A Neural Networks Based Method for Multivariate Time-Series Forecasting
文献类型：期刊论文
| 作者 | Li, Shaowei1,2; Huang, He1 ; Lu, Wei2
|
| 刊名 | IEEE ACCESS
 |
| 出版日期 | 2021 |
| 卷号 | 9 |
| 关键词 | Time series analysis Data models Predictive models Neural networks Forecasting Computational modeling Recurrent neural networks Multivariate time series autoregressive models convolutional neural network recurrent neural network |
| ISSN号 | 2169-3536 |
| DOI | 10.1109/ACCESS.2021.3075063 |
| 通讯作者 | Huang, He(hhuang@iim.ac.cn) |
| 英文摘要 | In recent years, more and more deep neural network methods have been used in the forecasting research of multivariate time series. Comparing to the traditional methods such as autoregressive models, methods based on neural networks have achieved superior results. However, the sequence data comes from all aspects, and the data contains long-term and short-term models, which is not a small challenge for data prediction research. We builds a model based on a deep neural network, and uses a convolutional network and a recurrent network in the long-term sequence data input and short-term sequence data input of the model. Convolutional networks are mainly used to extract short-term patterns in sequence data, and recurrent networks are mainly used to extract long-term patterns in sequence data. In addition, in order to solve the problem that the output of the neural network is not sensitive to the change of the input scale, we also added an autoregressive network to the model. When constructing the input of the model, we use the corresponding period characteristics to construct the two input of the model for different datasets: long-term historical data and short-term historical data. Our model has achieved better results than traditional prediction models on four public data sets: out of 32 indicators in 8 methods, 24 optimal results have been achieved. |
| WOS研究方向 | Computer Science ; Engineering ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:000645844900001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/121696]  |
| 专题 | 中国科学院合肥物质科学研究院 |
| 通讯作者 | Huang, He |
| 作者单位 | 1.Chinese Acad Sci, Inst Intelligent Machines, Hefei 230088, Peoples R China 2.Anhui Univ, Inst Phys Sci & Informat Technol, Hefei 230039, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Shaowei,Huang, He,Lu, Wei. A Neural Networks Based Method for Multivariate Time-Series Forecasting[J]. IEEE ACCESS,2021,9. |
| APA | Li, Shaowei,Huang, He,&Lu, Wei.(2021).A Neural Networks Based Method for Multivariate Time-Series Forecasting.IEEE ACCESS,9. |
| MLA | Li, Shaowei,et al."A Neural Networks Based Method for Multivariate Time-Series Forecasting".IEEE ACCESS 9(2021). |
入库方式： OAI收割
来源：合肥物质科学研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。