Motor imagery EEG recognition based on conditional optimization empirical mode decomposition and multi-scale convolutional neural network

作者：

Highlights：

• The EMD algorithm is improved by using two conditions to select IMFs.

• The improved EMD (CEMD) algorithm is used to reduce the noise of EEG signals.

• An EEG signal combination method is proposed to encode the ERS/ERD information.

• A model called 1DMSCNN is built to classify EEG signals.

• An intelligent wheelchair system based on the proposed algorithm is designed.

摘要

•The EMD algorithm is improved by using two conditions to select IMFs.•The improved EMD (CEMD) algorithm is used to reduce the noise of EEG signals.•An EEG signal combination method is proposed to encode the ERS/ERD information.•A model called 1DMSCNN is built to classify EEG signals.•An intelligent wheelchair system based on the proposed algorithm is designed.

论文关键词：Empirical mode decomposition,Convolutional neural network,Motor imagery EEG,Feature extraction,Intelligent wheelchair

论文评审过程：Received 19 August 2019, Revised 15 November 2019, Accepted 5 February 2020, Available online 6 February 2020, Version of Record 15 February 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113285