Affiliations: School of Mechanical Engineering, Northwestern Polytechnical University, Xi’an, China
Correspondence:
[*]
Corresponding author. Jie Hong, School of Mechanical Engineering, Northwestern Polytechnical University, Xi’an, China. Tel.: +86 159 0297 0962; Fax: +86 29 8849 4271; E-mail: hongjie@mail.nwpu.edu.cn.
Abstract: Over the past two decades, motor imagery brain-computer interface (MI-BCI) system has been extensively developed. In this system signal processing algorithms are critical to robust operation. In BCI community, however, there is no comprehensive review of the recent development of signal processing algorithms. Through analyzing the latest papers, signal processing algorithms of pre-processing, feature extraction, feature selection, and classification components are discussed in detail. Besides, post-processing and other existing problems are mentioned. The following key issues are addressed: (1) which components are the key of signal processing; (2) which signal processing algorithms are frequently used in each component; (3) which signal processing algorithms attract more attention. This information can be used as reference and guidance for further research.
Keywords: Motor imagery brain-computer interface (MI-BCI), signal processing algorithms, pre-processing, feature extraction, classification
