Research Article
Early Diagnosis of Tuberculosis Using Deep Learning Approach for IOT Based Healthcare Applications
Table 2
Performance of proposed DBN-AMBO with other classifiers.
| Datasets | Performance | DBN-BOA | DBN-EPO | DBN-MBO | DBN-AMBO |
| Shenzhen China | Accuracy | 0.852 | 0.927 | 0.931 | 0.992 | Precision | 0.871 | 0.952 | 0.967 | 0.978 | Recall | 0.915 | 0.947 | 0.924 | 0.954 | Specificity | 0.921 | 0.871 | 0.941 | 0.991 | NPV | 0.201 | 0.165 | 0.275 | 0.06 | FNR | 0.853 | 0.961 | 0.852 | 0.998 |
| Montgomery Country | Accuracy | 0.974 | 0.922 | 0.914 | 0.987 | Precision | 0.825 | 0.905 | 0.935 | 0.966 | Recall | 0.846 | 0.928 | 0.941 | 0.989 | Specificity | 0.862 | 0.811 | 0.745 | 0.994 | NPV | 0.141 | 0.065 | 0.813 | 0.02 | FNR | 0.882 | 0.835 | 0.923 | 0.972 |
|
|