Improved Sparse Representation based Robust Hybrid Feature Extraction Models with Transfer and Deep Learning for EEG Classification

作者：

Highlights：

• Improved Sparse Representation with six different combinations are proposed.

• Five Robust Hybrid Feature Extraction Models are proposed.

• Classified with the proposed Deep Learning methods.

• Analysis compared with Machine and Transfer Learning methods too.

• Implemented for two biosignal processing datasets.

摘要

•Improved Sparse Representation with six different combinations are proposed.•Five Robust Hybrid Feature Extraction Models are proposed.•Classified with the proposed Deep Learning methods.•Analysis compared with Machine and Transfer Learning methods too.•Implemented for two biosignal processing datasets.

论文关键词：EEG,Sparse representation,Hybrid feature extraction,Transfer learning,Deep learning,Classification

论文评审过程：Received 9 August 2021, Revised 14 January 2022, Accepted 26 February 2022, Available online 8 March 2022, Version of Record 14 March 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116783