Enhancing Security in Industrial IoT Networks: Machine Learning Solutions for Feature Selection and Reduction

被引:0
|
作者
Houkan, Ahmad [1 ]
Sahoo, Ashwin Kumar [1 ]
Gochhayat, Sarada Prasad [2 ]
Sahoo, Prabodh Kumar [3 ]
Liu, Haipeng [4 ]
Khalid, Syed Ghufran [5 ]
Jain, Prince [3 ]
机构
[1] C. V. Raman Global University, Department of Electrical Engineering, Odisha, Bhubaneswar,752054, India
[2] Indian Institute of Technology Jammu, Department of Computer Science Engineering, Jammu and Kashmir,181221, India
[3] Parul Institute of Technology, Department of Mechatronics Engineering, Parul University, Gujarat, Vadodara,391760, India
[4] Coventry University, Centre for Intelligent Healthcare, Coventry,CV1 5RW, United Kingdom
[5] Nottingham Trent University, Clifton, School of Science and Technology, Nottingham,NG11 8NF, United Kingdom
关键词
Adversarial machine learning - Feature Selection - Intrusion detection - Nearest neighbor search - Redundancy - Support vector regression;
D O I
10.1109/ACCESS.2024.3481459
中图分类号
学科分类号
摘要
The increasing deployment of Internet of Things devices has introduced significant cyber security challenges, creating a need for robust intrusion detection systems. This research focuses on improving anomaly detection in industrial Internet of Things networks through feature reduction and selection. Experiments were performed to compare the effectiveness of Minimum Redundancy Maximum Relevance for feature selection with Principal Component Analysis for feature reduction. Six machine learning algorithms - Decision Trees, k-nearest neighbors, Gaussian Support Vector Machine, Neural Network, Support Vector Machines kernel, and Logistic Regression Kernel - were evaluated for both binary and multi-class classification using feature sets of 4, 12, 23, 50, and 79 features. The results reveal that Minimum Redundancy Maximum Relevance is superior to Principal Component Analysis in identifying crucial features. Notably, Minimum Redundancy Maximum Relevance achieves high accuracy with just 12 features, where the Decision Tree classifier reached an outstanding 99.9% accuracy in binary classification, and k-nearest neighbors achieved 99% accuracy in multi-class classification. The article emphasizes the critical role of feature engineering, with a specific focus on feature selection and reduction, and elaborates on applying MRMR and PCA algorithms to various feature sets. By comparing these methods, it showcases their influence on both model performance and complexity, leading to the development of more efficient and precise intrusion detection systems for Industrial IoT networks. What sets this study apart from previous ones is its novel demonstration of how these techniques significantly reduce training time and model complexity while maintaining or even improving performance, confirming the effectiveness of strategic feature utilization in strengthening Industrial IoT security by balancing accuracy, speed, and model size. © 2013 IEEE.
引用
收藏
页码:160864 / 160883
相关论文
共 50 条
  • [1] Enhancing Security and Reliability in Industrial IoT Networks through Machine Learning
    V. Barekar, Praful
    Purandare, Radhika
    Sawlikar, Alka
    Welekar, Rashmi R.
    Ingole, Piyush K.
    Shelke, Nilesh
    [J]. JOURNAL OF ELECTRICAL SYSTEMS, 2024, 20 (01) : 289 - 302
  • [2] A critical review of feature selection methods for machine learning in IoT security
    Li, Jing
    Othman, Mohd Shahizan
    Chen, Hewan
    Yusuf, Lizawati Mi
    [J]. INTERNATIONAL JOURNAL OF COMMUNICATION NETWORKS AND DISTRIBUTED SYSTEMS, 2024, 30 (03) : 264 - 312
  • [3] Feature Selection for Malicious Detection on Industrial IoT Using Machine Learning
    Chuang, Hong-Yu
    Chen, Ruey-Maw
    [J]. SENSORS AND MATERIALS, 2024, 36 (03) : 1035 - 1046
  • [4] A Novel Hybrid Feature Selection with Cascaded LSTM: Enhancing Security in IoT Networks
    Sundaram, Karthic
    Natarajan, Yuvaraj
    Perumalsamy, Anitha
    Yusuf Ali, Ahmed Abdi
    [J]. Wireless Communications and Mobile Computing, 2024, 2024
  • [5] Machine learning enabled Industrial IoT Security: Challenges, Trends and Solutions
    Ni, Chunchun
    Li, Shan Cang
    [J]. JOURNAL OF INDUSTRIAL INFORMATION INTEGRATION, 2024, 38
  • [6] Enhancing intrusion detection in IoT networks using machine learning-based feature selection and ensemble models
    Almotairi, Ayoob
    Atawneh, Samer
    Khashan, Osama A.
    Khafajah, Nour M.
    [J]. SYSTEMS SCIENCE & CONTROL ENGINEERING, 2024, 12 (01)
  • [7] Detection of Security Attacks in Industrial IoT Networks: A Blockchain and Machine Learning Approach
    Vargas, Henry
    Lozano-Garzon, Carlos
    Montoya, German A.
    Donoso, Yezid
    [J]. ELECTRONICS, 2021, 10 (21)
  • [8] Hybrid Feature Selection Models for Machine Learning Based Botnet Detection in IoT Networks
    Guerra-Manzanares, Alejandro
    Nomm, Sven
    Bahsi, Hayretdin
    [J]. 2019 INTERNATIONAL CONFERENCE ON CYBERWORLDS (CW), 2019, : 324 - 327
  • [9] Enhancing IoT Botnet Detection through Machine Learning-based Feature Selection and Ensemble Models
    Sharma, Ravi
    Din, Saika Mohi Ud
    Sharma, Nonita
    Kumar, Arun
    [J]. EAI ENDORSED TRANSACTIONS ON SCALABLE INFORMATION SYSTEMS, 2024, 11 (02) : 1 - 6
  • [10] Feature Selection for Machine Learning Based Anomaly Detection in Industrial Control System Networks
    Mantere, Matti
    Sailio, Mirko
    Noponen, Sami
    [J]. 2012 IEEE INTERNATIONAL CONFERENCE ON GREEN COMPUTING AND COMMUNICATIONS, CONFERENCE ON INTERNET OF THINGS, AND CONFERENCE ON CYBER, PHYSICAL AND SOCIAL COMPUTING (GREENCOM 2012), 2012, : 771 - 774