Adaptive feature fusion for time series classification

作者：

Highlights：

• Adaptive Feature Fusion Network (AFFNet) to enhance time series classification accuracy.

• Multi-scale dynamic convolutional network to extract multi-scale temporal features.

• Distance prototype network to extract the distance features of time series.

• Fuse multi-scale temporal and distance features time series for classification.

• Experimental results on a large number of UCR datasets.

摘要

•Adaptive Feature Fusion Network (AFFNet) to enhance time series classification accuracy.•Multi-scale dynamic convolutional network to extract multi-scale temporal features.•Distance prototype network to extract the distance features of time series.•Fuse multi-scale temporal and distance features time series for classification.•Experimental results on a large number of UCR datasets.

论文关键词：Time series classification,Multi-scale temporal features,Distance features,Distance prototype network,Adaptive feature fusion

论文评审过程：Received 21 October 2021, Revised 9 February 2022, Accepted 16 February 2022, Available online 23 February 2022, Version of Record 3 March 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.108459