A deep learning-based time series model with missing value handling techniques to predict various types of liquid cargo traffic
作者：
Highlights：
• A LSTM-based time series model is proposed for liquid cargo traffic prediction.
• Missing value handling techniques are used to improve prediction performance.
• Dependencies between different types of liquid cargo traffic are considered.
• The proposed LSTM-based model overcomes a vanishing gradient problem as well.
• Performance of the proposed LSTM-based model is compared with ARIMA and VAR.
摘要
•A LSTM-based time series model is proposed for liquid cargo traffic prediction.•Missing value handling techniques are used to improve prediction performance.•Dependencies between different types of liquid cargo traffic are considered.•The proposed LSTM-based model overcomes a vanishing gradient problem as well.•Performance of the proposed LSTM-based model is compared with ARIMA and VAR.
论文关键词：Liquid cargo traffic prediction,Time series analysis,Missing value handling technique,Autoregressive integrated moving average,Vector autoregression,Long short-term memory
论文评审过程：Received 24 February 2020, Revised 26 April 2021, Accepted 29 June 2021, Available online 3 July 2021, Version of Record 9 July 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115532
