Rafael Ayllón-Gavilán
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rafael Ayllón-Gavilán has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Pedro Antonio Gutiérrez
Universidad de Córdoba
12 shared publications - David Guijo-Rubio
Universidad de Córdoba
10 shared publications - César Hervás-Martínez
Universidad de Córdoba
9 shared publications - Víctor Manuel Vargas
Universidad de Alcalà
5 shared publications - Antonio Manuel Gómez Orellana
Department of Computer Science and Artificial Intelligence Universidad de Córdoba Córdoba Spain
4 shared publications - Jorge Pérez-Aracil
University of Alcalá
2 shared publications
Latest Publications
- Open Access
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (7) , 4722-4741
Soft Labelling for Deep Ordinal Classification: An Experimental Review
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (7) , 4722-4741
Open AccessSoft Labelling for Deep Ordinal Classification: An Experimental Review
- Open Access
- 2 April 2026
- Published by Elsevier in Neurocomputing
- Vol. 684
TOC-UCO: a comprehensive repository of tabular ordinal classification datasets
- 2 April 2026
- Published by Elsevier in Neurocomputing
- Vol. 684
Open AccessTOC-UCO: a comprehensive repository of tabular ordinal classification datasets
- Open Access
- 31 March 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 197
Ordinal evolutionary artificial neural networks for predicting diabetic nephropathy progression
- 31 March 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 197
Open AccessOrdinal evolutionary artificial neural networks for predicting diabetic nephropathy progression
- Open Access
- 13 August 2025
- Published by Elsevier in Pattern Recognition
- Vol. 171
Splitting criteria for ordinal decision trees: An experimental study
- 13 August 2025
- Published by Elsevier in Pattern Recognition
- Vol. 171
Open AccessSplitting criteria for ordinal decision trees: An experimental study
- 15 May 2025
- Published by SAGE Publications in Integrated Computer-Aided Engineering
- Vol. 32 (4) , 366-378
Simultaneous multi-step wind speed prediction on multiple farms using multi-task deep learning
In this paper, we present the MUSONet model, which leverages information from different sources (in this case, wind farms) to perform a multi-step wind speed prediction. The main goal of this approach is improving the global prediction accuracy, specifically at longer prediction horizons. Thus, the proposed model is able to simultaneously predict the wind speed at three different prediction horizons ( 6 h, 12 h, and 24 h), across three different wind farms located in Spain. We also evaluate the performance of the presented methodology by considering three different activation functions for hidden neurons in the neural network: Sigmoid, ReLU, and ELUs+2L. The results show that the proposed multi-source approach improves the performance of the single-source counterpart for the longer prediction horizons ( 12 h and 24 h). In addition, the proposed multi-source method reduces by over 30 % the number of parameters compared to three single-source models (in this case, one model per wind farm), resulting in a simpler solution for the problem addressed and requiring much lower computational resources.
- 15 May 2025
- Published by SAGE Publications in Integrated Computer-Aided Engineering
- Vol. 32 (4) , 366-378
Simultaneous multi-step wind speed prediction on multiple farms using multi-task deep learning
In this paper, we present the MUSONet model, which leverages information from different sources (in this case, wind farms) to perform a multi-step wind speed prediction. The main goal of this approach is improving the global prediction accuracy, specifically at longer prediction horizons. Thus, the proposed model is able to simultaneously predict the wind speed at three different prediction horizons ( 6 h, 12 h, and 24 h), across three different wind farms located in Spain. We also evaluate the performance of the presented methodology by considering three different activation functions for hidden neurons in the neural network: Sigmoid, ReLU, and ELUs+2L. The results show that the proposed multi-source approach improves the performance of the single-source counterpart for the longer prediction horizons ( 12 h and 24 h). In addition, the proposed multi-source method reduces by over 30 % the number of parameters compared to three single-source models (in this case, one model per wind farm), resulting in a simpler solution for the problem addressed and requiring much lower computational resources.
- Open Access
- 1 January 2025
- Published by Elsevier in Neurocomputing
- Vol. 622
dlordinal: A Python package for deep ordinal classification
- 1 January 2025
- Published by Elsevier in Neurocomputing
- Vol. 622
Open Accessdlordinal: A Python package for deep ordinal classification
- Open Access
- 27 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 55 (2) , 537-549
Convolutional- and Deep Learning-Based Techniques for Time Series Ordinal Classification
Time-series classification (TSC) covers the supervised learning problem where input data is provided in the form of series of values observed through repeated measurements over time, and whose objective is to predict the category to which they belong. When the class values are ordinal, classifiers that take this into account can perform better than nominal classifiers. Time-series ordinal classification (TSOC) is the field bridging this gap, yet unexplored in the literature. There are a wide range of time-series problems showing an ordered label structure, and TSC techniques that ignore the order relationship discard useful information. Hence, this article presents the first benchmarking of TSOC methodologies, exploiting the ordering of the target labels to boost the performance of current TSC state of the art. Both convolutional-and deep-learning-based methodologies (among the best performing alternatives for nominal TSC) are adapted for TSOC. For the experiments, a selection of $29$ ordinal problems has been made. In this way, this article contributes to the establishment of the state of the art in TSOC. The results obtained by ordinal versions are found to be significantly better than current nominal TSC techniques in terms of ordinal performance metrics, outlining the importance of considering the ordering of the labels when dealing with this kind of problems.
- 27 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 55 (2) , 537-549
Open AccessConvolutional- and Deep Learning-Based Techniques for Time Series Ordinal Classification
Time-series classification (TSC) covers the supervised learning problem where input data is provided in the form of series of values observed through repeated measurements over time, and whose objective is to predict the category to which they belong. When the class values are ordinal, classifiers that take this into account can perform better than nominal classifiers. Time-series ordinal classification (TSOC) is the field bridging this gap, yet unexplored in the literature. There are a wide range of time-series problems showing an ordered label structure, and TSC techniques that ignore the order relationship discard useful information. Hence, this article presents the first benchmarking of TSOC methodologies, exploiting the ordering of the target labels to boost the performance of current TSC state of the art. Both convolutional-and deep-learning-based methodologies (among the best performing alternatives for nominal TSC) are adapted for TSOC. For the experiments, a selection of $29$ ordinal problems has been made. In this way, this article contributes to the establishment of the state of the art in TSOC. The results obtained by ordinal versions are found to be significantly better than current nominal TSC techniques in terms of ordinal performance metrics, outlining the importance of considering the ordering of the labels when dealing with this kind of problems.
- 12 June 2024
- Published by Springer Nature
- p. 50-60
O-Hydra: A Hybrid Convolutional and Dictionary-Based Approach to Time Series Ordinal Classification
- 12 June 2024
- Published by Springer Nature
- p. 50-60
O-Hydra: A Hybrid Convolutional and Dictionary-Based Approach to Time Series Ordinal Classification
- 12 June 2024
- Published by Springer Nature
- p. 223-232
Multivariate-Autoencoder Flow-Analogue Method for Heat Waves Reconstruction
- 12 June 2024
- Published by Springer Nature
- p. 223-232
Multivariate-Autoencoder Flow-Analogue Method for Heat Waves Reconstruction
- 1 October 2023
- Published by Springer Nature
- p. 505-516
Gramian Angular and Markov Transition Fields Applied to Time Series Ordinal Classification
- 1 October 2023
- Published by Springer Nature
- p. 505-516
Gramian Angular and Markov Transition Fields Applied to Time Series Ordinal Classification