Intrusion Detection System Based on Gradient Corrected Online Sequential Extreme Learning Machine

Qaiwmchi, Nedhal Ahmad Hamdi; Amintoosi, Haleh; Mohajerzadeh, Amir Hossein

doi:10.1109/access.2020.3047933

Cited by 11 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, conventional intrusion detection techniques face challenges in delivering sufficient and highly effective security for IoT systems, primarily due to the unique characteristics of IoT environments. These characteristics include limited bandwidth capacity 9 , energy constraints, diversity in device types and technologies, and widespread presence of IoT devices.…”

Section: Introductionmentioning

confidence: 99%

Firefly algorithm based WSN-IoT security enhancement with machine learning for intrusion detection

Karthikeyan,

Manimegalai,

RajaGopal

2024

Sci Rep

View full text Add to dashboard Cite

A Wireless Sensor Network (WSN) aided by the Internet of Things (IoT) is a collaborative system of WSN systems and IoT networks are work to exchange, gather, and handle data. The primary objective of this collaboration is to enhance data analysis and automation to facilitate improved decision-making. Securing IoT with the assistance of WSN necessitates the implementation of protective measures to confirm the safety and reliability of the interconnected WSN and IoT components. This research significantly advances the current state of the art in IoT and WSN security by synergistically harnessing the potential of machine learning and the Firefly Algorithm. The contributions of this work are twofold: firstly, the proposed FA-ML technique exhibits an exceptional capability to enhance intrusion detection accuracy within the WSN-IoT landscape. Secondly, the amalgamation of the Firefly Algorithm and machine learning introduces a novel dimension to the domain of security-oriented optimization techniques. The implications of this research resonate across various sectors, ranging from critical infrastructure protection to industrial automation and beyond, where safeguarding the integrity of interconnected systems are of paramount importance. The amalgamation of cutting-edge machine learning and bio-inspired algorithms marks a pivotal step forward in crafting robust and intelligent security measures for the evolving landscape of IoT-driven technologies. For intrusion detection in the WSN-IoT, the FA-ML method employs a support vector machine (SVM) machine model for classification with parameter tuning accomplished using a Grey Wolf Optimizer (GWO) algorithm. The experimental evaluation is simulated using NSL-KDD Dataset, revealing the remarkable enhancement of the FA-ML technique, achieving a maximum accuracy of 99.34%. In comparison, the KNN-PSO and XGBoost models achieved lower accuracies of 96.42% and 95.36%, respectively. The findings validate the potential of the FA-ML technique as an active security solution for WSN-IoT systems, harnessing the power of machine learning and the Firefly Algorithm to bolster intrusion detection capabilities.

show abstract

Section: Introductionmentioning

confidence: 99%

Firefly algorithm based WSN-IoT security enhancement with machine learning for intrusion detection

Karthikeyan,

Manimegalai,

RajaGopal

2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The surveys have covered studies on IDSs for cloud-related IoT systems, WSNs, mobile ad hoc networks (MANETs), and cyber-physical systems (CPS) [10]. However, conventional IDS techniques are insufficient or less effective for the security of IoT systems because of their peculiar features, for example" limited bandwidth capacity [11], limited energy, heterogeneity, global connectivity, and ubiquity.…”

Section: Introductionmentioning

confidence: 99%

Binary Chimp Optimization Algorithm with ML Based Intrusion Detection for Secure IoT-Assisted Wireless Sensor Networks

Aljebreen

Alohali

Saeed

et al. 2023

Sensors

View full text Add to dashboard Cite

An Internet of Things (IoT)-assisted Wireless Sensor Network (WSNs) is a system where WSN nodes and IoT devices together work to share, collect, and process data. This incorporation aims to enhance the effectiveness and efficiency of data analysis and collection, resulting in automation and improved decision-making. Security in WSN-assisted IoT can be referred to as the measures initiated for protecting WSN linked to the IoT. This article presents a Binary Chimp Optimization Algorithm with Machine Learning based Intrusion Detection (BCOA-MLID) technique for secure IoT-WSN. The presented BCOA-MLID technique intends to effectively discriminate different types of attacks to secure the IoT-WSN. In the presented BCOA-MLID technique, data normalization is initially carried out. The BCOA is designed for the optimal selection of features to improve intrusion detection efficacy. To detect intrusions in the IoT-WSN, the BCOA-MLID technique employs a class-specific cost regulation extreme learning machine classification model with a sine cosine algorithm as a parameter optimization approach. The experimental result of the BCOA-MLID technique is tested on the Kaggle intrusion dataset, and the results showcase the significant outcomes of the BCOA-MLID technique with a maximum accuracy of 99.36%, whereas the XGBoost and KNN-AOA models obtained a reduced accuracy of 96.83% and 97.20%, respectively.

show abstract

An improved extreme learning machine algorithm for transient electromagnetic nonlinear inversion

Zhang

Gao

et al. 2021

Computers & Geosciences

View full text Add to dashboard Cite

Intrusion Detection System Based on Gradient Corrected Online Sequential Extreme Learning Machine

Cited by 11 publications

References 35 publications

Firefly algorithm based WSN-IoT security enhancement with machine learning for intrusion detection

Firefly algorithm based WSN-IoT security enhancement with machine learning for intrusion detection

Binary Chimp Optimization Algorithm with ML Based Intrusion Detection for Secure IoT-Assisted Wireless Sensor Networks

An improved extreme learning machine algorithm for transient electromagnetic nonlinear inversion

Contact Info

Product

Resources

About