Table 7 Improvement with the MENN algorithm for the “Training_Data” set
Leave-one-out LOO (%) | Leave-one-subject-out LOSO (%) | |||||
|---|---|---|---|---|---|---|
Accuracy | Sensitivity | Specificity | Accuracy | Sensitivity | Specificity | |
DNNE (without MENN) | ||||||
Mean | 64.09 | 70 | 50.67 | 69.25 | 68.50 | 70 |
Std | 0.0178 | 0.0206 | 0.0477 | 0.0274 | 0.0298 | 0.0339 |
Best | 66.92 | 76.71 | 63.85 | 75 | 75 | 75 |
DNNE (with MENN) | ||||||
Mean | 67.71 | 71.71 | 64 | 73.37 | 71 | 75 |
Std | 0.037 | 0.018 | 0.033 | 0.042 | 0.056 | 0.032 |
Best | 68.79 | 72.83 | 70 | 85 | 90 | 80 |
RF (without MENN) | ||||||
Mean | 67.39 | 71.62 | 60 | 78.25 | 85.50 | 71.50 |
Std | 0.0141 | 0.0297 | 0.0165 | 0.041 | 0.035 | 0.074 |
Best | 68.46 | 76.92 | 62.36 | 85 | 90 | 85 |
RF (with MENN) | ||||||
Mean | 70.93 | 73.27 | 67.59 | 81.50 | 92.50 | 70.50 |
Std | 0.031 | 0.0052 | 0.0063 | 0.0105 | 0.0225 | 0.0211 |
Best | 76.07 | 73.65 | 68.46 | 88 | 97 | 88 |