Table 3 Dataset 1 long window (\(w=1\,\text{s}\)) features grand average (across all participants) accuracy and F1 score of sLDA classification, shown by condition, types of features and types of TFRs calculated with Shannon entropy
From: Detection of motor imagery based on short-term entropy of time–frequency representations
cond | Accuracy (%) | ||||||||
|---|---|---|---|---|---|---|---|---|---|
TFR | tfrsp | tfrrsp | tfrgabor | tfrrgab | tfrpwv | tfrrpwv | tfrspwv | tfrrspwv | |
Feature type | Entropy | Entropy | Entropy | Entropy | Entropy | Entropy | Entropy | Entropy | |
Right vs up | VtG | 53.69 | 52.73 | 53.14 | 51.51 | 52.83 | 52.74 | 52.41 | 53.01 |
noVtG | 53.38 | 52.78 | 52.42 | 53.52 | 52.71 | 53.19 | 52.88 | 51.99 | |
Right vs base | VtG | 65.22 | 59.51 | 79.40 | 58.68 | 83.24 | 94.21 | 71.41 | 62.65 |
noVtG | 65.40 | 59.29 | 77.82 | 58.38 | 85.32 | 94.19 | 71.52 | 63.41 | |
Up vs base | VtG | 62.54 | 60.97 | 77.30 | 58.04 | 81.64 | 93.77 | 68.39 | 61.69 |
noVtG | 67.60 | 58.41 | 79.25 | 57.83 | 86.23 | 94.17 | 72.41 | 61.32 | |
F1 score (%) | |||||||||
|---|---|---|---|---|---|---|---|---|---|
Right vs up | VtG | 52.51 | 51.84 | 52.72 | 50.07 | 52.19 | 52.45 | 51.16 | 52.00 |
noVtG | 53.16 | 52.92 | 52.05 | 52.82 | 51.78 | 51.85 | 53.23 | 51.42 | |
Right vs base | VtG | 64.29 | 58.48 | 78.91 | 57.51 | 81.30 | 93.83 | 70.98 | 61.84 |
noVtG | 63.91 | 58.07 | 77.22 | 57.80 | 83.54 | 93.76 | 71.01 | 62.81 | |
Up vs base | VtG | 62.03 | 59.24 | 76.76 | 57.00 | 79.44 | 93.32 | 67.83 | 61.04 |
noVtG | 66.73 | 57.43 | 78.73 | 57.26 | 84.87 | 93.78 | 71.81 | 60.76 | |