Feature Selection Model Using Naive Bayes ML Algorithm for WSN Intrusion Detection System

Abstract

Network intrusion detection is the pressing need of every communication network. Network Intrusion Detection Systems (NIDSes) play an important role in security operations to detect and defend against cyber- attacks. As artificial intelligence (AI)-powered NIDSes are adaptive to various kinds of attacks by exploring the knowledge presented in the data, they are in high demand to treat the cyber-attacks nowadays with increasing diversity and intensity. This research works finds that the efficient learning to overcome these issues. Further, this research works finds that the Attribute Selected Classifier with Naïve Bayes Updateable of second order ensemble model gives highest performance which as accuracy level. This Attribute Selected Classifiers with Naïve Bayes Updateable model is performing well compare with other models. Additionally, Wireless sensor network (WSN) is becoming increasingly one of the trendiest research areas in Computer Science applications. It finds wide applications department of Defence, banking, hospital, marketing, education, and all prioritized government sectors. Applications that have created many problems especially in security levels and hindrance caused due to the intrusion in WSN based communication. In proposed system depending upon the security and dependability of this article builds model on IoT is established using machine learning algorithms. This intrusion detection system is very compatible and characteristics of determining the interactions in any dataset have given an exemplary classification, performance level and receiver of operator characteristics. This paper uses specialized data set of WSN to detect and classify different class attributes like black hole flooding and scheduling attacks. This paper considers the use of novel Framework that is trained using a dataset to detect and classify different attacks. Output results of the model show that WSN has improved ability for the intrusion detection system using higher classification and accuracy rate of 99.45% for IBk c