No Detail Found!

An intrusion detection system on IOT networks using hybrid PCA-GWSO model

Author(s)
JAYABRABU RAMAKRISHNAN Department of Information Technology and Security College of Computer Science and Information Technology 1Jazan University, Saudi Arabia
Abstract
In any distributed system, network security is a critical concern. For this reason, intrusion detection system (IDS) has been offered to defend the networks against the hostile activity. This analysis aims to create and present an anomaly detection system that can be used to detect intrusions and abnormal activity in the Internet of Things (IoT) networks. The intrusion detection system is critical in identifying diverse attack types on the Internet of Things and improving the IoT's overall functionality. The anomaly identification in the Internet of Things network with glowworm swarm optimization (GWSO) in conjunction with principal components analysis (PCA) was implemented in this work. The proposed framework is a metaheuristic approach-based anomaly detection system that could be used for identifying attacks from the NSL-KDD data set. The anomaly identification process is carried out using the GWSO method based on PCA. The PCA algorithm is employed for feature extraction, and the GWSO technique is employed for classification. Various factors such as accuracy, recall, precision, FAR, and detection rate are assessed in order to conduct a performance analysis. The proposed model achieved 94.14 percent accuracy in the normal class, 95.52 percent accuracy in the DoS class, 93.15 percent accuracy in the R2L class, 93.50 percent accuracy in the probe class, and 88.62 percent accuracy in the U2R class. The detection rate was 94.08 percent, while the false alarm rate (FAR) was 3.41 percent.
Publication Details
Page(s) 4850-4858
DOI DOI not available
Published Journal: Journal of Theoretical and Applied Information Technology, Volume: 100, Issue: 24, Year: 2022

Request the full text from PASTIC

Keywords
IoT, IDS, PCA, Anomaly Detection, NSL-KDD Dataset, GWSO
0

Citations

0

Downloads

39

Views