Publication: Surrogate-assisted and filter-based multi-objective evolutionary feature selection for deep learning
Loading...
Date
2023-01-12
Authors
Espinosa Fernández, Raquel ; Jiménez Barrionuevo, Fernando ; Palma Méndez, José Tomás
item.page.secondaryauthor
item.page.director
Publisher
Institute of Electrical and Electronics Engineers
publication.page.editor
publication.page.department
DOI
https://doi.org/10.1109/TNNLS.2023.3234629
item.page.type
info:eu-repo/semantics/article
Description
© 2023, Publishers. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/
This document is the Accepted version of a Published Work that appeared in final form in IEEE Transactions on Neural Networks and Learning Systems.
To access the final edited and published work see https://doi.org/10.1109/TNNLS.2023.3234629
Abstract
Feature selection for deep learning prediction mod- els is a difficult topic for researchers to tackle. Most of the ap- proaches 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 paper, we propose new attribute subset evaluation feature selection methods for deep learning of the wrapper, filter and wrapper-filter hybrid types, where multi-objective 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 feature se
publication.page.subject
Citation
IEEE Transactions on Neural Networks and Learning Systems
item.page.embargo
Collections
Ir a Estadísticas
Este ítem está sujeto a una licencia Creative Commons. http://creativecommons.org/licenses/by-nc-nd/4.0/