Multivariate time series forecasting via attention-based encoder–decoder framework

Time series forecasting is an important technique to study the behavior of temporal data and forecast future values, which is widely applied in many fields, e.g. air quality forecasting, power load forecasting, medical monitoring, and intrusion detection. In this paper, we firstly propose a novel te...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Neurocomputing (Amsterdam) Ročník 388; s. 269 - 279
Hlavní autoři: Du, Shengdong, Li, Tianrui, Yang, Yan, Horng, Shi-Jinn
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 07.05.2020
Témata:
Deep learning
Encoder–decoder
Long short-term memory networks
Multi-step forecasting
Multivariate time series
Temporal attention
Temporal attention
Encoder–decoder
Deep learning
Multivariate time series
Long short-term memory networks
Multi-step forecasting
ISSN:0925-2312, 1872-8286
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Time series forecasting is an important technique to study the behavior of temporal data and forecast future values, which is widely applied in many fields, e.g. air quality forecasting, power load forecasting, medical monitoring, and intrusion detection. In this paper, we firstly propose a novel temporal attention encoder–decoder model to deal with the multivariate time series forecasting problem. It is an end-to-end deep learning structure that integrates the traditional encode context vector and temporal attention vector for jointly temporal representation learning, which is based on bi-directional long short-term memory networks (Bi-LSTM) layers with temporal attention mechanism as the encoder network to adaptively learning long-term dependency and hidden correlation features of multivariate temporal data. Extensive experimental results on five typical multivariate time series datasets showed that our model has the best forecasting performance compared with baseline methods.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2019.12.118