https://hdl.handle.net/20.500.12412/2548 2026-04-25T09:43:29Z 2026-04-25T09:43:29Z Becerra Alonso, David Carbonero Ruz, Mariano Martínez Estudillo, Francisco José Martínez Estudillo, Alfonso Carlos https://hdl.handle.net/20.500.12412/7194 2026-04-17T21:00:25Z 2011-01-01T00:00:00Z

A Hybrid Evolutionary Approach to Obtain Better Quality Classifiers Becerra Alonso, David; Carbonero Ruz, Mariano; Martínez Estudillo, Francisco José; Martínez Estudillo, Alfonso Carlos We present an extra measurement for classifiers, responding to the need to evaluate them with more than accuracy alone. This measure should be able to express, at least to some degree, the extent to which all classes are taken into account in a classification problem. In this communication we propose sensitivity dispersion (being as it is, the associated statistical dispersion measurement of accuracy), as the appropriate measure to have a more complete evaluation of the quality of classifiers. We use the Evolutionary Extreme Learning Machine algorithm, with a specific fitness function to optimize both measures simultaneously, and we compare it with other classifiers

2011-01-01T00:00:00Z Becerra Alonso, David Carbonero Ruz, Mariano Martínez Estudillo, Francisco José Martínez Estudillo, Alfonso Carlos https://hdl.handle.net/20.500.12412/7192 2026-04-17T21:00:30Z 2012-01-01T00:00:00Z

Evolutionary Extreme Learning Machine for Ordinal Regression Becerra Alonso, David; Carbonero Ruz, Mariano; Martínez Estudillo, Francisco José; Martínez Estudillo, Alfonso Carlos This paper presents a novel method for generally adapting ordinal classification models. We essentially rely on the assumption that the ordinal structure of the set of class labels is also reflected in the topology of the instance space. Under this assumption, this paper proposes an algorithm in two phases that takes advantage of the ordinal structure of the dataset and tries to translate this ordinal structure in the total ordered real line and then to rank the patterns of the dataset. The first phase makes a projection of the ordinal structure of the feature space. Next, an evolutionary algorithm tunes the first projection working with the misclassified patterns near the border of their right class. The results obtained in seven ordinal datasets are competitive in comparison with state-of-the-art algorithms in ordinal regression, but with much less computational time in datasets with many patterns.

2012-01-01T00:00:00Z Galnares Jiménez-Placer, Carlos Martínez Estudillo, Alfonso Carlos Carbonero Ruz, Mariano Campoy Muñoz, María Del Pilar https://hdl.handle.net/20.500.12412/7183 2026-04-16T21:00:30Z 2022-06-06T00:00:00Z

Revisiting the determinants of sovereign debt ratings in Europe through artificial intelligence techniques Galnares Jiménez-Placer, Carlos; Martínez Estudillo, Alfonso Carlos; Carbonero Ruz, Mariano; Campoy Muñoz, María Del Pilar In papers using artificial intelligence (AI) techniques, little attention has been paid to the determinants of sovereign debt ratings. We propose a reduced set of variables regarding the economic performance of a country that are consistent with the idea of debt sustainability. The robustness of this set is supported by the results obtained with different well-known AI techniques using data from EU-15 countries during the 2002–2017 period as the experimental setting. The variables are publicly available, allowing a quick and reliable assessment of the creditworthiness of a sovereign and providing useful information for decision-makers and investors.

2022-06-06T00:00:00Z Durán-Rosal, Antonio Manuel Hervás Martínez, César Tallón-Ballesteros, A.J. Martínez Estudillo, Alfonso Carlos Salcedo-Sanz, S. https://hdl.handle.net/20.500.12412/7182 2026-04-16T21:00:24Z 2016-05-01T00:00:00Z

Massive missing data reconstruction in ocean buoys with evolutionary product unit neural networks Durán-Rosal, Antonio Manuel; Hervás Martínez, César; Tallón-Ballesteros, A.J.; Martínez Estudillo, Alfonso Carlos; Salcedo-Sanz, S. In this paper we tackle the problem of massive missing data reconstruction in ocean buoys, with a Evolutionary Product Unit Neural Network (EPUNN). When considering a large number of buoys to reconstruct missing data, it is sometimes di cult to nd a common period of completeness (without missing data on it) in the data to form a proper training and test set. In this paper we solve this issue by using partial reconstruction, which are then used as inputs of the EPUNN, with linear models. Missing data reconstruction in several phases or steps is then proposed. In this work we also show the potential of EPUNN to obtain simple, interpretable models in spite of the non-linear characteristic of the network, much simpler than the commonly used sigmoid-based neural systems. In the experimental section of the paper we show the performance of the proposed approach in a real case of massive missing data reconstruction in 6 wave-rider buoys at the Gulf of Alaska.; Es la versión aceptada del artículo. Se puede consultar la versión final en https://doi.org/10.1016/j.oceaneng.2016.03.053

2016-05-01T00:00:00Z