Publications

@article{RING2025_Martin,

title = {Metalearning for improving time series forecasting based on deep learning: A water case study},

author = {Martín Solís and A. Gil-Gamboa and Alicia Troncoso},

url = {https://www.sciencedirect.com/science/article/pii/S2590123025035960},

doi = {10.1016/j.rineng.2025.107541},

year  = {2025},

date = {2025-12-09},

urldate = {2025-12-09},

journal = {Results in Engineering},

volume = {28},

pages = {107541},

keywords = {deep learning, forecasting, time series},

pubstate = {published},

tppubtype = {article}

}

@article{ASOC2024,

title = {Improving monsoon forecasting based on feature selection and explainable artificial intelligence},

author = {A.M. Chacón-Maldonado and A.R. Troncoso-García and G. Asencio-Cortés and A. Troncoso},

url = {https://www.sciencedirect.com/science/article/pii/S1568494625013663},

doi = {10.1016/j.asoc.2025.114053},

year  = {2025},

date = {2025-12-02},

urldate = {2025-12-02},

journal = {Applied Soft Computing},

volume = {185},

pages = {114053},

keywords = {feature selection, natural disasters, XAI},

pubstate = {published},

tppubtype = {article}

}

@article{CSUR2025,

title = {A Survey of Quantum Machine Learning: Foundations, Algorithms, Frameworks, Data and Applications},

author = {F. Rodríguez-Díaz and D. Gutiérrez-Avilés and A. Troncoso and F. Martínez-Álvarez},

url = {https://dl.acm.org/doi/10.1145/3764582},

doi = {10.1145/3764582},

year  = {2025},

date = {2025-10-01},

urldate = {2025-10-01},

journal = {ACM Computing Surveys},

volume = {58},

issue = {4},

pages = {1-35},

keywords = {quantum computing},

pubstate = {published},

tppubtype = {article}

}

@article{INFFUSChacon2025,

title = { A multimodal hybrid deep learning approach for pest forecasting using time series and satellite images},

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

url = {https://www.sciencedirect.com/science/article/pii/S1566253525004233},

doi = {10.1016/j.inffus.2025.103350},

year  = {2025},

date = {2025-07-01},

urldate = {2025-07-01},

journal = {Information Fusion},

volume = {124},

pages = {103350},

keywords = {deep learning, precision agriculture},

pubstate = {published},

tppubtype = {article}

}

@article{ULLAH25,

title = {A Novel Explainable AI Framework for Medical Image Classification Integrating Statistical, Visual, and Rule-Based Methods},

author = {N. Ullah and F. Guzmán-Aroca and F. Martínez-Álvarez and I. De Falco and G. Sannino},

url = {https://www.sciencedirect.com/science/article/pii/S1361841525002129},

doi = {https://doi.org/10.1016/j.media.2025.103665},

year  = {2025},

date = {2025-06-06},

urldate = {2025-06-06},

journal = {Medical Image Analysis},

volume = {105},

pages = {103665},

abstract = {Artificial intelligence and deep learning are powerful tools for extracting knowledge from large datasets, particularly in healthcare. However, their black-box nature raises interpretability concerns, especially in highstakes applications. Existing eXplainable Artificial Intelligence methods often focus solely on visualization or rule-based explanations, limiting interpretability’s depth and clarity. This work proposes a novel explainable AI method specifically designed for medical image analysis, integrating statistical, visual, and rule-based explanations to improve transparency in deep learning models. Statistical features are derived from deep features extracted using a custom Mobilenetv2 model. A two-step feature selection method—zero-based filtering with mutual importance selection—ranks and refines these features. Decision tree and RuleFit models

are employed to classify data and extract human-readable rules. Additionally, a novel statistical feature map overlay visualization generates heatmap-like representations of three key statistical measures (mean, skewness, and entropy), providing both localized and quantifiable visual explanations of model decisions. The proposed method has been validated on five medical imaging datasets—COVID-19 radiography, ultrasound

breast cancer, brain tumour magnetic resonance imaging, lung and colon cancer histopathological, and glaucoma images—with results confirmed by medical experts, demonstrating its effectiveness in enhancing interpretability for medical image classification tasks.},

keywords = {association rules, deep learning, feature selection, XAI},

pubstate = {published},

tppubtype = {article}

}

@article{GIL-GAMBOA25,

title = {Energy-efficient transfer learning for water consumption forecasting},

author = {A. Gil-Gamboa and J. F. Torres and F. Martínez-Álvarez and A. Troncoso},

url = {https://www.sciencedirect.com/science/article/pii/S2210537925000502},

doi = {https://doi.org/10.1016/j.suscom.2025.101130},

year  = {2025},

date = {2025-05-07},

urldate = {2025-05-07},

journal = {Sustainable Computing: Informatics and Systems},

volume = {46},

pages = {101130},

abstract = {Artificial intelligence is expanding at an unprecedented rate due to the numerous advantages it provides to all types of businesses and industries. Water utilities are adopting artificial intelligence models to optimize water management in cities nowadays. However, the substantial computational demands of artificial intelligence present challenges, particularly regarding energy consumption and environmental impact. This paper addresses this problem by proposing a transfer learning approach for water consumption forecasting that reduces computational time, energy usage, and CO$_2$ emissions. The proposed methodology consists in developing a transfer learning approach based on a deep learning model already trained for a task with similar characteristics such as predicting electricity consumption. Thus, a pre-trained deep learning model designed for electricity consumption prediction is adapted to the water consumption domain, leveraging shared characteristics between these tasks. Experiments are conducted to determine the optimal amount of knowledge transfer and compare the performance of this approach with other state-of-the-art time-series forecasting models. Using real data from a water company in Spain, the transfer learning model achieves a similar or better accuracy than the other methods, while demonstrating significantly lower computational times, energy consumption and CO2 emissions. In addition, a scalability analysis has been conducted leading to the conclusion that the proposed transfer learning model is highly suitable to deal with big data. These findings highlight the potential of transfer learning as a sustainable and scalable solution for big data challenges in water management systems.},

keywords = {deep learning, forecasting, time series, transfer learning},

pubstate = {published},

tppubtype = {article}

}

@article{GUTIERREZ-AVILES25,

title = {MetaGen: A framework for metaheuristic development and hyperparameter optimization in machine and deep learning},

author = {D. Gutiérrez-Avilés and M. J. Jiménez-Navarro and J. F. Torres and F. Martínez-Álvarez},

url = {https://www.sciencedirect.com/science/article/pii/S0925231225007180},

doi = {https://doi.org/10.1016/j.neucom.2025.130046},

year  = {2025},

date = {2025-03-15},

urldate = {2025-03-15},

journal = {Neurocomputing},

volume = {637},

pages = {130046},

abstract = {Hyperparameter optimization is a pivotal step in enhancing model performance within machine learning. Traditionally, this challenge is addressed through metaheuristics, which efficiently explore large search spaces to uncover optimal solutions. However, implementing these techniques can be complex without adequate development tools, which is the primary focus of this paper. Hence, we introduce MetaGen, a novel Python package designed to provide a comprehensive framework for developing and evaluating metaheuristic algorithms. MetaGen follows best practices in Python design, ensuring minimalistic code implementation, intuitive comprehension, and full flexibility in solution representation. The package defines two distinct user roles: Developers, responsible for algorithm implementation for hyperparameter optimization, and Solvers, who leverage pre-implemented metaheuristics to address optimization problems. Beyond algorithm implementation, MetaGen facilitates benchmarking through built-in test functions, ensuring standardized performance comparisons. It also provides automated reporting and visualization tools to analyze optimization progress and outcomes effectively. Furthermore, its modular design allows distribution

and integration into existing machine learning workflows. Several illustrative use cases are presented to demonstrate its adaptability and efficacy. The package, along with code, a user manual, and supplementary materials, is available at: https://github.com/Data-Science-Big-Data-Research-Lab/MetaGen.},

keywords = {big data, deep learning},

pubstate = {published},

tppubtype = {article}

}

@article{HABTEMARIAM25,

title = {A novel approach based on clustering and optimized ensemble deep learning for energy consumption forecasting in Ethiopia},

author = {E. T. Habtemariam and M. Martínez-Ballesteros and A. Troncoso and F. Martínez-Álvarez},

url = {https://www.sciencedirect.com/science/article/pii/S092523122500699X},

doi = {https://doi.org/10.1016/j.neucom.2025.130027},

year  = {2025},

date = {2025-03-13},

urldate = {2025-03-13},

journal = {Neurocomputing},

volume = {637},

pages = {130027},

abstract = {Predicting energy consumption accurately is crucial for optimizing energy management strategies and achieving sustainability goals. Traditional methods often struggle with the complexity of energy consumption patterns, particularly in developing regions such as Ethiopia, where unique challenges exist. This study proposes an ensemble deep learning approach that integrates multiple models to enhance prediction accuracy.

Additionally, as a previous step, a clustering process has been applied to discover different groups of customers. Our method combines deep learning architectures, including Gated Recurrent Units, Long Short-Term Memory, and Convolutional Neural Networks, within an optimized ensemble with weights computed with the Coronavirus Optimization Algorithm. This approach aims to leverage the strengths of each model

to produce robust and reliable predictions. We demonstrate that our ensemble approach yields competitive results, outperforming individual models within the ensemble. By integrating diverse models, our framework captures nuanced patterns in energy consumption data more effectively, contributing to improved prediction accuracy. Furthermore, we validate the effectiveness of our approach using three distinct datasets from Ethiopia for three different customer clusters. These datasets represent different regions and consumption profiles within the country, ensuring the robustness and generalizability of our proposed methodology.},

keywords = {clustering, deep learning, energy, forecasting},

pubstate = {published},

tppubtype = {article}

}

@article{TRONCOSO-GARCIA25,

title = {A new metric based on association rules to assess explainability techniques for time series forecasting},

author = {A. R. Troncoso-García and M. Martínez-Ballesteros and F. Martínez-Álvarez and A. Troncoso},

url = {https://ieeexplore.ieee.org/document/10879535},

doi = {10.1109/TPAMI.2025.3540513},

year  = {2025},

date = {2025-02-11},

urldate = {2025-02-11},

journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},

volume = {47},

number = {5},

pages = {4140-4155},

abstract = {This paper introduces a new, model-independent, metric, called RExQUAL, for quantifying the quality of explanations provided by attribution-based explainable artificial intelligence techniques and compare them. The underlying idea is based on feature attribution, using a subset of the ranking of the attributes highlighted by a model-agnostic explainable method in a forecasting task. Then, association rules are generated using these key attributes as input data. Novel metrics, including global support and confidence, are proposed to assess the joint quality of generated rules. Finally, the quality of the explanations is calculated based on a wise and comprehensive combination of the association rules global metrics. The proposed method integrates local explanations through attribution-based approaches for evaluation and feature selection with global explanations for the entire dataset. This paper rigorously evaluates the new metric by comparing three explainability techniques: the widely used SHAP and LIME, and the novel methodology RULEx. The experimental design includes predicting time series of different natures, including univariate and multivariate, through deep learning models. The results underscore the efficacy and versatility of the proposed methodology as a quantitative framework for evaluating and comparing explainable techniques.},

keywords = {association rules, forecasting, time series, XAI},

pubstate = {published},

tppubtype = {article}

}

@article{SCITOVSKI25,

title = {A partitioning incremental algorithm using adaptive Mahalanobis fuzzy clustering and identifying the most appropriate partition},

author = {R. Scitovski and K. Sabo and D. Grahovac and F. Martínez-Álvarez and S. Ungar},

url = {https://link.springer.com/article/10.1007/s10044-024-01360-2},

doi = {https://doi.org/10.1007/s10044-024-01360-2},

year  = {2025},

date = {2025-01-02},

journal = {Pattern Analysis and Applications},

volume = {28},

pages = {3},

abstract = {This paper deals with the problem of determining the most appropriate number of clusters in a fuzzy Mahalanobis partition. 

First, a new fuzzy Mahalanobis incremental algorithm is constructed to search for an optimal fuzzy Mahalanobis 

partition with 2, 3, ... clusters. Among these partitions, selecting the one with the most appropriate number of clusters 

is based on appropriately modified existing fuzzy indexes. In addition, the Fuzzy Mahalanobis Minimal Distance index 

is defined as a natural extension of the recently proposed Mahalanobis Minimal Distance index for non-fuzzy clustering. 

The new fuzzy Mahalanobis incremental algorithm was tested on several artificial data sets and the color image segmentation 

problems from real-world applications: art images, nature photography images, and medical images. The algorithm 

includes multiple usage of the global optimization algorithm DIRECT. But unlike previously known fuzzy Mahalanobis 

indexes, the proposed Fuzzy Mahalanobis Minimal Distance index ensures accurate results even when applied to complex 

real-world applications. A possible disadvantage could be the need for longer CPU time. Furthermore, besides effective 

identification of the partition with the most appropriate number of clusters, it is shown how to use the proposed Fuzzy 

Mahalanobis Minimal Distance index to search for an acceptable partition, which proved particularly useful in the abovementioned 

real-world applications.},

keywords = {clustering},

pubstate = {published},

tppubtype = {article}

}

@article{CASAS-GOMEZ25,

title = {Forecasting basal area increment in forest ecosystems using deep learning: A multi-species analysis in the Himalayas},

author = {P. Casas-Gómez and J. F. Torres and J. C. Linares and A. Troncoso and F. Martínez-Álvarez},

url = {https://www.sciencedirect.com/science/article/pii/S157495412400493X?via%3Dihub},

doi = {https://doi.org/10.1016/j.ecoinf.2024.102951},

year  = {2025},

date = {2025-01-01},

journal = {Ecological Informatics},

volume = {85},

pages = {102951},

abstract = {This study addresses the task of forecasting Basal Area Increment trends in forest ecosystems, which is essential for conservation and biodiversity management, particularly in the context of climate change. Traditional forecasting techniques, such as Linear Mixed Models, Random Forest and standard Artificial Neural Networks, often fail to account for the time-dependent nature of tree growth and utilize simple architectures. To overcome these limitations, we introduce the use of two different Deep Learning models: the Long Short-Term Memory network and the Temporal Convolutional Neural Network, which capture the temporal dependencies of growth by incorporating lagged Basal Area Increment values. Our methodology includes rigorous hyperparameter tuning to optimize the Deep Learning models’ architecture. We evaluate the models’ performance across 15 species in the Himalayan region, individually and collectively, using temperature and precipitation data as predictors. The Deep Learning model significantly outperforms state-of-the-art techniques, achieving the lowest Root Mean Squared Error (7.407 for LSTM and 6.202 for TCNN), highest 𝑅2 (0.495 for LSTM an0.585 for TCNN) and lowest Mean Absolute Percentage Error values (37.653 for LSTM and 34.296 for TCNN). These findings highlight the potential of Deep Learning networks to provide accurate and reliable Basal AreaIncrement forecasts, offering valuable insights for forest management and conservation efforts in the face of ongoing climate change.},

keywords = {deep learning, time series},

pubstate = {published},

tppubtype = {article}

}

@article{Melgar2025,

title = {Online forecasting using neighbor-based incremental learning for electricity markets},

author = {L. Melgar-García and D. Gutiérrez-Avilés and C. Rubio-Escudero and A. Troncoso },

url = {https://link.springer.com/article/10.1007/s00521-024-10876-x},

doi = {https://doi.org/10.1007/s00521-024-10876-x},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Neural Computing and Applications},

keywords = {energy, IoT, time series},

pubstate = {published},

tppubtype = {article}

}

@article{Chacon2025,

title = {A novel method based on hybrid deep learning with explainability for olive fruit pest forecasting},

author = {A. M. Chacón-Maldonado and L. Melgar-García and G. Asencio-Cortés and A. Troncoso},

url = {https://link.springer.com/article/10.1007/s00521-024-10731-z},

doi = {https://doi.org/10.1007/s00521-024-10731-z},

year  = {2025},

date = {2025-01-01},

urldate = {2024-01-01},

journal = {Neural Computing and Applications},

keywords = {deep learning, precision agriculture, XAI},

pubstate = {published},

tppubtype = {article}

}

@article{lopez2025data,

title = {Data mining for enhancing learning and assessment to a microcompetence-based methodology in higher education},

author = { A. Lopez-Fernandez and F. Divina and F. A. Gomez-Vela and M. Garcia-Torres},

doi = {10.1109/RITA.2025.3532879},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {IEEE Revista Iberoamericana de Tecnologias del Aprendizaje},

publisher = {IEEE},

abstract = {This work introduces an innovative teaching methodology based on microcompetences applied in a higher education context. The intervention involved creating a repository of practical case studies in the form of quizzes and integrating microcompetences 

 into each course activity. The digital tool Sapiens was used to identify learning deficiencies and provide both collective and individualized feedback. The results indicate a significant increase in student participation and academic performance compared to 

 previous years. Furthermore, students voluntarily used virtual teaching modalities to reinforce their knowledge, particularly in more complex areas. Data mining techniques identified performance patterns among students, highlighting the methodology’s 

 effectiveness in improving both transversal and specific competences. The study’s findings underscore the importance of implementing microcompetency-based methodologies in higher education to enhance the quality of learning and continuous assessment. This 

 approach not only facilitated a deeper understanding of course content but also promoted critical thinking, abstract reasoning, and interpersonal skills, preparing students for future academic and professional challenges. Additionally, the flexibility and 

 adaptability of the digital tools used provided a seamless transition across different teaching modalities, such as in-person, hybrid, and online formats. Thus, the implementation of this innovative methodology has demonstrated its potential to significantly 

 improve student engagement, participation, and academic success, thereby contributing to a more effective and comprehensive educational experience in higher education. url = https://ieeexplore.ieee.org/abstract/document/10849581},

keywords = {data mining, education},

pubstate = {published},

tppubtype = {article}

}

@article{garcia2025feature,

title = {Feature selection for high-dimensional data using a multivariate search space reduction strategy based scatter search},

author = {M. Garcia-Torres},

doi = {10.1007/s10732-025-09550-9},

year  = {2025},

date = {2025-01-01},

journal = {Journal of Heuristics},

volume = {31},

number = {1},

pages = {10},

publisher = {Springer},

abstract = {In feature selection, the increasing of the dimensionality and the complexity of feature interactions make the problem challenging. Furthermore, searching for an optimal subset of features from a high-dimensional feature space is known to be an 

 NP-hard problem. To improve the efficiency and effectiveness of the search algorithm, feature grouping has emerged as a way to reduce the search space by clustering features according to a measure. In this work we propose to reduce the search space by 

 applying a greedy algorithm, called Multivariate Greedy Predominant Groups Generator (MGPGG). MGPGG extends the idea of the Greedy Predominant Groups Generator (GPGG) algorithm by taking into account feature interaction among three or more features. For 

 this purpose, MGPGG uses the Multivariate Symmetrical Uncertainty (MSU) to group features that share information about the class label. We also propose a Scatter Search strategy that integrates MGPGG to find small subsets of features with high predictive power. 

 The proposed algorithm, called Multivariate Predominant Group-based Scatter Search (MPGSS), is tested on high-dimensional data from biomedical and text-mining fields. The proposal is compared with state-of-the-art feature selection strategies. Results show that 

 MPGSS is competitive since it is capable of finding small subsets of features while keeping high predictive classification models. url = https://link.springer.com/article/10.1007/s10732-025-09550-9},

keywords = {feature selection},

pubstate = {published},

tppubtype = {article}

}

@article{garcia2025rfmsu,

title = {RFMSU: A multivariate symmetrical uncertainty based random forest},

author = {M. Garcia-Torres and F. Saucedo and F. Divina and S. Gómez},

url = {https://www.sciencedirect.com/science/article/pii/S0031320325005990?via%3Dihub},

doi = {https://doi.org/10.1016/j.patcog.2025.111939},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Pattern Recognition},

volume = {169},

pages = {111939},

publisher = {Elsevier},

abstract = {Decision Trees (DTs) have become very popular classifiers due to their good performance and, most of all, their interpretability. In addition, the machine learning community is also paying attention to Random Forests (RFs) since they defy the interpretability-accuracy tradeoff. Most RFs strategies are based on univariate measures, a fact that may limit the capability of identifying the interaction among more than two features. In order to overcome this problem many multivariate approaches have been proposed. However, most of them are based on finding linear or non-linear combinations of features. In this work, we propose a novel univariate RF strategy that builds DTs using the Multivariate Symmetrical Uncertainty (MSU) measure as splitting criterion. The proposal, referred to as RF$_MSU$, was tested on high-dimensional datasets and compared to state-of-the-art univariate 

and multivariate DTs and RFs classifiers. Results suggest that RF$_MSU$ is capable of finding simpler rules than other RFs approaches while keeping a high predictive power equivalent to that of multivariate approaches. The DT strategies considered obtained simpler models than RF$_MSU$, but at the expense of degrading the classifier. Thus, we can conclude that RFMS U is a RF-based classifier that achieves a good trade-off between the performance and the complexity of the model.},

keywords = {Classification, data mining},

pubstate = {published},

tppubtype = {article}

}

@article{vazquez2025mammography,

title = {Mammography Reporting Dataset with BI-RADS System for Natural Language Processing Applications: Addressing Public Data Gaps in Spanish},

author = { J. L. Vázquez Noguera and A. Torres-Hurtado and H. Gómez-Adorno and J. C. Mello-Román and E. J. Fleitas-Alvarez and F. F. Espinola Schulze and M. García-Torres and C. D. Méndez Gaona and P. E. Gardel Sotomayor and S. Vázquez Noguera and N. E. Zaracho Amarilla and O. W. Gamarra Esquivel},

url = {https://www.sciencedirect.com/science/article/pii/S2352340925004883?via%3Dihub},

doi = {https://doi.org/10.1016/j.dib.2025.111761},

year  = {2025},

date = {2025-01-01},

journal = {Data in Brief},

volume = {61},

pages = {111761},

publisher = {Elsevier},

abstract = {Applying Natural Language Processing (NLP) to clinical reports is important for automating the analysis and classification of clinical data, improving diagnostic accuracy, and enhancing healthcare workflows. This article presents a dataset derived from mammography reports written in Spanish collected across multiple medical units operated by the Oxades company in Paraguay. The dataset contains 4,357 records and 15 variables, including the text of the complete report and also each of its sections separately (clinical observations, diagnostic conclusions, follow-up recommendations), and the BI-RADS (Breast Imaging Reporting and Data System) classification assigned to each one of the reports. Additionally, the dataset includes metadata such as report IDs, dates, and patient information such as age, patient reasons for the analysis, last menstruation period, type of hormonal therapy received, family history and number of children. To ensure patient confidentiality, all identifiable data was removed, and the dataset was structured using automated segmentation and manual verification to ensure quality and transparency. This dataset is an invaluable resource for both medical and AI research communities. It provides real-world data for developing and testing NLP algorithms and machine learning models, specifically for automating BI-RADS classification and analyzing mammography reports.},

keywords = {Classification, data mining},

pubstate = {published},

tppubtype = {article}

}

@article{rodriguez2025binrec,

title = {BinRec: addressing data sparsity and cold-start challenges in recommender systems with biclustering},

author = {D. Rodríguez-Baena and F. Gómez-Vela and A. Lopez-Fernandez and M. García-Torres and F. Divina},

url = {https://link.springer.com/article/10.1007/s10489-025-06725-6},

doi = {10.1007/s10489-025-06725-6},

year  = {2025},

date = {2025-01-01},

journal = {Applied Intelligence},

volume = {55},

number = {12},

pages = {830},

abstract = {Recommender Systems help users in making decision in different fields such as purchases or what movies to watch. User-Based Collaborative Filtering (UBCF) approach is one of the most commonly used techniques for developing these software tools. It is based on the idea that users who have previously shared similar tastes will almost certainly share similar tastes in the future. As a result, determining the nearest users to the one for whom recommendations are sought (active user) is critical. However, the massive growth of online commercial data has made this task especially difficult. As a result, Biclustering techniques have been used in recent years to perform a local search for the nearest users in subgroups of users with similar rating behaviour under a subgroup of items (biclusters), rather than searching the entire rating database. Nevertheless, due to the large size of these databases, the number of biclusters generated can be extremely high, making their processing very complex. In this paper we propose BinRec, a novel UBCF approach based on Biclustering. BinRec simplifies the search for neighbouring users by determining which ones are nearest to the active user based on the number of biclusters shared by the users. Experimental results show that BinRec outperforms other state-of-the-art recommender systems, with a remarkable improvement in environments with high data sparsity. The flexibility and scalability of the method position it as an efficient alternative for common collaborative filtering problems such as sparsity or cold-start.},

keywords = {clustering, pattern recognition},

pubstate = {published},

tppubtype = {article}

}

@article{vanhaeren2025enhancing,

title = {Enhancing R-loop prediction with high-throughput sequencing data},

author = {T. Vanhaeren and L. Cataneo and F. Divina and P. M. Martínez-García},

url = {https://academic.oup.com/nargab/article/7/2/lqaf077/8160316},

doi = {10.1093/nargab/lqaf077},

year  = {2025},

date = {2025-01-01},

journal = {NAR Genomics and Bioinformatics},

volume = {7},

number = {2},

pages = {lqaf077},

abstract = {R-loops are three-stranded RNA and DNA hybrid structures that often occur in the genome and play important roles in a variety of cellular processes from bacteria to mammals. Sequencing methods profiling R-loops genome-wide have revealed that they can form co-transcriptionally at cell type specific genes and associate with specific chromatin states during cell differentiation and reprogramming. However, current computational methods for the prediction of R-loops rely solely on their DNA sequence properties, which precludes detection across cell types, tissues or developmental stages. Here, we conduct a machine learning approach that allows the prediction of mammalian cell type-specific R-loops using sequence information and high-throughput sequencing signals. Our predictive models are induced from human samples and achieve highly accurate predictions, with transcriptomics, DNA features, chromatin accessibility and the active gene body H3K36me3 epigenomic mark being the most informative datasets. We generate de novo virtual R-loop maps that show high concordance with experimental ones and capture cell type specificity. Our approach compares favorably to sequence-based methods and can be generalized to mouse datasets. Based on this, we generate virtual R-loop maps in 51 mammalian systems that are freely accessible to the scientific community.},

keywords = {big data, bioinformatics, pattern recognition},

pubstate = {published},

tppubtype = {article}

}

@article{vanhaeren2025application,

title = {Application of XAI to the prediction of CTCF binding sites},

author = {T. Vanhaeren and A. R. Troncoso-García and J. F. Torres and F. Divina and P. M. Martínez-García},

url = {https://www.sciencedirect.com/science/article/pii/S259012302402019X},

doi = {10.1016/j.rineng.2024.103776},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Results in Engineering},

volume = {25},

pages = {103776},

abstract = {The inherent ‘black box’ nature of deep learning models has hindered their widespread adoption in certain fields, as they provide limited transparency into the reasoning behind their predictions. In the last years, Explainable Artificial Intelligence (XAI) techniques have proven to be effective not only in prediction itself but also in the extraction of meaningful knowledge from deep learning models by means of feature interpretation. In this study, Local Interpretable Model-agnostic Explanations are applied to the prediction of CTCF binding sites, a common task in the field of genomics. Good prediction performances and inferred explanations are obtained that highlight the most informative features that contribute to predictions such as chromatin accessibility and cis-regulatory elements which align well with previously reported data. This work represents a proof of concept showing that XAI are suitable for the extraction of molecular insights from complex biological problems like CTCF binding prediction.},

keywords = {big data, bioinformatics, deep learning},

pubstate = {published},

tppubtype = {article}

}

@article{Vellinger2025Livestock,

title = {Forecasting Livestock Activity through Interpretable Neuroevolutionary Transfer Learning},

author = {A. Vellinger and F. Rodriguez-Diaz and F. Divina and J. F. Torres},

url = {https://doi.org/10.1093/jigpal/jzaf034},

doi = {10.1093/jigpal/jzaf034},

year  = {2025},

date = {2025-01-01},

journal = {Logic Journal of the IGPL},

volume = {to appear},

number = {to appear},

pages = {to appear},

abstract = {In this paper, we describe a neuroevolutionary approach to livestock activity forecasting, specifically targeting the prediction of Iberian pigs movements. We successfully integrated Transfer Learning to save computational time and used an Explainable Artificial Intelligence technique to provide valuable insights from the model predictions. Inspired by previous work, we employ Deep Evolutionary Network Structured Representation to optimize both Long Short-Term Memory networks and Convolutional Neural Networks using genetic algorithms and dynamic structured grammatical evolution, and we compare the results with other commonly used approaches for time series forecasting. Experimental results demonstrate the superior performance of the proposed Long Short-Term Memory models over more traditional methods, highlighting their precision and consistency in predicting livestock activities. Furthermore, the application of Explainable Artificial Intelligence techniques enable to gain a deeper understanding and trust in AI-driven decisions within precision livestock farming.},

keywords = {deep learning, pattern recognition, time series},

pubstate = {published},

tppubtype = {article}

}

@article{RODRIGUEZ24,

title = {Explainable Olive grove and Grapevine pest forecasting through machine learning-based classification and regression},

author = {F. Rodríguez-Díaz and A. M. Chacón-Maldonado and A. R. Troncoso-García and G. Asencio-Cortés},

url = {https://www.sciencedirect.com/science/article/pii/S2590123024013136},

doi = {https://doi.org/10.1016/j.rineng.2024.103058},

year  = {2024},

date = {2024-09-09},

urldate = {2024-09-09},

journal = {Results in Engineering},

volume = {24},

pages = {103058},

abstract = {Pests significantly impact agricultural productivity, making early detection crucial for maximizing yields. This paper explores the use of machine learning models to predict olive fly and red spider mite infestations in Andalusia. Four datasets on crop phenology, pest populations, and damage levels were used, with models developed using the Python package H20, which focuses on interpretability through SHAP values and ICE plots. The results showed high precision in predicting pest outbreaks, particularly for the olive fly, with minimal differences between models using feature selection. In the vineyard dataset, the selection of characteristics improved the performance of the model by reducing the MAE and increasing R2. Explainability techniques identified solar radiation and wind direction as key factors in olive fly predictions, while past pest occurrences and wind velocity were influential for red spider mites, providing farmers with actionable insights for timely pest control.},

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

pubstate = {published},

tppubtype = {article}

}

@article{JIMENEZ-NAVARRO24b,

title = {Embedded feature selection for neural networks via learnable drop layer},

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

url = {https://academic.oup.com/jigpal/advance-article/doi/10.1093/jigpal/jzae062/7689640},

doi = {https://doi.org/10.1093/jigpal/jzae062},

year  = {2024},

date = {2024-07-06},

urldate = {2024-07-06},

journal = {Logic Journal of the IGPL},

pages = {jzae062},

abstract = {Feature selection is a widely studied technique whose goal is to reduce the dimensionality of the problem by removing irrelevant features. It has multiple benefits, such as improved efficacy, efficiency and interpretability of almost any type of machine learning model. Feature selection techniques may be divided into three main categories, depending on the process used to remove the features known as Filter, Wrapper and Embedded. Embedded methods are usually the preferred feature selection method that efficiently obtains a selection of the most relevant features of the model. However, not all models support an embedded feature selection that forces the use of a different method, reducing the efficiency and reliability of the selection. Neural networks are an example of a model that does not support embedded feature selection. As neural networks have shown to provide remarkable results in multiple scenarios such as classification and regression, sometimes in an ensemble with a model that includes an embedded feature selection, we attempt to embed a feature selection process with a general-purpose methodology. In this work, we propose a novel general-purpose layer for neural networks that removes the influence of irrelevant features. The Feature-Aware Drop Layer is included at the top of the neural network and trained during the backpropagation process without any additional parameters. Our methodology is tested with 17 datasets for classification and regression tasks, including data from different fields such as Health, Economic and Environment, among others. The results show remarkable improvements compared to three different feature selection approaches, with reliable, efficient and effective results.},

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

pubstate = {published},

tppubtype = {article}

}

@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{PEREZ24,

title = {Pattern sequence-based algorithm for multivariate big data time series forecasting: Application to electricity consumption},

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

url = {https://www.sciencedirect.com/science/article/pii/S0167739X23004752},

doi = {https://doi.org/10.1016/j.future.2023.12.021},

year  = {2024},

date = {2024-01-29},

journal = {Future Generation Computer Systems},

volume = {154},

pages = {397-412},

abstract = {Several interrelated variables typically characterize real-world processes, and a time series cannot be predicted without considering the influence that other time series might have on the target time series. This work proposes a novel algorithm to forecast multivariate big data time series. This new general-purpose approach consists first of a previous pattern recognition performed jointly using all time series that form the multivariate time series and then predicts the target time series by searching for similarities between pattern sequences. The proposed algorithm is designed to tackle multivariate time series forecasting problems within the context of big data. In particular, the algorithm has been developed with a distributed nature to enhance its efficiency in analyzing and processing large volumes of data. Moreover, the algorithm is straightforward to use, with only two parameters needing adjustment. Another advantage of the MV-bigPSF algorithm is its ability to perform multi-step forecasting, which is particularly useful in many practical applications. To evaluate the algorithm’s performance, real-world data from Uruguay’s power consumption has been utilized. Specifically, MV-bigPSF has been compared with both univariate and multivariate methods. Regarding the univariate ones, MV-bigPSF improved 12.8% in MAPE compared to the second-best method. Regarding the multivariate comparison, MV-bigPSF improved 44.8% in MAPE with respect to the second most accurate method. Regarding efficiency, the execution time of MV-bigPSF was 1.83 times faster than the second-fastest multivariate method, both in a single-core environment. Therefore, the proposed algorithm can be a valuable tool for practitioners and researchers working in multivariate time series forecasting, particularly in big data applications.},

keywords = {big data, energy, forecasting, time series},

pubstate = {published},

tppubtype = {article}

}

@article{GARCIA-SOTO24,

title = {Water consumption time series forecasting in urban centers using deep neural networks},

author = {C. G. García-Soto and J. F. Torres and M. A. Zamora-Izquierdo and J. Palma and A. Troncoso},

url = {https://link.springer.com/article/10.1007/s13201-023-02072-4},

doi = {https://doi.org/10.1007/s13201-023-02072-4},

year  = {2024},

date = {2024-01-12},

journal = {Applied Water Science},

volume = {14},

pages = {1-14},

abstract = {The time series analysis and prediction techniques are highly valued in many application felds, such as economy, medicine and biology, environmental sciences or meteorology, among others. In the last years, there is a growing interest in the sustainable and optimal management of a resource as scarce as essential: the water. Forecasting techniques for water management can be used for diferent time horizons from the planning of constructions that can respond to long-term needs, to the detection of anomalies in the operation of facilities or the optimization of the operation in the short and medium term. In this paper, a deep neural network is specifcally designed to predict water consumption in the short-term. Results are reported using the time series of water consumption for a year and a half measured with 10-min frequency in the city of Murcia, the seventh largest city in Spain by number of inhabitants. The results are compared with K Nearest Neighbors, Random Forest, Extreme Gradient Boosting, Seasonal Autoregressive Integrated Moving Average and two persistence models as naive methods, showing the proposed deep learning model the most accurate results.},

keywords = {deep learning, forecasting, time series},

pubstate = {published},

tppubtype = {article}

}

@article{MARTINEZ24,

title = {Emerging trends in big data analytics and natural disasters (Editorial)},

author = {F. Martínez-Álvarez and R. Scitovski and C. Rubio-Escudero and A. Morales-Esteban},

url = {https://www.sciencedirect.com/science/article/pii/S0098300423001693},

doi = {https://doi.org/10.1016/j.cageo.2023.105465},

year  = {2024},

date = {2024-01-01},

journal = {Computers and Geosciences},

volume = {182},

pages = {105465},

keywords = {big data, natural disasters, time series},

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{morales2024machine,

title = {Machine learning for electric energy consumption forecasting: Application to the Paraguayan system},

author = { F. Morales-Mareco and M. García-Torres and F. Divina and D. H Stalder and C. Sauer},

url = {https://academic.oup.com/jigpal/advance-article-abstract/doi/10.1093/jigpal/jzae035/7639120},

doi = {10.1093/jigpal/jzae035},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Logic Journal of the IGPL},

pages = {jzae035},

publisher = {Oxford University Press},

abstract = {In this paper we address the problem of short-term 

electric energy prediction using a time series forecasting approach 

applied to data generated by a Paraguayan electricity distribution 

provider. The dataset used in this work contains data collected over a 

three-year period. This is the first time that these data have been 

used; therefore, a preprocessing phase of the data was also performed. 

In particular, we propose a comparative study of various machine 

learning and statistical strategies with the objective of predicting the 

electric energy consumption for a given prediction horizon, in our case 

seven days, using historical data. In this paper we have tested the 

effectiveness of the techniques with different historical window sizes. 

Specifically, we considered two ensemble strategies, a neural network, a 

deep learning technique and linear regression. Moreover, in this study, 

we tested whether the inclusion of meteorological data can help achieve 

better predictions. In particular, we considered data regarding 

temperature, humidity, wind speed and atmospheric pressure registered 

during the three-year period of data collection. The results show that, 

in general, the deep learning approach obtains the best results and that 

such results are obtained when meteorological data are also considered. 

Moreover, when meteorological data is used, a smaller historical window 

size is required to obtain precise predictions.},

keywords = {energy},

pubstate = {published},

tppubtype = {article}

}

@article{sosa2024feature,

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  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

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

volume = {17},

number = {2},

pages = {139–151},

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{divina2024stacking,

title = {A stacking ensemble learning for Iberian pigs activity prediction: a time series forecasting approach},

author = { F. Divina and M. García-Torres and F. Gómez-Vela and D. S. Rodriguez-Baena},

url = {https://www.aimspress.com/article/doi/10.3934/math.2024652},

doi = {10.3934/math.2024652},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {AIMS Mathematics},

volume = {9},

number = {5},

pages = {13358–13384},

abstract = {Automatic determination of abnormal animal activities can 

be helpful for the timely detection of signs of health and welfare 

problems. Usually, this problem is addressed as a classification 

problem, which typically requires manual annotation of behaviors. This 

manual annotation can introduce noise into the data and may not always 

be possible. This motivated us to address the problem as a time-series 

forecasting problem in which the activity of an animal can be predicted. 

In this work, different machine learning techniques were tested to 

obtain activity patterns for Iberian pigs. In particular, we propose a 

novel stacking ensemble learning approach that combines base learners 

with meta-learners to obtain the final predictive model. Results confirm 

the superior performance of the proposed method relative to the other 

tested strategies. We also explored the possibility of using predictive 

models trained on an animal to predict the activity of different animals 

on the same farm. As expected, the predictive performance degrades in 

this case, but it remains acceptable. The proposed method could be 

integrated into a monitoring system that may have the potential to 

transform the way farm animals are monitored, improving their health and 

welfare conditions, for example, by allowing the early detection of a 

possible health problem.},

keywords = {time series},

pubstate = {published},

tppubtype = {article}

}

@article{ESWA2024,

title = {Medium-term water consumption forecasting based on deep neural networks},

author = {A. Gil-Gamboa and P. Paneque and O. Trull and A. Troncoso},

url = {https://www.sciencedirect.com/science/article/pii/S095741742400099X},

doi = {10.1016/j.eswa.2024.123234},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Expert Systems With Applications},

volume = {247},

pages = {123234},

abstract = {Water consumption forecasting is an essential tool for water management, as it allows for efficient planning and allocation of water resources, an undervalued but indispensable resource for all living beings. With the increasing demand for accurate and timely water forecasting, traditional forecasting methods are proving to be insufficient. Deep learning techniques, which have shown remarkable performance in a wide range of applications, offer a promising approach to address the challenges of water consumption forecasting. In this work, the use of deep learning models for medium-term water consumption forecasting of residential areas is explored. A deep feed-forward neural network is developed to predict water consumption of a company’s customers for the next quarter. First, customers are grouped according to their consumption as these customers include both household consumers and special consumers such as public swimming pools, sports halls or small industries. Then, a deep feed-forward neural network is designed for household customers by obtaining the optimal values for those hyperparameters that have a great influence on the network performance. Results are reported using a real-world dataset composed of the water consumption from 1999 to 2015 on a quarterly basis, corresponding to 3262 clients of a water supply company. Finally, the proposed algorithm is evaluated by comparing it with other reference algorithms including an LSTM network.},

keywords = {deep learning, forecasting, time series},

pubstate = {published},

tppubtype = {article}

}

@article{AIMS_Math2024,

title = {Special issue on Advances in Time Series Forecasting},

author = {J. F. Torres and M. Martinez-Ballesteros and A. Troncoso and F. Martínez-Álvarez},

url = {https://www.aimspress.com/article/doi/10.3934/math.20241174},

doi = {10.3934/math.20241174},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {AIMS Mathematics},

volume = {9},

issue = {9},

pages = {24163-24165},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Melgar2024,

title = {A novel incremental ensemble learning for real-time explainable forecasting of electricity price},

author = {L. Melgar-García and A. Troncoso},

url = {https://www.sciencedirect.com/science/article/pii/S0950705124012085},

doi = {https://doi.org/10.1016/j.knosys.2024.112574},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Knowledge-Based Systems},

volume = {305},

pages = {112574},

keywords = {energy, IoT, time series, XAI},

pubstate = {published},

tppubtype = {article}

}

@article{corthis2024effective,

title = {Effective Identification and Authentication of Healthcare IoT Using Fog Computing with Hybrid Cryptographic Algorithm},

author = {P. B. Corthis and G. P. Ramesh and M. García-Torres and R. Ruiz},

doi = {10.3390/sym16060726},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Symmetry},

volume = {16},

number = {6},

pages = {726},

publisher = {MDPI},

abstract = {Currently, Internet of Things (IoT)-based cloud systems face several problems such as privacy leakage, failure in centralized operation, managing IoT devices, and malicious attacks. The data transmission 

between the cloud and healthcare IoT needs trust and secure transmission of Electronic Health Records (EHRs). IoT-enabled healthcare equipment is seen in hospitals that have been implementing the technology for many 

 years. Nonetheless, medical agencies fail to consider the security risk associated with healthcare IoT devices, which are readily compromised and cause potential threats to authentication and encryption procedures. 

 Existing cloud computing methods like homomorphic encryption and the elliptic curve cryptography are unable to meet the security, identity, authentication, and security needs of healthcare IoT devices. The 

majority of conventional healthcare IoT algorithms lack secure data transmission. Therefore, fog computing is introduced to overcome the problems of IoT device verification, authentication, and identification 

for scalable and secure transmission of data. In this research manuscript, fog computing includes a hybrid mathematical model: Elliptic Curve Cryptography (ECC) and Proxy Re-encryption (PR) with Enhanced 

Salp Swarm Algorithm (ESSA) for IoT device verification, identification, and authentication of EHRs. ESSA is incorporated into the PR algorithm to determine the optimal key size and parameters of the PR algorithm. 

Specifically, in the ESSA, a Whale Optimization Algorithm (WOA) is integrated with the conventional Salp Swarm Algorithm (SSA) to enhance its global and local search processes. The primary objective of the 

proposed mathematical model is to further secure data sharing in the real time services. The extensive experimental analysis shows that the proposed model approximately reduced 60 Milliseconds (ms) to 18 

milliseconds of processing time and improved 25% to 3% of reliability, compared to the traditional cryptographic algorithms. Additionally, the proposed model obtains a communication cost of 4260 bits with a memory 

usage of 680 bytes in the context of security analysis. url = https://www.mdpi.com/2073-8994/16/6/726},

keywords = {IoT},

pubstate = {published},

tppubtype = {article}

}

@article{10.1093/bfgp/elae006,

title = {ASACO: Automatic and Serial Analysis of CO-expression to discover gene modifiers with potential use in drug repurposing},

author = {C. Moral-Turón an G. Asencio-Cortés and F. Rodriguez-Diaz and A. Rubio and A. G. Navarro and A. M. Brokate-Llanos and A. Garzón and M. J. Muñoz and A. J. Pérez-Pulido},

url = {https://doi.org/10.1093/bfgp/elae006},

doi = {10.1093/bfgp/elae006},

issn = {2041-2657},

year  = {2024},

date = {2024-01-01},

journal = {Briefings in Functional Genomics},

volume = {23},

number = {4},

pages = {484-494},

abstract = {Massive gene expression analyses are widely used to find differentially expressed genes under specific conditions. The results of these experiments are often available in public databases that are undergoing a growth similar to that of molecular sequence databases in the past. This now allows novel secondary computational tools to emerge that use such information to gain new knowledge. If several genes have a similar expression profile across heterogeneous transcriptomics experiments, they could be functionally related. These associations are usually useful for the annotation of uncharacterized genes. In addition, the search for genes with opposite expression profiles is useful for finding negative regulators and proposing inhibitory compounds in drug repurposing projects. Here we present a new web application, Automatic and Serial Analysis of CO-expression (ASACO), which has the potential to discover positive and negative correlator genes to a given query gene, based on thousands of public transcriptomics experiments. In addition, examples of use are presented, comparing with previous contrasted knowledge. The results obtained propose ASACO as a useful tool to improve knowledge about genes associated with human diseases and noncoding genes. ASACO is available at http://www.bioinfocabd.upo.es/asaco/.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{JIMENEZ-NAVARRO23a,

title = {From Simple to Complex: A Sequential Method for Enhancing Time Series Forecasting with Deep Learning},

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

url = {https://academic.oup.com/jigpal/advance-article/doi/10.1093/jigpal/jzae030/7670726},

doi = {10.1093/jigpal/jzae030},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Logic Journal of the IGPL},

volume = {32},

number = {6},

pages = {986-1003},

abstract = {Time series forecasting is a well-known deep learning application field in which previous data are used to predict the future behavior of the series. Recently, several deep learning approaches have been proposed in which several nonlinear functions are applied to the input to obtain the output. In this paper, we introduce a novel method to improve the performance of deep learning models in time series forecasting. This method divides the model into hierarchies or levels from simpler to more complex ones. Simpler levels handle smoothed versions of the input, whereas the most complex level processes the original time series. This method follows the human learning process where general/simpler tasks are performed first, and afterward, more precise/harder ones are accomplished.Our proposed methodology has been applied to the LSTM architecture, showing remarkable performance in various time series. In addition, a comparison is reported including a standard LSTM and novel methods such as DeepAR, Temporal Fusion Transformer (TFT), NBEATS and Echo State Network (ESN).},

keywords = {deep learning, time series},

pubstate = {published},

tppubtype = {article}

}

@article{TRONCOSO-GARCIA23b,

title = {Explainable hybrid deep learning and Coronavirus Optimization Algorithm for improving evapotranspiration forecasting},

author = {A. R. Troncoso-García and I. S. Brito and A. Troncoso and F. Mártinez-Álvarez},

url = {https://www.sciencedirect.com/science/article/pii/S0168169923007755},

doi = {https://doi.org/10.1016/j.compag.2023.108387},

year  = {2023},

date = {2023-11-08},

journal = {Computers and Electronics in Agriculture},

volume = {215},

pages = {108387},

abstract = {Reference evapotranspiration is a critical hydrological measurement closely associated with agriculture. Accurate forecasting is vital in effective water management and crop planning in sustainable agriculture. In this study, the future values of reference evapotranspiration are forecasted by applying a recurrent long shortterm memory neural network optimized using the Coronavirus Optimization Algorithm, a novel bioinspired metaheuristic based on the spread of COVID-19. The input data is sourced from the Sistema Agrometeorológico para a Gestão da Rega no Alentejo, in Portugal, with meteorological data such as air temperature or wind speed. Several baseline models are applied to the same problem to facilitate comparisons, including support vector machines, multi-layer perceptron, Lasso and decision tree. The results demonstrate the successful forecasting performance of the proposed model and its potential in this field. In turn, to gain deeper insights into the model’s inner workings, the SHapley Additive exPlanation tool is applied for explainability. Consequently, the study identifies the most relevant variables for reference evapotranspiration forecasting, including previously measured evapotranspiration values. Additionally, a univariable model is tested using historic evapotranspiration values as input, offering a comparable performance with a considerable reduction of computational time},

keywords = {deep learning, forecasting, precision agriculture, XAI},

pubstate = {published},

tppubtype = {article}

}