:
Intrusion Detection System is one of the prominent ways to identify the attacks by effectively monitoring the network. Designing an intrusion detection system that utilizes the resources efficiently by improving the precision is a challenging factor. This paper proposes a Least Square Support Vector Machine (LS-SVM) based on bat algorithm (BA) for efficient intrusion detection. The proposed technique is divided into two phases. In the first phase, the Kernel principal component analysis (KPCA) is utilized as a pre-processing of LS-SVM to decrease the dimension of feature vectors and abbreviates the preparing time with a specific end goal to decrease the noise caused by feature contrasts and enhance the implementation of LS-SVM. In the second phase, the LS-SVM with bat algorithm is applied for the classification of detection. BA utilizes programmed zooming to adjust investigation and abuse among the hunting procedure. Finally, as per the ideal feature subset, the feature weights and the parameters of LS-SVM are optimized at the same time. The proposed algorithm is named as Kernel principal component analysis based least square support vector machine with bat algorithm (KPCA-BA-LS-SVM). To show the adequacy of proposed method, the tests are completed on KDD 99 dataset which is viewed as an accepted benchmark for assessing the execution of intrusions detection. Furthermore, our proposed hybridization method gets a sensible execution regarding precision and efficiency.
Feature or Attribute Extraction for Intrusion Detection System using Gain Ratio and Principal Component Analysis (PCA)
