Multi-scale signed recurrence plot based time series classification using inception architectural networks
作者：
Highlights：
• The reccurence plots (RP) suffer from the multi-scale and tendency confusion problems.
• Multi-scale signed recurrence plots (MSRP) are proposed to handle the defects of RP for better representation abilities.
• Existing time series classification (TSC) networks cannot adapt to the scale variability of MSRP effectively.
• The inception fully convolutional networks (IFCN) are proposed, which better extract multi-scale features from MSRP images .
• Our proposed MSRP-IFCN achieves superior performance on 85 UCR datasets.
摘要
•The reccurence plots (RP) suffer from the multi-scale and tendency confusion problems.•Multi-scale signed recurrence plots (MSRP) are proposed to handle the defects of RP for better representation abilities.•Existing time series classification (TSC) networks cannot adapt to the scale variability of MSRP effectively.•The inception fully convolutional networks (IFCN) are proposed, which better extract multi-scale features from MSRP images .•Our proposed MSRP-IFCN achieves superior performance on 85 UCR datasets.
论文关键词：Time series classification,Multi-scale,Signed,Recurrence plots,Inception network
论文评审过程：Received 2 December 2019, Revised 12 September 2021, Accepted 20 October 2021, Available online 22 October 2021, Version of Record 16 November 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108385
