Research Article
Improved TLBO-JAYA Algorithm for Subset Feature Selection and Parameter Optimisation in Intrusion Detection System
Table 14
Comparison with the existing work for the NSL-KDD dataset.
| Ref. | Method | Dataset | Acc. | DR | FAR |
| [35] | Two-stage classifier | NSL-KDD | 96.38 | N.G | N.G | [36] | Hypergraph-based genetic algorithm and SVM | NSL-KDD | 0.975 | 0.9714 | 0.83 | [8] | PSO and SVM | NSL-KDD | 0.9784 | 0.9723 | 0.87 | [37] | Chi-square and SVM | NSL-KDD | 0.98 | N.G | 0.13 | [38] | SVM and hybrid PSO | NSL-KDD | 0.7341 | 0.6628 | 2.81 | [39] | SVM and feature selection | NSL-KDD | 0.90 | N.G | N.G | [40] | SVM and GA | NSL-KDD | 0.975 | N.G | N.G | TLBO-SVM | TLBO and SVM | NSL-KDD | 0.9801 | 0.9755 | 0.0284 | ITLBO-SVM | Improved TLBO and SVM | NSL-KDD | 0.981 | 0.9758 | 0.0277 | ITLBO-JAYA-SVM | Improved TLBO, improved JAYA and SVM | NSL-KDD | 0.9816 | 0.9794 | 0.0265 | ITLBO-IPJAYA-SVM | Improved TLBO, improved JAYA and SVM | NSL-KDD | 0.9823 | 0.9798 | 0.0262 |
|
|