Multi-feature fusion method based on WOSF and MSE for four-class MI EEG identification. (August 2021)

• Record Type: Journal Article
• Authors: Hu, Lingyan; Xie, Jingjing; Pan, Changhui; Wu, Xiaolong; Hu, Dongxia
• Is Part Of: Biomedical signal processing and control. Volume 69(2021)
• Publication Date: 2021-08
• Subjects: Brain Computer Interface -- Multiclass EEG -- Feature fusion -- Common Spatial Pattern -- Local Mean Decomposition; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102907
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: We combine Local Mean Decomposition with Common Spatial Pattern. Considering characteristics of different methods, Multi-Features are fused. Design a second experiment for unilateral motor imagery tasks. The accuracy is greatly improved compared with other methods in two experiments. Abstract: Background: Brain-Computer Interface (BCI) can bring great convenience to patients in the process of rehabilitation training and prosthetic control. However, how to extract effective features is a core issue in a BCI system. Methods: We proposes the Multi-Feature Fusion Method based on Wavelength Optimal Spatial Filter and Multiscale Entropy for classifying the electroencephalogram signals (EEG) in four kinds of motor imagery tasks. The method can combine Wavelength features with Multiscale Entropy. Results: Two groups of experiments were conducted. One for simple four types of motor imagery (MI) tasks and another for unilateral limb. Experiments show that our proposed method has better performance compared to other methods. (82.55% versus 73.08% average accuracy respectively). Conclusions: The proposed method can effectively improve the accuracy of EEG classification in multiclass motor imagery and will be useful for neurorehabilitation through motor imagery for hemiplegic patients.