Network Intrusion Detection Based on Kernel Principal Component Analysis and Extreme Learning Machine

This study is aimed at the problem that the detection rate of intrusion detection technology based on Extreme Learning Machine (ELM) algorithm is not high and the intrusion detection technology based on Support Vector Machine (SVM) algorithm is slow. An intrusion detection method based on Kernel Principal Component Analysis (KPCA) and extreme learning machine algorithm is proposed. Using the KPCA algorithm to reduce the dimension of the extracted feature matrix, and using the ELM algorithm to perform multi-classification detection on four common types of attacks. Simulation results show that the proposed method is more efficient and faster than intrusion detection based on extreme learning machine algorithm and intrusion detection based on support vector machine algorithm. Finally, the accuracy, false alarm rate, detection rate, and detection time in intrusion detection technology are improved.