Feature or Attribute Extraction for Intrusion Detection System using Gain Ratio and Principal Component Analysis (PCA)

: 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.

Download Full-text

Autonomous profile-based anomaly detection system using principal component analysis and flow analysis

Applied Soft Computing ◽

10.1016/j.asoc.2015.05.019 ◽

2015 ◽

Vol 34 ◽

pp. 513-525 ◽

Cited By ~ 21

Author(s):

Gilberto Fernandes ◽

Joel J.P.C. Rodrigues ◽

Mario Lemes Proença

Keyword(s):

Principal Component Analysis ◽

Anomaly Detection ◽

Detection System ◽

Flow Analysis ◽

Principal Component ◽

Component Analysis ◽

Anomaly Detection System

Download Full-text

Hybridization of Machine Learning Algorithm in Intrusion Detection System

Handbook of Research on Machine and Deep Learning Applications for Cyber Security - Advances in Information Security, Privacy, and Ethics ◽

10.4018/978-1-5225-9611-0.ch008 ◽

2020 ◽

pp. 150-175

Author(s):

Amudha P. ◽

Sivakumari S.

Keyword(s):

Machine Learning ◽

Intrusion Detection ◽

Classification Accuracy ◽

Intrusion Detection System ◽

Learning Algorithm ◽

Detection System ◽

Principal Component ◽

Machine Learning Algorithms ◽

Feature Selection Technique ◽

Efficient Manner

In recent years, the field of machine learning grows very fast both on the development of techniques and its application in intrusion detection. The computational complexity of the machine learning algorithms increases rapidly as the number of features in the datasets increases. By choosing the significant features, the number of features in the dataset can be reduced, which is critical to progress the classification accuracy and speed of algorithms. Also, achieving high accuracy and detection rate and lowering false alarm rates are the major challenges in designing an intrusion detection system. The major motivation of this work is to address these issues by hybridizing machine learning and swarm intelligence algorithms for enhancing the performance of intrusion detection system. It also emphasizes applying principal component analysis as feature selection technique on intrusion detection dataset for identifying the most suitable feature subsets which may provide high-quality results in a fast and efficient manner.

Download Full-text