深層学習と線形モデルを併用した時系列予測手法

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2016/03/01

タイトル(英語): A Novel Approach to Time Series Forecasting using Deep Learning and Linear Model

著者名: 平田　貴臣（山口大学大学院理工学研究科），呉本　尭（山口大学大学院理工学研究科），大林　正直（山口大学大学院理工学研究科），間普　真吾（山口大学大学院理工学研究科），小林　邦和（愛知県立大学情報科学部）

著者名(英語): Takaomi Hirata (Graduate School of Science and Engineering, University of Yamaguchi), Takashi Kuremoto (Graduate School of Science and Engineering, University of Yamaguchi), Masanao Obayashi (Graduate School of Science and Engineering, University of Yamaguchi), Shingo Mabu (Graduate School of Science and Engineering, University of Yamaguchi), Kunikazu Kobayashi (School of Information Science & Technology, Aichi Prefectural University)

キーワード: 深層学習，ニューラルネットワーク，時系列予測，ハイブリッド型予測モデル　　deep learning，artificial neural networks，time series forecasting，hybrid time series predictors

要約(英語): 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.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.136 No.3 （2016） 特集：機械学習が拓くシステムイノベーション

本誌掲載ページ: 348-356 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/136/3/136_348/_article/-char/ja/