@article{pulido2021,

title = {Serial co-expression analysis of host factors from SARS-CoV viruses highly converges with former high-throughput screenings and proposes key regulators},

author = {A. J. Pérez-Pulido and G. Asencio-Cortés and A. M. Brokate-Llanos and G. Brea-Calvo and M. R. Rodríguez-Griñolo and A. Garzón and M. J. Muñoz},

url = {https://academic.oup.com/bib/article/22/2/1038/6103172},

doi = {10.1093/bib/bbaa419},

year  = {2021},

date = {2021-01-01},

journal = {Briefings in Bioinformatics},

volume = {22},

number = {2},

pages = {1038--1052},

abstract = {The current genomics era is bringing an unprecedented growth in the amount of gene expression data, only comparable to the exponential growth of sequences in databases during the last decades. This data allow the design of secondary analyses that take advantage of this information to create new knowledge. One of these feasible analyses is the evaluation of the expression level for a gene through a series of different conditions or cell types. Based on this idea, we have developed Automatic and Serial Analysis of CO-expression, which performs expression profiles for a given gene along hundreds of heterogeneous and normalized transcriptomics experiments and discover other genes that show either a similar or an inverse behavior. It might help to discover co-regulated genes, and common transcriptional regulators in any biological model. The present severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic is an opportunity to test this novel approach due to the wealth of data that are being generated, which could be used for validating results. Thus, we have identified 35 host factors in the literature putatively involved in the infectious cycle of SARS-CoV viruses and searched for genes tightly co-expressed with them. We have found 1899 co-expressed genes whose assigned functions are strongly related to viral cycles. Moreover, this set of genes heavily overlaps with those identified by former laboratory.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{MARTINEZ-ALVAREZ20,

title = {Coronavirus Optimization Algorithm: A bioinspired metaheuristic based on the COVID-19 propagation model},

author = {F. Martínez-Álvarez and G. Asencio-Cortés and J. F. Torres and D. Gutiérrez-Avilés and L. Melgar-García and R. Pérez-Chacón and C. Rubio-Escudero and A. Troncoso and J. C. Riquelme},

url = {https://www.liebertpub.com/doi/full/10.1089/big.2020.0051},

doi = {10.1089/big.2020.0051},

year  = {2020},

date = {2020-07-22},

journal = {Big Data},

volume = {8},

number = {4},

pages = {308-322},

abstract = {This work proposes a novel bioinspired metaheuristic, simulating how the coronavirus spreads and infects healthy people. From a primary infected individual (patient zero), the coronavirus rapidly infects new victims, creating large populations of infected people who will either die or spread infection. Relevant terms such as reinfection probability, super-spreading rate, social distancing measures or traveling rate are introduced into the model in order to simulate the coronavirus activity as accurately as possible. The infected population initially grows exponentially over time, but taking into consideration social isolation measures, the mortality rate and number of recoveries, the infected population gradually decreases. The Coronavirus Optimization Algorithm has two major advantages when compared to other similar strategies. Firstly, the input parameters are already set according to the disease statistics, preventing researchers from initializing them with arbitrary values. Secondly, the approach has the ability to end after several iterations, without setting this value either. Furthermore, a parallel multi-virus version is proposed, where several coronavirus strains evolve over time and explore wider search space areas in less iterations. Finally, the metaheuristic has been combined with deep learning models, in order to find optimal hyperparameters during the training phase. As application case, the problem of electricity load time series forecasting has been addressed, showing quite remarkable performance.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PEREZ20,

title = {Big data time series forecasting based on pattern sequence similarity and its application to the electricity demand},

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

url = {https://www.sciencedirect.com/science/article/pii/S0020025520306010},

doi = {10.1016/j.ins.2020.06.014},

year  = {2020},

date = {2020-06-06},

journal = {Information Sciences},

volume = {540},

pages = {160-174},

abstract = {This work proposes a novel algorithm to forecast big data time series. Based on the well-established Pattern Sequence Forecasting algorithm, this new approach has two major contributions to the literature. First, the improvement of the aforementioned algorithm with respect to the accuracy of predictions, and second, its transformation into the big data context, having reached meaningful results in terms of 

scalability. The algorithm uses the Apache Spark distributed computation framework and it is a ready-to-use application with few parameters to adjust. Physical and cloud clusters have been used to carry out the experimentation, which consisted in applying the algorithm to real-world data from Uruguay electricity demand.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{GOMEZ19,

title = {A novel ensemble method for electric vehicle power consumption forecasting: application to the Spanish system},

author = {C. Gómez-Quiles and G. Asencio-Cortés and A. Gastalver-Rubio and F. Martínez-Álvarez and A. Troncoso and J. Manresa and J. C. Riquelme and 

J. M. Riquelme},

url = {https://ieeexplore.ieee.org/document/8807120},

doi = {https://doi.org/10.1109/ACCESS.2019.2936478},

year  = {2019},

date = {2019-08-01},

journal = {IEEE Access},

volume = {7},

pages = {120840-120856},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{en12010094b,

title = {A Novel Hybrid Algorithm to Forecast Functional Time Series Based on Pattern Sequence Similarity with Application to Electricity Demand},

author = {F. Martinez-Alvarez and A. Schmutz and G. Asencio-Cortes and J. Jacques},

url = {http://www.mdpi.com/1996-1073/12/1/94},

doi = {10.3390/en12010094},

issn = {1996-1073},

year  = {2019},

date = {2019-01-01},

journal = {Energies},

volume = {12},

number = {94},

pages = {1-18},

abstract = {The forecasting of future values is a very challenging task. In almost all scientific disciplines, the analysis of time series provides useful information and even economic benefits. In this context, this paper proposes a novel hybrid algorithm to forecast functional time series with arbitrary prediction horizons. It integrates a well-known clustering functional data algorithm into a forecasting strategy based on pattern sequence similarity, which was originally developed for discrete time series. The new approach assumes that some patterns are repeated over time, and it attempts to discover them and evaluate their immediate future. Hence, the algorithm first applies a clustering functional time series algorithm, i.e., it assigns labels to every data unit (it may represent either one hour, or one day, or any arbitrary length). As a result, the time series is transformed into a sequence of labels. Later, it retrieves the sequence of labels occurring just after the sample that we want to be forecasted. This sequence is searched for within the historical data, and every time it is found, the sample immediately after is stored. Once the searching process is terminated, the output is generated by weighting all stored data. The performance of the approach has been tested on real-world datasets related to electricity demand and compared to other existing methods, reporting very promising results. Finally, a statistical significance test has been carried out to confirm the suitability of the election of the compared methods. In conclusion, a novel algorithm to forecast functional time series is proposed with very satisfactory results when assessed in the context of electricity demand.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ENV2018,

title = {Imbalanced classification techniques for monsoon forecasting based on a new climatic time series},

author = {A. Troncoso and P. Ribera and G. Asencio-Cortés and I. Vega and D. Gallego},

url = {https://www.sciencedirect.com/science/article/pii/S1364815217301950},

doi = {10.1016/j.envsoft.2017.11.024},

year  = {2018},

date = {2018-01-01},

journal = {Environmental Modelling & Software},

volume = {106},

number = {6},

pages = {48-56},

abstract = {Monsoons have been widely studied in the literature due to their climatic impact related to precipitation 

and temperature over different regions around the world. In this work, data mining techniques, namely 

imbalanced classification techniques, are proposed in order to check the capability of climate indices to 

capture and forecast the evolution of theWestern North Pacific Summer Monsoon. Thus, the main goal is 

to predict if the monsoon will be an extreme monsoon for a temporal horizon of a month. Firstly, a new 

monthly index of the monsoon related to its intensity has been generated. Later, the problem of forecasting 

has been transformed into a binary imbalanced classification problem and a set of representative 

techniques, such as models based on trees, models based on rules, black box models and ensemble 

techniques, are applied to obtain the forecasts. From the results obtained, it can be concluded that the 

methodology proposed here reports promising results according to the quality measures evaluated and 

predicts extreme monsoons for a temporal horizon of a month with a high accuracy.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Gomez-Losada2018b,

title = {A novel approach to forecast urban surface-level ozone considering heterogeneous locations and limited information},

author = {A. Gomez-Losada and G. Asencio-Cortes and F. Martinez-Alvarez and J. C. Riquelme},

doi = {10.1016/j.envsoft.2018.08.013},

issn = {1364-8152},

year  = {2018},

date = {2018-01-01},

journal = {Environmental Modelling and Software},

number = {110},

pages = {52-61},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Florido2018,

title = {A novel tree-based algorithm to discover seismic patterns in earthquake catalogs},

author = {E. Florido and G. Asencio-Cortes and J. L. Aznarte and C. Rubio-Escudero and F. Martinez-Alvarez},

doi = {10.1016/j.cageo.2018.03.005},

issn = {0098-3004},

year  = {2018},

date = {2018-01-01},

journal = {Computers and Geosciences},

number = {115},

pages = {96-104},

abstract = {A novel methodology is introduced in this research study to detect seismic precursors. Based on an existing approach, the new methodology searches for patterns in the historical data. Such patterns may contain statistical or soil dynamics information. It improves the original version in several aspects. First, new seismicity indicators have been used to characterize earthquakes. Second, a machine learning clustering algorithm has been applied in a very flexible way, thus allowing the discovery of new data groupings. Third, a novel search strategy is proposed in order to obtain non-overlapped patterns. And, fourth, arbitrary lengths of patterns are searched for, thus discovering long and short-term behaviors that may influence in the occurrence of medium-large earthquakes. The methodology has been applied to seven different datasets, from three different regions, namely the Iberian Peninsula, Chile and Japan. Reported results show a remarkable improvement with respect to the former version, in terms of all evaluated quality measures. In particular, the number of false positives has decreased and the positive predictive values increased, both of them in a very remarkable manner.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Asencio-Cortes2018b,

title = {Earthquake prediction in California using regression algorithms and cloud-based big data infrastructure},

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

doi = {10.1016/j.cageo.2017.10.011},

issn = {0098-3004},

year  = {2018},

date = {2018-01-01},

journal = {Computers and Geosciences},

number = {115},

pages = {198-210},

abstract = {Earthquake magnitude prediction is a challenging problem that has been widely studied during the last decades. Statistical, geophysical and machine learning approaches can be found in literature, with no particularly satisfactory results. In recent years, powerful computational techniques to analyze big data have emerged, making possible the analysis of massive datasets. These new methods make use of physical resources like cloud based architectures. California is known for being one of the regions with highest seismic activity in the world and many data are available. In this work, the use of several regression algorithms combined with ensemble learning is explored in the context of big data (1 GB catalog is used), in order to predict earthquakes magnitude within the next seven days. Apache Spark framework, H2O library in R language and Amazon cloud infrastructure were been used, reporting very promising results.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Shang2018b,

title = {Data field-based K-means clustering for spatio-temporal seismicity analysis and hazard assessment},

author = {X. Shang and X. Li and A. Morales-Esteban and G. Asencio-Cortes and Z. Wang},

doi = {10.3390/rs10030461},

issn = {2072-4292},

year  = {2018},

date = {2018-01-01},

journal = {Remote Sensing},

volume = {10},

number = {461},

pages = {1-22},

abstract = {Microseismic sensing taking advantage of sensors can remotely monitor seismic activities and evaluate seismic hazard. Compared with experts' seismic event clusters, clustering algorithms are more objective, and they can handle many seismic events. Many methods have been proposed for seismic event clustering and the K-means clustering technique has become the most famous one. However, K-means can be affected by noise events (large location error events) and initial cluster centers. In this paper, a data field-based K-means clustering methodology is proposed for seismicity analysis. The application of synthetic data and real seismic data have shown its effectiveness in removing noise events as well as finding good initial cluster centers. Furthermore, we introduced the time parameter into the K-means clustering process and applied it to seismic events obtained from the Chinese Yongshaba mine. The results show that the time-event location distance and data field-based K-means clustering can divide seismic events by both space and time, which provides a new insight for seismicity analysis compared with event location distance and data field-based K-means clustering. The Krzanowski-Lai (KL) index obtains a maximum value when the number of clusters is five: the energy index (EI) shows that clusters C1, C3 and C5 have very critical periods. In conclusion, the time-event location distance, and the data field-based K-means clustering can provide an effective methodology for seismicity analysis and hazard assessment. In addition, further study can be done by considering time-event location-magnitude distances.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}