Table 6 Trust calibration scores across methods.
From: Explainable AI and echo state networks calibrate trust in human machine interaction
Method | Trust Calibration Score (Mean ± SD) |
|---|---|
Proposed method | 5.92 ± 0.43 |
Baseline CNN | 5.12 ± 0.51 |
LIME | 5.45 ± 0.49 |
SHAP | 5.50 ± 0.47 |
Attention mechanisms | 5.60 ± 0.45 |
Grad-CAM (Standalone) | 5.75 ± 0.44 |
