An improved synergistic dual-layer feature selection algorithm with two type classifier for efficient intrusion detection in IoT environment

In an era of increasing sophistication and frequency of cyber threats, securing Internet of Things (IoT) networks has become a paramount concern. IoT networks, with their diverse and interconnected devices, face unique security challenges that traditional methods often fail to address effectively. T...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Scientific reports Ročník 15; číslo 1; s. 8050 - 21
Hlavní autori: Logeswari, G, Thangaramya, K, Selvi, M, Roselind, J. Deepika
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: London Nature Publishing Group UK 07.03.2025
Nature Publishing Group
Nature Portfolio
Predmet:
639/166
639/166/987
Algorithms
Anomaly detection
Classification
Dynamic feature selection
Feature selection
Humanities and Social Sciences
Internet of Things
Intrusion detection system
Machine learning
multidisciplinary
Science
Science (multidisciplinary)
Security systems
Statistical analysis
Statistical methods
Internet of things
Dynamic feature selection
Intrusion detection system
Security systems
Anomaly detection
Machine learning
ISSN:2045-2322, 2045-2322
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In an era of increasing sophistication and frequency of cyber threats, securing Internet of Things (IoT) networks has become a paramount concern. IoT networks, with their diverse and interconnected devices, face unique security challenges that traditional methods often fail to address effectively. To tackle these challenges, an Intrusion Detection System (IDS) is specifically designed for IoT environments. This system integrates a multi-faceted approach to enhance security against emerging threats. The proposed IDS encompasses three critical subsystems: data pre-processing, feature selection and detection. The data pre-processing subsystem ensures high-quality data by addressing missing values, removing duplicates, applying one-hot encoding, and normalizing features using min-max scaling. A robust feature selection subsystem, employing Synergistic Dual-Layer Feature Selection (SDFC) algorithm, combines statistical methods, such as mutual information and variance thresholding, with advanced model-based techniques, including Support Vector Machine (SVM) with Recursive Feature Elimination (RFE) and Particle Swarm Optimization (PSO) are employed to identify the most relevant features. The classification subsystem employ two stage classifier namely LightGBM and XGBoost for efficient classification of the network traffic as normal or malicious. The proposed IDS is implemented in MATLAB by using TON-IoT dataset with various performance metrics. The experimental results demonstrate that the proposed SDFC method significantly enhances classifier performance, consistently achieving higher accuracy, precision, recall, and F1 scores compared to other existing methods.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-025-91663-z