Ensemble SVM classifiers based on PCA and LDA for IDS
Abdulla Amin Aburomman, Mamun Bin Ibne Reaz · 2016
Feature extraction addresses the problem of finding the most compact and informative set of features. To maximize the effectiveness of each single feature extraction algorithm and to develop an efficient intrusion detection system, an ensemble of Linear Discriminant Analysis and Principle Component Analysis feature extraction algorithms is implemented. The experiments demonstrate that the ensemble method outperforms single feature extraction method with 92% in overall accuracy.