Research Article
An Improved Refined Composite Multivariate Multiscale Fuzzy Entropy Method for MI-EEG Feature Extraction
Table 2
Comparison of average recognition rates with 10 × 10-fold CV (%) of multivariate entropy-based feature extraction methods.
| Methods | Subjects | Average results (%) | “aa” | “al” | “av” | “aw” | “ay” |
| mvMFE | 75.54 ± 1.70 | 86.00 ± 0.98 | 74.46 ± 1.54 | 84.07 ± 1.52 | 79.32 ± 1.24 | 79.88 ± 1.40 | RCmvMFE | 93.82 ± 1.48 | 98.46 ± 0.61 | 95.86 ± 1.01 | 98.79 ± 0.72 | 97.04 ± 0.79 | 96.97 ± 0.92 | IRCmvMFE | 99.39 ± 0.38 | 99.71 ± 0.15 | 98.61 ± 0.62 | 99.61 ± 0.26 | 99.82 ± 0.35 | 99.43 ± 0.35 |
|
|