An Improved Composite Multiscale Fuzzy Entropy for Feature Extraction of MI-EEG

• Published in: Entropy (Basel, Switzerland) Vol. 22; no. 12; p. 1356
• Main Authors: Li, Mingai, Wang, Ruotu, Xu, Dongqin
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 30.11.2020; MDPI
• Subjects: Algorithms; Back propagation networks; Datasets; Electroencephalography; Entropy; Feature extraction; Filtration; Imagery; Methods; motor imagery electroencephalography; Neural networks; Nonlinear dynamics; Signal processing; Time series; Wavelet transforms; weight factors; weighted composite multiscale fuzzy entropy; weight factors; feature extraction; motor imagery electroencephalography; weighted composite multiscale fuzzy entropy
• ISSN: 1099-4300; 1099-4300
• DOI: 10.3390/e22121356

Motor Imagery Electroencephalography (MI-EEG) has shown good prospects in neurorehabilitation, and the entropy-based nonlinear dynamic methods have been successfully applied to feature extraction of MI-EEG. Especially based on Multiscale Fuzzy Entropy (MFE), the fuzzy entropies of the τ coarse-grained sequences in τ scale are calculated and averaged to develop the Composite MFE (CMFE) with more feature information. However, the coarse-grained process fails to match the nonstationary characteristic of MI-EEG by a mean filtering algorithm. In this paper, CMFE is improved by assigning the different weight factors to the different sample points in the coarse-grained process, i.e., using the weighted mean filters instead of the original mean filters, which is conductive to signal filtering and feature extraction, and the resulting personalized Weighted CMFE (WCMFE) is more suitable to represent the nonstationary MI-EEG for different subjects. All the WCMFEs of multi-channel MI-EEG are fused in serial to construct the feature vector, which is evaluated by a back-propagation neural network. Based on a public dataset, extensive experiments are conducted, yielding a relatively higher classification accuracy by WCMFE, and the statistical significance is examined by two-sample t-test. The results suggest that WCMFE is superior to the other entropy-based and traditional feature extraction methods.