An attention-based deep learning model for multi-horizon time series forecasting by considering periodic characteristic
Recently, transformer-based models have exhibited great performance in multi-horizon time series forecasting tasks. However, the core module of these models, the self-attention mechanism, is insensitive to the temporal order and suffers from attention dispersion over long time sequences. These limit...
保存先:
主要な著者: | Fang, Jin, Guo, Xin, Liu, Yujia, Chang, Xiaokun, Fujita, Hamido, Wu, Jian |
---|---|
フォーマット: | 論文 |
出版事項: |
Elsevier Ltd
2023
|
主題: | |
オンライン・アクセス: | http://eprints.utm.my/106425/ http://dx.doi.org/10.1016/j.cie.2023.109667 |
タグ: |
タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
|
類似資料
-
Multi-horizon ternary time series forecasting
著者:: Htike@Muhammad Yusof, Zaw Zaw
出版事項: (2013) -
Time horizon volatility forecasting of Malaysian property stocks
著者:: Gooi, Leong Mow
出版事項: (2019) -
Foreign exchange EURUSD forecasting: a time-series forecasting through periodic U.S. economic event announcements
著者:: Heng, Xin Peng, 等
出版事項: (2019) -
A Replenishment inventory model for items under time-varying demand rates considering trade credit period and cash discount for a finite time horizon
著者:: Mohd Omar,
出版事項: (2012) -
Attention gate guided multiscale recursive fusion strategy for deep neural network-based fault diagnosis
著者:: Zhang, Zhiqiang, 等
出版事項: (2023)