Miguel García Torres is an associate professor in the Escuela Politécnica Superior of the Universidad Pablo de Olavide. He received the BS degree in physics and the PhD degree in computer science from the Universidad de La Laguna, Tenerife, Spain, in 2001 and 2007, respectively. After obtaining the doctorate he held a postoc position in the Laboratory for Space Astrophysics and Theoretical Physics at the National institute of Aerospace Technology (INTA). There, he joined in the Gaia mission from the European Space Agency (ESA) and started to participate in the Gaia Data Processing and Analysis Consortium (DPAC) as a member of “Astrophysical Parameters”, Coordination Unit (CU8). He has been involved in the “Object Clustering Analysis” (OCA) Development Unit since then. His research areas of interests include machine learning, metaheuristics, big data, time series forecasting, bioinformatics and astrostatistics.
Publications
2021 |
V.E. Castillo Benítez and I. Castro Matto and J.C. Mello Román and J.L. Vázquez Noguera and M. García-Torres and J. Ayala and D.P. Pinto-Roa and P.E. Gardel-Sotomayor and J. Facon and S.A. Grillo Dataset from fundus images for the study of diabetic retinopathy Journal Article In: Data in Brief, vol. 36, pp. 107068, 2021. @article{benitez2021dataset, This article presents a database containing 757 color fundus images acquired at the Department of Ophthalmology of the Hospital de Clínicas, Facultad de Ciencias Médicas (FCM), Universidad Nacional de Asunción (UNA), Paraguay. Firstly, the retinal images were acquired with a clinical procedure presented in this paper. The acquisition of the retinographies was made through the Visucam 500 camera of the Zeiss brand. Next, two expert ophthalmologists have classified the dataset. These data can help physicians and researchers in the detection of cases of Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR), in their different stages. The dataset generated will be useful for ophthalmologists and researchers to work on automatic detection algorithms for Diabetic Retinopathy (DR). |
H. Ho Shin and C. Sauer Ayala and P. Pérez-Estigarribia and S.A. Grillo and L. Segovia-Cabrera and M. García-Torres and C. Gaona and S. Irala and M.E. Pedrozo and G. Sequera and J.L. Vázquez Noguera and E. De Los Santos A Mathematical Model for COVID-19 with Variable Transmissibility and Hospitalizations: A Case Study in Paraguay Journal Article In: Applied Sciences, vol. 11, no. 20, pp. 9726, 2021. @article{shin2021mathematical, Forecasting the dynamics of the number of cases with coronavirus disease 2019 (COVID-19) in a given population is a challenging task due to behavioural changes which occur over short periods. Planning of hospital resources and containment measures in the near term require a scenario analysis and the use of predictive models to gain insight into possible outcomes for each scenario. In this paper, we present the SEIR-H epidemiological model for the spread dynamics in a given population and the impact of COVID-19 in the local health system. It was developed as an extension of the classic SEIR model to account for required hospital resources and behavioural changes of the population in response to containment measures. Time-varying parameters such as transmissibility are estimated using Bayesian methods, based on the database of reported cases with a moving time-window strategy. The assessment of the model offers reasonable results with estimated parameters and simulations, reflecting the observed dynamics in Paraguay. The proposed model can be used to simulate future scenarios and possible effects of containment strategies, to guide the public institution response based on the available resources in the local health system. |
Gaia Collaboration and M. García-Torres Gaia Early Data Release 3-Acceleration of the Solar System from Gaia astrometry Journal Article In: Astronomy & Astrophysics, vol. 649, pp. A9, 2021. @article{klioner2021gaia, |
Gaia Collaboration and M. García-Torres Gaia Early Data Release 3-The Galactic anticentre Journal Article In: Astronomy & Astrophysics, vol. 649, pp. A8, 2021. @article{antoja2021gaia, |
A. GA. Brown and A. Vallenari and T. Prusti and JHJ. De Bruijne and C. Babusiaux and M. Biermann and OL. Creevey and DW. Evans and L. Eyer and A. Hutton and M. García-Torres and others Gaia Early Data Release 3-Summary of the contents and survey properties Journal Article In: Astronomy & Astrophysics, vol. 649, pp. A1, 2021. @article{brown2021gaia, |
Gaia Collaboration and M. García-Torres Gaia Early Data Release 3-Structure and properties of the Magellanic Clouds Journal Article In: Astronomy & Astrophysics, vol. 649, pp. A7, 2021. @article{luri2021gaia, |
Gaia Collaboration and M. García-Torres Gaia Early Data Release 3-The Gaia Catalogue of Nearby Stars Journal Article In: Astronomy & Astrophysics, vol. 649, pp. A6, 2021. @article{smart2021gaia, |
F. Divina and F. Gómez-Vela and M. García-Torres Advanced Optimization Methods and Big Data Applications in Energy Demand Forecast Journal Article In: Applied Sciences, vol. 11, no. 3, pp. 1261, 2021. @article{divina2021advanced, |
A. Lopez-Fernandez and D. Rodriguez-Baena and F. Gomez-Vela and F. Divina and M. Garcia-Torres A multi-GPU biclustering algorithm for binary datasets Journal Article In: Journal of Parallel and Distributed Computing, vol. 147, pp. 209–219, 2021. @article{lopez2021multi, |
J. A. Gallardo and M. García-Torres and F. Gómez-Vela and F. Morales and F. Divina and D. Becerra-Alonso and G. Velázquez and F. Daumas-Ladouce and J. L. Vázquez Noguera and C. Ayala Sauer Forecasting Electricity Consumption Data from Paraguay Using a Machine Learning Approach Conference SOCO 16th International Conference on Soft Computing Models in Industrial and Environmental Applications, vol. 1401, Advances in Intelligent Systems and Computing 2021. @conference{gallardo2022forecasting, |
2020 |
F. Divina and J. F. Torres and M. García-Torres and F. Martínez-Álvarez and A. Troncoso Hybridizing deep learning and neuroevolution: Application to the Spanish short-term electric energy consumption forecasting Journal Article In: Applied Sciences, vol. 10, no. 16, pp. 5487, 2020. @article{DIVINA2020, The electric energy production would be much more efficient if accurate estimations of the future demand were available, since these would allow allocating only the resources needed for the production of the right amount of energy required. With this motivation in mind, we propose a strategy, based on neuroevolution, that can be used to this aim. Our proposal uses a genetic algorithm in order to find a sub-optimal set of hyper-parameters for configuring a deep neural network, which can then be used for obtaining the forecasting. Such a strategy is justified by the observation that the performances achieved by deep neural networks are strongly dependent on the right setting of the hyper-parameters, and genetic algorithms have shown excellent search capabilities in huge search spaces. Moreover, we base our proposal on a distributed computing platform, which allows its use on a large time-series. In order to assess the performances of our approach, we have applied it to a large dataset, related to the electric energy consumption registered in Spain over almost 10 years. Experimental results confirm the validity of our proposal since it outperforms all other forecasting techniques to which it has been compared. |
F. M. Delgado-Chaves and F. Gómez-Vela and F. Divina and M. García-Torres and D. S. Rodríguez-Baena Computational Analysis of the Global Effects of Ly6E in the Immune Response to Coronavirus Infection Using Gene Networks Journal Article In: Genes, vol. 11, no. 7, pp. 831-864, 2020. @article{Delgado-Chaves20, Gene networks have arisen as a promising tool in the comprehensive modeling and analysis of complex diseases. Particularly in viral infections, the understanding of the host-pathogen mechanisms, and the immune response to these, is considered a major goal for the rational design of appropriate therapies. For this reason, the use of gene networks may well encourage therapy-associated research in the context of the coronavirus pandemic, orchestrating experimental scrutiny and reducing costs. In this work, gene co-expression networks were reconstructed from RNA-Seq expression data with the aim of analyzing the time-resolved effects of gene Ly6E in the immune response against the coronavirus responsible for murine hepatitis (MHV). Through the integration of differential expression analyses and reconstructed networks exploration, significant differences in the immune response to virus were observed in Ly6E∆HSC compared to wild type animals. Results show that Ly6E ablation at hematopoietic stem cells (HSCs) leads to a progressive impaired immune response in both liver and spleen. Specifically, depletion of the normal leukocyte mediated immunity and chemokine signaling is observed in the liver of Ly6E∆HSC mice. On the other hand, the immune response in the spleen, which seemed to be mediated by an intense chromatin activity in the normal situation, is replaced by ECM remodeling in Ly6E∆HSC mice. These findings, which require further experimental characterization, could be extrapolated to other coronaviruses and motivate the efforts towards novel antiviral approaches. |
D. S. Rodríguez-Baena and F. Gómez-Vela and M. García-Torres and F. Divina and C. D. Barranco and N- Díaz-Díaz and M. Jimenez and G. Montalvo Identifying livestock behavior patterns based on accelerometer dataset Journal Article In: Journal of Computational Science, vol. 41, pp. 101076, 2020. @article{Rodriguez-Baena20, In large livestock farming it would be beneficial to be able to automatically detect behaviors in animals. In fact, this would allow to estimate the health status of individuals, providing valuable insight to stock raisers. Traditionally this process has been carried out manually, relying only on the experience of the breeders. Such an approach is effective for a small number of individuals. However, in large breeding farms this may not represent the best approach, since, in this way, not all the animals can be effectively monitored all the time. Moreover, the traditional approach heavily rely on human experience, which cannot be always taken for granted. To this aim, in this paper, we propose a new method for automatically detecting activity and inactivity time periods of animals, as a behavior indicator of livestock. In order to do this, we collected data with sensors located in the body of the animals to be analyzed. In particular, the reliability of the method was tested with data collected on Iberian pigs and calves. Results confirm that the proposed method can help breeders in detecting activity and inactivity periods for large livestock farming. |
T. Vanhaeren and F. Divina and M. García-Torres and F. Gómez-Vela and W. Vanhoof and P. M. Martínez-García A Comparative Study of Supervised Machine Learning Algorithms for the Prediction of Long-Range Chromatin Interactions Journal Article In: Genes, vol. 11, no. 9, pp. 985, 2020. @article{Vanhaeren20, The role of three-dimensional genome organization as a critical regulator of gene expression has become increasingly clear over the last decade. Most of our understanding of this association comes from the study of long range chromatin interaction maps provided by Chromatin Conformation Capture-based techniques, which have greatly improved in recent years. Since these procedures are experimentally laborious and expensive, in silico prediction has emerged as an alternative strategy to generate virtual maps in cell types and conditions for which experimental data of chromatin interactions is not available. Several methods have been based on predictive models trained on one-dimensional (1D) sequencing features, yielding promising results. However, different approaches vary both in the way they model chromatin interactions and in the machine learning-based strategy they rely on, making it challenging to carry out performance comparison of existing methods. In this study, we use publicly available 1D sequencing signals to model cohesin-mediated chromatin interactions in two human cell lines and evaluate the prediction performance of six popular machine learning algorithms: decision trees, random forests, gradient boosting, support vector machines, multi-layer perceptron and deep learning. Our approach accurately predicts long-range interactions and reveals that gradient boosting significantly outperforms the other five methods, yielding accuracies of about 95%. We show that chromatin features in close genomic proximity to the anchors cover most of the predictive information, as has been previously reported. Moreover, we demonstrate that gradient boosting models trained with different subsets of chromatin features, unlike the other methods tested, are able to produce accurate predictions. In this regard, and besides architectural proteins, transcription factors are shown to be highly informative. Our study provides a framework for the systematic prediction of long-range chromatin interactions, identifies gradient boosting as the best suited algorithm for this task and highlights cell-type specific binding of transcription factors at the anchors as important determinants of chromatin wiring mediated by cohesin |
F. Daumas-Ladouce and M. García-Torres and J.L. Vázquez Noguera and D. P. Pinto-Roa and H. Legal-Alaya Multi-Objective Pareto Histogram Equalization Journal Article In: Electronic Notes in Theoretical Computer Science, vol. 349, pp. 3-23, 2020. @article{Daumas-Ladouce20, Several histogram equalization methods focus on enhancing the contrast as one of their main objectives, but usually without considering the details of the input image. Other methods seek to keep the brightness while improving the contrast, causing distortion. Among the multi-objective algorithms, the classical optimization (a priori) techniques are commonly used given their simplicity. One of the most representative method is the weighted sum of metrics used to enhance the contrast of an image. These type of techniques, beside just returning a single image, have problems related to the weight assignment for each selected metric. To avoid the pitfalls of the algorithms just mentioned, we propose a new method called MOPHE (MultiObjective Pareto Histogram Equalization) which is based on Multi-objective Particle Swarm Optimization (MOPSO) approach combining different metrics in a posteriori selection criteria context. The goal of this method is three-fold: (1) improve the contrast (2) without losing important details, (3) avoiding an excessive distortion. MOPHE, is a pure multi-objective optimization algorithm, consequently a set of tradeoff optimal solutions are generated, thus providing alternative solutions to the decision-maker, allowing the selection of one or more resulting images, depending on the application needs. Experimental results indicate that MOPHE is a promising approach, as it calculates a set of trade-off optimal solutions that are better than the results obtained from representative algorithms from the state-of-the-art regarding visual quality and metrics measurement. |