivariate Symmetrical Uncertainty},

author = {S. Gómez-Guerrero and I. Ortiz and G. and Sosa-Cabrera and M. García-Torres and C.E. Schaerer},

url = {https://www.mdpi.com/1099-4300/24/1/64},

doi = {10.3390/e24010064},

year  = {2022},

date = {2022-01-01},

journal = {Entropy},

volume = {24},

number = {1},

pages = {64},

publisher = {Multidisciplinary Digital Publishing Institute},

abstract = {Interaction between variables is often found in statistical models, and it is usually expressed in the model as an additional term when the variables are numeric. However, when the variables are categorical (also known as nominal or qualitative) or mixed numerical-categorical, defining, detecting, and measuring interactions is not a simple task. In this work, based on an entropy-based correlation measure for n nominal variables (named as Multivariate Symmetrical Uncertainty (MSU)), we propose a formal and broader definition for the interaction of the variables. Two series of experiments are presented. In the first series, we observe that datasets where some record types or combinations of categories are absent, forming patterns of records, which often display interactions among their attributes. In the second series, the interaction/non-interaction behavior of a regression model (entirely built on continuous variables) gets successfully replicated under a discretized version of the dataset. It is shown that there is an interaction-wise correspondence between the continuous and the discretized versions of the dataset. Hence, we demonstrate that the proposed definition of interaction enabled by the MSU is a valuable tool for detecting and measuring interactions within linear and non-linear models.},

keywords = {feature selection},

pubstate = {published},

tppubtype = {article}

}

@article{Mortazavi21,

title = {Wrapper-based feature selection using regression trees to predict intrinsic viscosity of polymer},

author = {R. Mortazavi and S. Mortazavi and A. Troncoso},

url = {https://link.springer.com/article/10.1007/s00366-020-01226-1},

doi = {10.1007/s00366-020-01226-1},

year  = {2021},

date = {2021-01-01},

journal = {Engineering with Computers},

abstract = {This paper introduces different types of regression trees for viscosity property forecasting in polymer solutions. Although regression trees have been extensively used in other fields, they do not have been explored to predict the viscosity. One key issue in the context of materials science is to determine a priori which characteristics must be included to describe the prediction model due to a large number of molecular descriptors is obtained. To deal with this, we propose a wrapper method to select the features based on regression trees. Thus, we use regression trees to evaluate different subsets of attributes and build a model from the subset of features that achieved the minimum error. In particular, the performance of eight regression tree algorithms, including both linear and non-linear models, is evaluated and compared to other forecasting approaches using a dataset composed of 64 polymers and 2962 molecular descriptors. The results show that regression trees with nearest neighbors based local models in leaves predict with high accuracy. Moreover, results have been compared to other forecasting approaches such as multivariate linear regression, neural networks and support vector machines showing remarkable improvements in terms of accuracy.},

keywords = {feature selection},

pubstate = {published},

tppubtype = {article}

}

@article{grillo2021adjacent,

title = {Adjacent Inputs With Different Labels and Hardness in Supervised Learning},

author = {S.A. Grillo and J.C. Román and J.D. Mello-Román and J.L. Vázquez Noguera and M. García-Torres and F. Divina and P.E. Sotomayor},

doi = {10.1109/ACCESS.2021.3131150 volume=9},

year  = {2021},

date = {2021-01-01},

journal = {IEEE Access},

pages = {162487--162498},

publisher = {IEEE pubstate = published},

keywords = {feature selection, pattern recognition},

pubstate = {published},

tppubtype = {article}

}

@article{JDE_Feria,

title = {Applying wrapper-based variable selection techniques to predict MFIs profitability: evidence from Peru},

author = {F. Pietrapiana and J. M. Feria-Dominguez and A. Troncoso},

doi = {10.1080/19439342.2021.1884119},

year  = {2021},

date = {2021-01-01},

journal = {Journal of Development Effectiveness},

abstract = {In this paper, we analyse the main factors explaining the profitability (ROA) of Microfinance Institutions (MFIs) in Peru from 2011 to 2107. We apply three wrapper techniques to a sample of 168 Peruvians MFIs and 69 attributes obtained from MIX Market database. After running the algorithms M5ʹ, k nearest neighbours (KNN) and Random Forest, we find that the M5ʹ algorithm provides the best fit for predicting ROA. Particularly, the key variable of the regression tree is the percentage of expenses over assets and, depending on its value, it is followed by net income after taxes and before donations, or profit margins.},

keywords = {feature selection},

pubstate = {published},

tppubtype = {article}

}

@article{IS-2019,

title = {A multivariate approach to the symmetrical uncertainty measure: Application to feature selection problem},

author = {G. Sosa-Cabrera and M. García-Torres and S. Gómez-Guerrero and C.E. Schaerer and F. Divina},

url = {https://www.sciencedirect.com/science/article/pii/S0020025519303603},

doi = {https://doi.org/10.1016/j.ins.2019.04.046},

year  = {2019},

date = {2019-01-01},

journal = {Information Sciences},

volume = {494},

pages = {1--20},

abstract = {In this work we propose an extension of the Symmetrical Uncertainty (SU) measure in order to address the multivariate case, simultaneously acquiring the capability to detect possible correlations and interactions among features. This generalization, denoted Multivariate Symmetrical Uncertainty (MSU), is based on the concepts of Total Correlation (TC) and Mutual Information (MI) extended to the multivariate case. The generalized measure accounts for the total amount of dependency within a set of variables as a single monolithic quantity. Multivariate measures are usually biased due to several factors. To overcome this problem, a mathematical expression is proposed, based on the cardinality of all features, which can be used to calculate the number of samples needed to estimate the MSU without bias at a pre-specified significance level. Theoretical and experimental results on synthetic data show that the proposed sample size expression properly controls the bias. In addition, when the MSU is applied to feature selection on synthetic and real-world data, it has the advantage of adequately capturing linear and nonlinear correlations and interactions, and it can therefore be used as a new feature subset evaluation method.},

keywords = {feature selection},

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{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{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{EJOR:GL-2006,

title = {Solving the Feature Selection Problem by a Parallel Scatter Search},

author = {F.~C. García-López and M. García-Torres and B. Melián-Batista and J.~A. Moreno Pérez and J.~M. Moreno-Vega},

url = {https://www.sciencedirect.com/science/article/abs/pii/S0377221704005491},

doi = {10.1016/j.ejor.2004.08.010},

year  = {2006},

date = {2006-01-01},

journal = {European Journal of Operations Research},

volume = {169},

number = {2},

pages = {477-489},

keywords = {feature selection},

pubstate = {published},

tppubtype = {article}

}