DWNet: Dual-Window Deep Neural Network for Time Series Prediction
Multivariate time series prediction is a very important task, which plays a huge role in climate, economy, and other fields. We usually use an Attention-based Encoder-Decoder network to deal with multivariate time series prediction because the attention mechanism makes it easier for the model to foc...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/1125630 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832561503191957504 |
|---|---|
| author | Jin Fan Yipan Huang Ke Zhang Sen Wang Jinhua Chen Baiping Chen |
| author_facet | Jin Fan Yipan Huang Ke Zhang Sen Wang Jinhua Chen Baiping Chen |
| author_sort | Jin Fan |
| collection | DOAJ |
| description | Multivariate time series prediction is a very important task, which plays a huge role in climate, economy, and other fields. We usually use an Attention-based Encoder-Decoder network to deal with multivariate time series prediction because the attention mechanism makes it easier for the model to focus on the really important attributes. However, the Encoder-Decoder network has the problem that the longer the length of the sequence is, the worse the prediction accuracy is, which means that the Encoder-Decoder network cannot process long series and therefore cannot obtain detailed historical information. In this paper, we propose a dual-window deep neural network (DWNet) to predict time series. The dual-window mechanism allows the model to mine multigranularity dependencies of time series, such as local information obtained from a short sequence and global information obtained from a long sequence. Our model outperforms nine baseline methods in four different datasets. |
| format | Article |
| id | doaj-art-74c8143795e04335ac291a16dcba2407 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-74c8143795e04335ac291a16dcba24072025-02-03T01:24:48ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/11256301125630DWNet: Dual-Window Deep Neural Network for Time Series PredictionJin Fan0Yipan Huang1Ke Zhang2Sen Wang3Jinhua Chen4Baiping Chen5Hangzhou Dianzi University, Hangzhou, ChinaHangzhou Dianzi University, Hangzhou, ChinaHangzhou Dianzi University, Hangzhou, ChinaHangzhou Dianzi University, Hangzhou, ChinaHangzhou Dianzi University, Hangzhou, ChinaHangzhou Dianzi University, Hangzhou, ChinaMultivariate time series prediction is a very important task, which plays a huge role in climate, economy, and other fields. We usually use an Attention-based Encoder-Decoder network to deal with multivariate time series prediction because the attention mechanism makes it easier for the model to focus on the really important attributes. However, the Encoder-Decoder network has the problem that the longer the length of the sequence is, the worse the prediction accuracy is, which means that the Encoder-Decoder network cannot process long series and therefore cannot obtain detailed historical information. In this paper, we propose a dual-window deep neural network (DWNet) to predict time series. The dual-window mechanism allows the model to mine multigranularity dependencies of time series, such as local information obtained from a short sequence and global information obtained from a long sequence. Our model outperforms nine baseline methods in four different datasets.http://dx.doi.org/10.1155/2021/1125630 |
| spellingShingle | Jin Fan Yipan Huang Ke Zhang Sen Wang Jinhua Chen Baiping Chen DWNet: Dual-Window Deep Neural Network for Time Series Prediction Complexity |
| title | DWNet: Dual-Window Deep Neural Network for Time Series Prediction |
| title_full | DWNet: Dual-Window Deep Neural Network for Time Series Prediction |
| title_fullStr | DWNet: Dual-Window Deep Neural Network for Time Series Prediction |
| title_full_unstemmed | DWNet: Dual-Window Deep Neural Network for Time Series Prediction |
| title_short | DWNet: Dual-Window Deep Neural Network for Time Series Prediction |
| title_sort | dwnet dual window deep neural network for time series prediction |
| url | http://dx.doi.org/10.1155/2021/1125630 |
| work_keys_str_mv | AT jinfan dwnetdualwindowdeepneuralnetworkfortimeseriesprediction AT yipanhuang dwnetdualwindowdeepneuralnetworkfortimeseriesprediction AT kezhang dwnetdualwindowdeepneuralnetworkfortimeseriesprediction AT senwang dwnetdualwindowdeepneuralnetworkfortimeseriesprediction AT jinhuachen dwnetdualwindowdeepneuralnetworkfortimeseriesprediction AT baipingchen dwnetdualwindowdeepneuralnetworkfortimeseriesprediction |