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

References(12)*help

See more

Related Projects

See more

Details 詳細情報について

Report a problem

Back to top