An Intrusion Detection Method and System based on KPCA and ELM for Wireless Sensor Networks
Author:Letian Duan, Dezhi Han, Qiuting Tian Author Unit: College of Information Engineering, Shanghai Maritime University, Shanghai 201306, China
Abstract:Intrusion detection is a research hotspot in wireless sensor network security. This paper proposes an intrusion
detection method based on kernel principal component analysis (KPCA) and extreme learning machine (ELM)
for wireless sensor networks. First, KPCA is used for feature extraction to reduce the dimension of network
data. It improves the performance of intrusion detection methods. Then, ELM classifies the network data,
detects and identifies the abnormal data. It improves the training and response speed of the model. Finally, we
design an intrusion detection system based on KPCA and ELM for wireless sensor networks, which makes
full use of the characteristics of different functional nodes in the sensor networks. A hierarchical intrusion
detection system for wireless sensor networks is proposed to effectively detect malicious data and ensure the
wireless sensor network security. At the same time, the energy consumption of the sensor network is reduced
as a whole. The experimental results on the NSL-KDD dataset show that the method can greatly reduce the
training time of the model and improve the detection rate of abnormal data.