A multi-hierarchical attention-based prediction method on time series with spatio-temporal context among variables

DOI10.1016/j.physa.2022.127664OpenAlexW4281688916MaRDI QIDQ2162223

Ling-Yu Xu, Bao-Gang Jin, Jie Yu, Xiaolin Zhang, Zhuolin Li

Publication date: 5 August 2022

Published in: Physica A (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.physa.2022.127664

zbMATH Keywords

time series predictiondeep learningattention mechanismmulti-type variablesspatio-temporal context

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Uses Software

• Adam
• TPA-LSTM
• Faster R-CNN

Cites Work

• Unnamed Item
• Temporal pattern attention for multivariate time series forecasting
• A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
• A Reduced-Order Kalman Filter for Data Assimilation in Physical Oceanography

This page was built for publication: A multi-hierarchical attention-based prediction method on time series with spatio-temporal context among variables