Research Article
Pulmonary Nodule Recognition Based on Multiple Kernel Learning Support Vector Machine-PSO
Table 1
Comparison of various indexes in parameter optimization stage of different algorithms.
| ā | Different inertial weight algorithm | Average parameter optimization time (s) | Average optimal fitness value | Average ACC value obtained from test set | Average SEN value obtained from test set |
| 1 | The constant is 1 | 370.7950 | 94.1176% | 90.45% | 86.85% | 2 | (16) | 462.4134 | 94.1176% | 91% | 88.89% | 3 | (17) | 457.0022 | 94.1176% | 91% | 88.89% | 4 | (18) | 416.0204 | 94.1176% | 91% | 88.89% | 5 | (19) | 448.1536 | 94.1176% | 91% | 88.89% | 6 | (20) | 450.4456 | 94.1176% | 91% | 88.89% | 7 | Grid search algorithm | 3096.1427 | 94.1176% | 91% | 88.89% |
|
|