Table 3 Resulting average classification accuracy together with precision, recall and F1-score for each Bayes model tested in our approach to performing the symbolic anchoring functionalities in nuScene, MOTFront and Mix datasets and in the Leon@Home scenario.
From: SAILOR: perceptual anchoring for robotic cognitive architectures
Accuracy | Precision | Recall | F1-score | |
|---|---|---|---|---|
nuScenes dataset | ||||
nuScenes | 0.9999 | 0.9994 | 0.9994 | 0.9994 |
MOTFront | 0.8105 | 0.8809 | 0.4568 | 0.6017 |
Mix | 0.8695 | 0.8911 | 0.4821 | 0.6257 |
Leon@Home | 0.9143 | 0.9971 | 0.1628 | 0.2799 |
MOTFront dataset | ||||
nuScenes | 0.9770 | 0.9965 | 0.3220 | 0.4867 |
MOTFront | 0.9904 | 0.9716 | 0.9986 | 0.9849 |
Mix | 0.9862 | 0.9720 | 0.9671 | 0.9695 |
Leon@Home | 0.9930 | 0.9957 | 0.9363 | 0.9652 |
Mix dataset | ||||
nuScenes | 0.9884 | 0.9933 | 0.6629 | 0.7952 |
MOTFront | 0.9915 | 0.9750 | 0.9983 | 0.9865 |
Mix | 0.9859 | 0.9658 | 0.9722 | 0.9690 |
Leon@Home | 0.9905 | 0.9755 | 0.9827 | 0.9791 |
