An intelligent embedded fuzzy genetic classifier based network intrusion detection system for secured communication in internet of things.

Authors

Muneer M A, A Ayyasamy, L Sridhara Rao

Published in

Scientific reports. Jul 02, 2026. Epub Jul 02, 2026.

Abstract

Internet of things (IoT) is a distributed connection of smart objects which collects the data or information from the deployed environment and communicates the data to other devices with Internet as a backbone. Due to its unfriendly deployment nature and openness in communication via Internet, IoT is vulnerable to various types of attacks during data transmission. Intrusion Detection System (IDS) is an effective method to provide strong and efficient security to IoT devices. IDS is a software that tracks the network traffic and identifies the anomalies and abnormal activities. An Improved Ant Colony Optimization (IACO) algorithm with mutual information is proposed which effectively identifies the features in the given dataset and ranks. Moreover, for classification a Hybrid Fuzzy Genetic Algorithm (HFGA) is proposed to identify various types of attacks in the network. The proposed classifier comprises two layers namely external and internal. The external layer generates fuzzy sets and internal layer generates fuzzy rules. In the proposed system during training phase the External Fuzzy Genetic Algorithm (EFGA) helps Internal Fuzzy Genetic Algorithm (IFGA) and the finest individual from EFGA is associated with the fragile individual from IFGA to produce a new output which enhances the estimation of mutated attacks. The performance of the proposed system is evaluated using NSL-KDD dataset. Most of the existing IDS in IoT suffers from lower Intrusion detection accuracy, false alarm rate and has high computational and communication overhead. From the result, the proposed system has achieved better intrusion accuracy and reduced the false alarm rate in the network. Moreover, the proposed system identifies both known attacks and unknown attacks in the network.

PMID:
42393171
Bibliographic data and abstract were imported from PubMed on 03 Jul 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.