@misc{10481/79524,
year = {2023},
month = {1},
url = {https://hdl.handle.net/10481/79524},
abstract = {The combination of convolutional and recurrent neural networks is a promising framework. This arrangement allows the extraction of high-quality spatio-temporal features together with their temporal dependencies. This fact is key for time series prediction problems such as forecasting, classification or anomaly detection, amongst others. In this paper, the TSFEDL library is introduced. It compiles 22 state-of-the-art methods for both time series feature extraction and prediction, employing convolutional and recurrent deep neural networks for its use in several data mining tasks. The library is built upon a set of Tensorflow + Keras and PyTorch modules under the AGPLv3 license. The performance validation of the architectures included in this proposal confirms the usefulness of this Python package.},
organization = {This work has been partially supported by the Contract UGRAM OTRI-4260 and the Regional Government of Andalusia, under the program ‘‘Personal Investigador Doctor”, reference DOC_00235. This work was also supported by project PID2020-119478 GB-I00 granted by Ministerio de Ciencia, Innovación y Universidades, and projects P18-FR-4961 and P18-FR-4262 by Proyectos I + D+i Junta de Andalucia 2018.},
publisher = {Neurocomputing},
keywords = {Time series},
keywords = {Deep learning},
keywords = {Python},
title = {TSFEDL: A python library for time series spatio-temporal feature extraction and prediction using deep learning},
doi = {https://doi.org/10.1016/j.neucom.2022.10.062},
author = {Aguilera Martos, Ignacio and García Vico, Ángel Miguel and Luengo Martín, Julián and Damas Arroyo, Sergio and Melero Rus, Francisco Javier and Valle-Alonso, José Javier and Herrera Triguero, Francisco},
}