@article{Energies2019b,

title = {A Comparative Study of Time Series Forecasting Methods for Short Term Electric Energy Consumption Prediction in Smart Buildings},

author = {F. Divina and M. García-Torres and F. Goméz-Vela and J.L. Vázquez Noguera},

url = {https://www.mdpi.com/1996-1073/12/10/1934},

doi = {https://doi.org/10.3390/en12101934},

year  = {2019},

date = {2019-01-01},

journal = {Applied Sciences},

volume = {12},

number = {10},

pages = {1934},

abstract = {Smart buildings are equipped with sensors that allow monitoring a range of building systems including heating and air conditioning, lighting and the general electric energy consumption. Thees data can then be stored and analyzed. The ability to use historical data regarding electric energy consumption could allow improving the energy efficiency of such buildings, as well as help to spot problems related to wasting of energy. This problem is even more important when considering that buildings are some of the largest consumers of energy. In this paper, we are interested in forecasting the energy consumption of smart buildings, and, to this aim, we propose a comparative study of different forecasting strategies that can be used to this aim. To do this, we used the data regarding the electric consumption registered by thirteen buildings located in a university campus in the south of Spain. The empirical comparison of the selected methods on the different data showed that some methods are more suitable than others for this kind of problem. In particular, we show that strategies based on Machine Learning approaches seem to be more suitable for this task.},

keywords = {},

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 = {},

pubstate = {published},

tppubtype = {article}

}

@article{Genes2019,

title = {Computational Inference of Gene Co-Expression Networks for the identification of Lung Carcinoma Biomarkers: An Ensemble Approach},

author = {F. M Delgado-Chaves and F. Gómez-Vela and M. García-Torres and F. Divina and J.L. Vázquez Noguera},

url = {https://www.mdpi.com/2073-4425/10/12/962},

doi = {https://doi.org/10.3390/genes10120962},

year  = {2019},

date = {2019-01-01},

journal = {Genes},

volume = {10},

number = {12},

pages = {962},

abstract = {Gene Networks (GN), have emerged as an useful tool in recent years for the analysis of different diseases in the field of biomedicine. In particular, GNs have been widely applied for the study and analysis of different types of cancer. In this context, Lung carcinoma is among the most common cancer types and its short life expectancy is partly due to late diagnosis. For this reason, lung cancer biomarkers that can be easily measured are highly demanded in biomedical research. In this work, we present an application of gene co-expression networks in the modelling of lung cancer gene regulatory networks, which ultimately served to the discovery of new biomarkers. For this, a robust GN inference was performed from microarray data concomitantly using three different co-expression measures. Results identified a major cluster of genes involved in SRP-dependent co-translational protein target to membrane, as well as a set of 28 genes that were exclusively found in networks generated from cancer samples. Amongst potential biomarkers, genes NCKAP1L and DMD are highlighted due to their implications in a considerable portion of lung and bronchus primary carcinomas. These findings demonstrate the potential of GN reconstruction in the rational prediction of biomarkers.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Energy2018,

title = {Stacking ensemble learning for short-term electricity consumption forecasting},

author = {F. Divina and A. Gilson and F. Goméz-Vela and M. García-Torres and J. F. Torres},

url = {https://www.mdpi.com/1996-1073/11/4/949},

doi = {https://doi.org/10.3390/en11040949},

year  = {2018},

date = {2018-01-01},

journal = {Energies},

volume = {11},

number = {4},

pages = {949},

abstract = {The ability to predict short-term electric energy demand would provide several benefits, both at the economic and environmental level. For example, it would allow for an efficient use of resources in order to face the actual demand, reducing the costs associated to the production as well as the emission of CO 2 . To this aim, in this paper we propose a strategy based on ensemble learning in order to tackle the short-term load forecasting problem. In particular, our approach is based on a stacking ensemble learning scheme, where the predictions produced by three base learning methods are used by a top level method in order to produce final predictions. We tested the proposed scheme on a dataset reporting the energy consumption in Spain over more than nine years. The obtained experimental results show that an approach for short-term electricity consumption forecasting based on ensemble learning can help in combining predictions produced by weaker learning methods in order to obtain superior results. In particular, the system produces a lower error with respect to the existing state-of-the art techniques used on the same dataset. More importantly, this case study has shown that using an ensemble scheme can achieve very accurate predictions, and thus that it is a suitable approach for addressing the short-term load forecasting problem.},

keywords = {},

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 = {},

pubstate = {published},

tppubtype = {article}

}