Table 5 Dataset 2 long window (\(w=1\,\text{s}\)) and amplitude features grand average (across all participants) accuracy and F1 score of sLDA classification, shown by types of features and types of TFRs calculated with Rényi entropy
From: Detection of motor imagery based on short-term entropy of time–frequency representations
Accuracy (%) | |||||||||
|---|---|---|---|---|---|---|---|---|---|
TFR | – | tfrsp | tfrrsp | tfrgabor | tfrrgab | tfrpwv | tfrrpwv | tfrspwv | tfrrspwv |
Feature type | Ampl. | Entropy | Entropy | Entropy | Entropy | Entropy | Entropy | Entropy | Entropy |
EE vs EF | 53.59 | 52.49 | 54.23 | 52.60 | 53.65 | 52.96 | 51.74 | 53.67 | 52.84 |
EE vs base | 66.26 | 55.13 | 57.21 | 54.05 | 59.35 | 58.6 | 71.28 | 56.42 | 58.31 |
EF vs base | 66.15 | 55.23 | 56.85 | 54.58 | 58.61 | 59.9 | 70.95 | 57.01 | 57.64 |
F1 score (%) | |||||||||
|---|---|---|---|---|---|---|---|---|---|
EE vs EF | 52.72 | 52.42 | 53.90 | 52.27 | 53.08 | 52.46 | 50.99 | 53.04 | 52.41 |
EE vs base | 55.85 | 54.68 | 56.01 | 52.8 | 58.56 | 56.34 | 70.7 | 54.7 | 56.1 |
EF vs base | 56.18 | 54.61 | 55.91 | 53.93 | 58.27 | 57.32 | 70.39 | 55.16 | 56.14 |