Auto-adaptive multilayer perceptron for univariate time series classification
作者：
Highlights：
• A novel auto-adaptive MLP for time series classification is proposed.
• Batch size and number of neurons in the hidden layers auto-adapts according to time series nature.
• Our model does not need a computer cluster, it runs on standard equipment.
• Accuracy obtained with our MLP is competitive versus 14 state-of-the-art methods.
• Experiments on 61 univariate UCR data sets verify effectiveness of our proposal.
摘要
•A novel auto-adaptive MLP for time series classification is proposed.•Batch size and number of neurons in the hidden layers auto-adapts according to time series nature.•Our model does not need a computer cluster, it runs on standard equipment.•Accuracy obtained with our MLP is competitive versus 14 state-of-the-art methods.•Experiments on 61 univariate UCR data sets verify effectiveness of our proposal.
论文关键词：Time series,Time series classification,Multilayer perceptron,UCR data set
论文评审过程：Received 18 January 2021, Revised 29 April 2021, Accepted 29 April 2021, Available online 19 May 2021, Version of Record 19 May 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115147
