• Vikas kumar
• Ritika

To detect malicious activities from the network various classification techniques are designed. The existing technique is SVM which is applied to classify data into malicious and normal classes. In this research work, stacking approach is designed for the classification of network traffic. The base classifier which is used in this research work is SVM classifier and meta-classifier is KNN classifier. The performance of existing and proposed approach is tested in terms of accuracy and execution time. It is analyzed that proposed technique performs well as compared to existing SVM classifier for the network traffic classification SVM classifier given 77% accuracy with in 0.02 second and KNN classifier given 79% accuracy within 0.05 second. We can analyze that the accuracy of KNN is better than SVM but in case of execution time the SVM is better. Thus we applied an stacking approach (SVM+KNN) and we get 87.50% accuracy with in 0.04 second.

SVM, KNN, Stacking, KDD

"An esemble based stacking approach for Network intrusion detection system ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.968-971, June 2019, Available :http://www.jetir.org/papers/JETIR1906Y61.pdf

"An esemble based stacking approach for Network intrusion detection system ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp968-971, June 2019, Available at : http://www.jetir.org/papers/JETIR1906Y61.pdf