Raquel Espinosa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Raquel Espinosa has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Fernando Jiménez
Department of Information and Communication Engineering, University of Murcia, 30100 Murcia, Spain
4 shared publications - José Palma
Departamento de Ingenieria de la Informacion y las Comunicaciones, Universidad de Murcia, Murcia, Spain.
3 shared publications José Palma
2 shared publicationsEstrella Lucena-Sánchez
1 shared publicationFernando Jiménez
1 shared publication- Gracia Sánchez
Department of Information and Communication Engineering, University of Murcia, 30100 Murcia, Spain
1 shared publication
Latest Publications
- Open Access
- 10 November 2025
- Published by Elsevier in Swarm and Evolutionary Computation
- Vol. 99
Multi-objective evolutionary feature selection for ensemble learning with random forests in time series forecasting
- 10 November 2025
- Published by Elsevier in Swarm and Evolutionary Computation
- Vol. 99
Open AccessMulti-objective evolutionary feature selection for ensemble learning with random forests in time series forecasting
- 12 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (7) , 9591-9605
Surrogate-Assisted and Filter-Based Multiobjective Evolutionary Feature Selection for Deep Learning
Feature selection (FS) for deep learning prediction models is a difficult topic for researchers to tackle. Most of the approaches proposed in the literature consist of embedded methods through the use of hidden layers added to the neural network architecture that modify the weights of the units associated with each input attribute so that the worst attributes have less weight in the learning process. Other approaches used for deep learning are filter methods, which are independent of the learning algorithm, which can limit the precision of the prediction model. Wrapper methods are impractical with deep learning due to their high computational cost. In this article, we propose new attribute subset evaluation FS methods for deep learning of the wrapper, filter and wrapper-filter hybrid types, where multiobjective and many-objective evolutionary algorithms are used as search strategies. A novel surrogate-assisted approach is used to reduce the high computational cost of the wrapper-type objective function, while the filter-type objective functions are based on correlation and an adaptation of the reliefF algorithm. The proposed techniques have been applied in a time series forecasting problem of air quality in the Spanish south-east and an indoor temperature forecasting problem in a domotic house, with promising results compared to other FS techniques used in the literature.
- 12 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (7) , 9591-9605
Surrogate-Assisted and Filter-Based Multiobjective Evolutionary Feature Selection for Deep Learning
Feature selection (FS) for deep learning prediction models is a difficult topic for researchers to tackle. Most of the approaches proposed in the literature consist of embedded methods through the use of hidden layers added to the neural network architecture that modify the weights of the units associated with each input attribute so that the worst attributes have less weight in the learning process. Other approaches used for deep learning are filter methods, which are independent of the learning algorithm, which can limit the precision of the prediction model. Wrapper methods are impractical with deep learning due to their high computational cost. In this article, we propose new attribute subset evaluation FS methods for deep learning of the wrapper, filter and wrapper-filter hybrid types, where multiobjective and many-objective evolutionary algorithms are used as search strategies. A novel surrogate-assisted approach is used to reduce the high computational cost of the wrapper-type objective function, while the filter-type objective functions are based on correlation and an adaptation of the reliefF algorithm. The proposed techniques have been applied in a time series forecasting problem of air quality in the Spanish south-east and an indoor temperature forecasting problem in a domotic house, with promising results compared to other FS techniques used in the literature.
- Open Access
- 31 May 2022
- Published by Elsevier in Future Generation Computer Systems
- Vol. 136, 15-33
Multi-objective evolutionary spatio-temporal forecasting of air pollution
- 31 May 2022
- Published by Elsevier in Future Generation Computer Systems
- Vol. 136, 15-33
Open AccessMulti-objective evolutionary spatio-temporal forecasting of air pollution
- Open Access
- 1 December 2021
- Published by Elsevier in Applied Soft Computing
- Vol. 113
A time series forecasting based multi-criteria methodology for air quality prediction
- 1 December 2021
- Published by Elsevier in Applied Soft Computing
- Vol. 113
Open AccessA time series forecasting based multi-criteria methodology for air quality prediction