Two-dimensional attention-based multi-input LSTM for time series prediction
- Authors
- Kim, Eun Been; Park, Jung Hoon; Lee, Yung-Seop; Lim, Changwon
- Issue Date
- Jan-2021
- Publisher
- KOREAN STATISTICAL SOC
- Keywords
- recurrent neural network; correlation; attention; time series
- Citation
- COMMUNICATIONS FOR STATISTICAL APPLICATIONS AND METHODS, v.28, no.1, pp 39 - 57
- Pages
- 19
- Journal Title
- COMMUNICATIONS FOR STATISTICAL APPLICATIONS AND METHODS
- Volume
- 28
- Number
- 1
- Start Page
- 39
- End Page
- 57
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/48331
- DOI
- 10.29220/CSAM.2021.28.1.039
- ISSN
- 2287-7843
2383-4757
- Abstract
- Time series prediction is an area of great interest to many people. Algorithms for time series prediction are widely used in many fields such as stock price, temperature, energy and weather forecast; in addtion, classical models as well as recurrent neural networks (RNNs) have been actively developed. After introducing the attention mechanism to neural network models, many new models with improved performance have been developed; in addition, models using attention twice have also recently been proposed, resulting in further performance improvements. In this paper, we consider time series prediction by introducing attention twice to an RNN model. The proposed model is a method that introduces H-attention and T-attention for output value and time step information to select useful information. We conduct experiments on stock price, temperature and energy data and confirm that the proposed model outperforms existing models.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School > ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/48331)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.