Deep Fusion Prediction Method for Nonstationary Time Series Based on Feature Augmentation and Extraction

Deep learning effectively identifies and predicts modes but faces performance reduction under few-shot learning conditions. In this paper, a time series prediction framework for small samples is proposed, including a data augmentation algorithm, time series trend decomposition, multi-model predictio...

Full description

Saved in:
Bibliographic Details
Published inApplied sciences Vol. 13; no. 8; p. 5088
Main Authors Zhang, Yu-Lei, Bai, Yu-Ting, Jin, Xue-Bo, Su, Ting-Li, Kong, Jian-Lei, Zheng, Wei-Zhen
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.04.2023
Subjects
covariance intersection fusion
Data augmentation
Datasets
Decomposition
Deep learning
feature decomposition
few-shot learning
Kalman filters
Machine learning
Neural networks
Parameter identification
Predictions
Statistical methods
Time series
time series prediction
Variables
China
Online AccessGet full text

Cover

More Information
Summary:Deep learning effectively identifies and predicts modes but faces performance reduction under few-shot learning conditions. In this paper, a time series prediction framework for small samples is proposed, including a data augmentation algorithm, time series trend decomposition, multi-model prediction, and error-based fusion. First, data samples are augmented by retaining and extracting time series features. Second, the expanded data are decomposed based on data trends, and then, multiple deep models are used for prediction. Third, the models’ predictive outputs are combined with an error estimate from the intersection of covariances. Finally, the method is verified using natural systems and classic small-scale simulation datasets. The results show that the proposed method can improve the prediction accuracy of small sample sets with data augmentation and multi-model fusion.
ISSN:2076-3417
2076-3417
DOI:10.3390/app13085088