vioft2nntf2t|tblJournal|Abstract_paper|0xf4ff57572b000000c3ca000001000f00 This paper suggested Vector Machine Service (SVM) and Intrusion Detection Ant Colony Optimization (ACO). There have been two stages of the suggested approaches. In the first level, PCA is used as a SVM preprocessor to minimize practical vector measurements and to shorten preparation time. To increasing the noise generated by interface contrast and to enhance the execution of SVM with a specific end goal. The second phase is used to distinguish identification by using the least-square support vector machine with an ACO algorithm. To order to adjust work and violence through the hunting process, ACO is using coded zooming. Ultimately, the function weights and SVM parameters are tuned concurrently in accordance with the optimal interface subset. The PCA algorithm focused on ACO with Support Vector Machine (PCA-ACO-SVM). The experiments were conducted using KDD 99 dataset which are seen as an agreed standard to assess the quality of intrusion detection to demonstrate the adequacy of the proposed method. In fact, the accurate and effective application of our suggested hybridizing approach is sensible.
M Ramkumar, M Manikandan, K Sathish Kumar, R Krishna Kumar
Gnanamani College of Technology, India
ACO, Support Vector Machine, Principal Component Analysis, Intrusion Detection
| January | February | March | April | May | June | July | August | September | October | November | December |
| 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| Published By :
ICTACT
Published In :
ICTACT Journal on Data Science and Machine Learning
( Volume: 1 , Issue: 1 , Pages: 37-42 )
Date of Publication :
December 2019
Page Views :
230
Full Text Views :
4
|