Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting

  • Renzhuo Wan
    Nano-Optical Material and Storage Device Research Center, School of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan 430200, China
  • Shuping Mei
    Nano-Optical Material and Storage Device Research Center, School of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan 430200, China
  • Jun Wang
    Nano-Optical Material and Storage Device Research Center, School of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan 430200, China
  • Min Liu
    State Key Laboratory of Powder Metallurgy, School of Physics and Electronics, Central South University, Changsha 410083, China
  • Fan Yang
    Nano-Optical Material and Storage Device Research Center, School of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan 430200, China

書誌事項

公開日
2019-08-07
権利情報
  • https://creativecommons.org/licenses/by/4.0/
DOI
  • 10.3390/electronics8080876
公開者
MDPI AG

説明

<jats:p>Multivariable time series prediction has been widely studied in power energy, aerology, meteorology, finance, transportation, etc. Traditional modeling methods have complex patterns and are inefficient to capture long-term multivariate dependencies of data for desired forecasting accuracy. To address such concerns, various deep learning models based on Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) methods are proposed. To improve the prediction accuracy and minimize the multivariate time series data dependence for aperiodic data, in this article, Beijing PM2.5 and ISO-NE Dataset are analyzed by a novel Multivariate Temporal Convolution Network (M-TCN) model. In this model, multi-variable time series prediction is constructed as a sequence-to-sequence scenario for non-periodic datasets. The multichannel residual blocks in parallel with asymmetric structure based on deep convolution neural network is proposed. The results are compared with rich competitive algorithms of long short term memory (LSTM), convolutional LSTM (ConvLSTM), Temporal Convolution Network (TCN) and Multivariate Attention LSTM-FCN (MALSTM-FCN), which indicate significant improvement of prediction accuracy, robust and generalization of our model.</jats:p>

収録刊行物

  • Electronics

    Electronics 8 (8), 876-, 2019-08-07

    MDPI AG

被引用文献 (2)*注記

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ