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

G Logeswari,

K. Thangaramya,

M. Selvi

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 7, 2025

Abstract In an era of increasing sophistication and frequency cyber threats, securing Internet Things (IoT) networks has become a paramount concern. IoT networks, with their diverse interconnected devices, face unique security challenges that traditional methods often fail to address effectively. To tackle these challenges, Intrusion Detection System (IDS) is specifically designed for environments. This system integrates multi-faceted approach enhance against emerging threats. The proposed IDS encompasses three critical subsystems: data pre-processing, feature selection detection. pre-processing subsystem ensures high-quality by addressing missing values, removing duplicates, applying one-hot encoding, normalizing features using min-max scaling. A robust subsystem, employing Synergistic Dual-Layer Feature Selection (SDFC) algorithm, combines statistical methods, such as mutual information variance thresholding, advanced model-based techniques, including Support Vector Machine (SVM) Recursive Elimination (RFE) Particle Swarm Optimization (PSO) are employed identify the most relevant features. classification employ two stage classifier namely LightGBM XGBoost efficient network traffic normal or malicious. implemented in MATLAB TON-IoT dataset various performance metrics. experimental results demonstrate SDFC method significantly enhances performance, consistently achieving higher accuracy, precision, recall, F1 scores compared other existing methods.

Язык: Английский

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

G Logeswari,

K. Thangaramya,

M. Selvi

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 7, 2025

Abstract In an era of increasing sophistication and frequency cyber threats, securing Internet Things (IoT) networks has become a paramount concern. IoT networks, with their diverse interconnected devices, face unique security challenges that traditional methods often fail to address effectively. To tackle these challenges, Intrusion Detection System (IDS) is specifically designed for environments. This system integrates multi-faceted approach enhance against emerging threats. The proposed IDS encompasses three critical subsystems: data pre-processing, feature selection detection. pre-processing subsystem ensures high-quality by addressing missing values, removing duplicates, applying one-hot encoding, normalizing features using min-max scaling. A robust subsystem, employing Synergistic Dual-Layer Feature Selection (SDFC) algorithm, combines statistical methods, such as mutual information variance thresholding, advanced model-based techniques, including Support Vector Machine (SVM) Recursive Elimination (RFE) Particle Swarm Optimization (PSO) are employed identify the most relevant features. classification employ two stage classifier namely LightGBM XGBoost efficient network traffic normal or malicious. implemented in MATLAB TON-IoT dataset various performance metrics. experimental results demonstrate SDFC method significantly enhances performance, consistently achieving higher accuracy, precision, recall, F1 scores compared other existing methods.

Язык: Английский

Процитировано

0