IF2CNN: Towards non-stationary time series feature extraction by integrating iterative filtering and convolutional neural networks
作者：
Highlights：
• A novel framework called IF2CNN is proposed to deal with time series.
• Iterative filtering and convolutional neural network are used in our framework.
• It is suitable for processing non-stationary time series due to the ability of IF.
• CNN enables IF2CNN to extract the deep and global features from time series.
• Three real datasets are used to demonstrate the performance of the new framework.
摘要
•A novel framework called IF2CNN is proposed to deal with time series.•Iterative filtering and convolutional neural network are used in our framework.•It is suitable for processing non-stationary time series due to the ability of IF.•CNN enables IF2CNN to extract the deep and global features from time series.•Three real datasets are used to demonstrate the performance of the new framework.
论文关键词：Iterative filtering,Convolution neural networks,Non-stationary time series,Feature extraction
论文评审过程：Received 1 July 2020, Revised 15 November 2020, Accepted 20 December 2020, Available online 24 December 2020, Version of Record 10 January 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.114527
