A Novel Approach to Time Series Forecasting using Deep Learning and Linear Model
-
- Hirata Takaomi
- Graduate School of Science and Engineering, University of Yamaguchi
-
- Kuremoto Takashi
- Graduate School of Science and Engineering, University of Yamaguchi
-
- Obayashi Masanao
- Graduate School of Science and Engineering, University of Yamaguchi
-
- Mabu Shingo
- Graduate School of Science and Engineering, University of Yamaguchi
-
- Kobayashi Kunikazu
- School of Information Science & Technology, Aichi Prefectural University
Bibliographic Information
- Other Title
-
- 深層学習と線形モデルを併用した時系列予測手法
- シンソウ ガクシュウ ト センケイ モデル オ ヘイヨウ シタ ジケイレツ ヨソク シュホウ
Search this article
Abstract
Since 1970s, linear models such as autoregressive (AR), moving average (MA), autoregressive integrated moving average (ARIMA), etc. have been popular for time series data analyze and prediction. Meanwhile, artificial neural networks (ANNs), inspired by connectionism bio-informatics, have been showing their powerful abilities of function approximation, pattern recognition, dimensionality reduction, and so on since 1980s. Recently, deep belief nets (DBNs) which use multiple restricted Boltzmann machines (RBMs) and multi-layered perceptron (MLP) are proposed as time series predictors. In this study, a hybrid prediction method using DBNs and ARIMA is proposed. The effectiveness of the proposed method was confirmed by the experiments using CATS benchmark data and chaotic time series data.
Journal
-
- IEEJ Transactions on Electronics, Information and Systems
-
IEEJ Transactions on Electronics, Information and Systems 136 (3), 348-356, 2016
The Institute of Electrical Engineers of Japan
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282679584540800
-
- NII Article ID
- 130005132289
-
- NII Book ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL BIB ID
- 027160219
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed