RT Journal Article
T1 PHILNet: A novel efficient approach for time series forecasting using deep learning
A1 Jiménez Navarro, Manuel Jesús
A1 Martínez Ballesteros, María
A1 Martínez-Álvarez, Francisco
A1 Asencio Cortés, Gualberto
K1 Time series
K1 Forecasting
K1 Deep learning
K1 Efficiency
AB Time series is one of the most common data types in the industry nowadays. Forecasting the future of a time series behavior can be useful in planning ahead, saving time, resources, and helping avoid undesired scenarios. To make the forecasting, historical data is utilized due to the causal nature of the time series. Several deep learning algorithms have been presented in this area, where the input is processed through a series of non-linear functions to produce the output. We present a novel strategy to improve the performance of deep learning models in time series forecasting in terms of efficiency while reaching similar effectiveness. This approach separates the model into levels, starting with the easiest and continuing to the most difficult. The simpler levels deal with smoothed versions of the input, whereas the most sophisticated level deals with the raw data. This strategy seeks to mimic the human learning process, in which basic tasks are completed initially, followed by more precise and sophisticated ones. Our method achieved promising results, obtaining a 35% improvement in mean squared error and a 2.6 time decrease in training time compared with the best models found in a variety of time series.
PB Elsevier
YR 2023
FD 2023-03-15
LK https://hdl.handle.net/10433/19782
UL https://hdl.handle.net/10433/19782
LA en
NO Information Sciences, vol 632, p. 815–832
NO Data Science and Big Data Research Lab
DS RIO
RD May 4, 2026