Unsupervised multi-subepoch feature learning and hierarchical classification for EEG-based sleep staging

作者：

Highlights：

• An unsupervised feature learning method is proposed to extract EEG features.

• A hierarchical classification model is established for EEG-based sleep staging.

• A novel feature evaluation criterion is presented for feature subset selecting.

• Extensive experiments are conducted to evaluate the proposed method.

摘要

•An unsupervised feature learning method is proposed to extract EEG features.•A hierarchical classification model is established for EEG-based sleep staging.•A novel feature evaluation criterion is presented for feature subset selecting.•Extensive experiments are conducted to evaluate the proposed method.

论文关键词：EEG,Sleep staging,Unsupervised feature learning,Hierarchical classification,H-WSVM

论文评审过程：Received 24 March 2021, Revised 14 June 2021, Accepted 9 August 2021, Available online 16 August 2021, Version of Record 23 August 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115759