@article{MOLINA22,

title = {DIAFAN-TL: An instance weighting-based transfer learning algorithm with application to phenology forecasting},

author = {M. Á. Molina and M. J. Jiménez-Navarro and R. Arjona and F. Mártinez-Álvarez and G. Asencio-Cortés},

url = {https://www.sciencedirect.com/science/article/pii/S0950705122008322},

doi = {https://doi.org/10.1016/j.knosys.2022.109644},

year  = {2022},

date = {2022-10-22},

journal = {Knowledge-Based Systems},

volume = {254},

pages = {109644},

abstract = {The agricultural sector has been, and still is, the most important economic sector in many countries. Due to advances in technology, the amount and variety of available data have been increasing over the years. However, compared to other economic sectors, there is not always enough quality data for one particular domain (crops, plantations, plots) to obtain acceptable forecasting results with machine learning algorithms. In this context, transfer learning can help extract knowledge from different but related domains with enough data to transfer it to a target domain with scarce data. This process can overcome forecasting accuracy compared to training models uniquely with data from the target domain. In this work, a novel instance weighting-based transfer learning algorithm is proposed and applied to the phenology forecasting problem. A new metric named DIAFAN is proposed to weight samples from different source domains according to their relationship with the target domain, promoting the diversity of the information and avoiding inconsistent samples. Additionally, a set of validation schemes is specifically designed to ensure fair comparisons in terms of data volume with other benchmark transfer learning algorithms. The proposed algorithm, DIAFAN-TL, is tested with a proposed dataset of 16 plots of olive groves from different places, including information fusion from satellite images, meteorological stations and human field sampling of crop phenology. DIAFAN-TL achieves a remarkable improvement with respect to 15 other well-known transfer learning algorithms and three nontransfer learning scenarios. Finally, several performance analyses according to the different phenological states, prediction horizons and source domains are also performed.},

keywords = {},

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 = {},

pubstate = {published},

tppubtype = {article}

}

@article{castan2022,

title = {A new hybrid method for predicting univariate and multivariate time series based on pattern forecasting},

author = {M.A. Castán-Lascorz and P. Jiménez-Herrera and A. Troncoso and G. Asencio-Cortés},

url = {https://www.sciencedirect.com/science/article/pii/S0020025521012226?via%3Dihub},

doi = {10.1016/j.ins.2021.12.001},

year  = {2022},

date = {2022-01-01},

journal = {Information Sciences},

volume = {586},

pages = {611--627},

abstract = {Time series forecasting has become indispensable for multiple applications and industrial processes. Currently, a large number of algorithms have been developed to forecast time series, all of which are suitable depending on the characteristics and patterns to be inferred in each case. In this work, a new algorithm is proposed to predict both univariate and multivariate time series based on a combination of clustering, classification and forecasting techniques. The main goal of the proposed algorithm is first to group windows of time series values with similar patterns by applying a clustering process. Then, a specific forecasting model for each pattern is built and training is only conducted with the time windows corresponding to that pattern. The new algorithm has been designed using a flexible framework that allows the model to be generated using any combination of approaches within multiple machine learning techniques. To evaluate the model, several experiments are carried out using different configurations of the clustering, classification and forecasting methods that the model consists of. The results are analyzed and compared to classical prediction models, such as autoregressive, integrated, moving average and Holt-Winters models, to very recent forecasting methods, including deep, long short-term memory neural networks, and to well-known methods in the literature, such as k nearest neighbors, classification and regression trees, as well as random forest.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@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}

}