IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Real-Time Threat Detection on Machine Learning Approaches in Wireless Sensor Network Security

Real-Time Threat Detection on Machine Learning Approaches in Wireless Sensor Network Security
View Sample PDF
Author(s): M. Nirmal Kumar (Bharath Institute of Higher Education and Research, India), T. Vijayan (Bharath Institute of Higher Education and Research, India)and B. Karthik (Bharath Institute of Higher Education and Research, India)
Copyright: 2026
Pages: 28
Source title: Pioneering AI and Data Technologies for Next-Gen Security, IoT, and Smart Ecosystems
Source Author(s)/Editor(s): Ferdin Joe John Joseph (Thai-Nichi Institute of Technology, Thailand), Karthikeyan Chinnusamy (Veritas, USA), Joseph Jeganathan (University of Bahrain, Bahrain), Ahmed J. Obaid (University of Kufa, Iraq)and S. Suman Rajest (Dhaanish Ahmed College of Engineering, India)
DOI: 10.4018/979-8-3373-4672-4.ch012

Purchase

View Real-Time Threat Detection on Machine Learning Approaches in Wireless Sensor Network Security on the publisher's website for pricing and purchasing information.

Abstract

Wireless Sensor Networks (WSNs) play a vital role in applications like environmental monitoring and military operations but face significant security challenges such as Denial of Service (DoS), Sybil, and sinkhole attacks. Traditional security mechanisms are ineffective due to their reliance on static rules, high false positive rates, and limited scalability. This chapter introduces a machine learning (ML)-based real-time threat detection system using Decision Trees (DT), Support Vector Machines (SVM), and Neural Networks (NN) to identify network anomalies dynamically. The system preprocesses real-time sensor data, extracts relevant features, and continuously retrains models to detect both known and novel attacks with high accuracy. Compared to existing systems, the proposed approach demonstrates superior performance, achieving 95.1% accuracy versus 85.7% and 82.3% for previous models. It enhances detection accuracy (97.5%) and true positive rate (95.8%), making it more reliable for intrusion detection.

Related Content

P. V. Naveen, A. Poongodi. © 2026. 24 pages.
Sathya Selvaraj Sinnasamy, S. Kamaleswari, U. Surendar, Biswaranjan Senapati, B. Vaidianathan, M. Gandhi. © 2026. 14 pages.
B. Aarthi, A. Smruthi, Pamireddy Thanishka, G. Sakthi Prasanna, P. Mahendran. © 2026. 18 pages.
R. Radhika, A. Muthukumaravel. © 2026. 24 pages.
R. Regin, K. Lalith Reddy, R. Sanjay Narayanan, Y. Likhith Srinivas, R. Steffi, S. Saranya, S. R. Saranya. © 2026. 26 pages.
R. Saranya, S. Silvia Priscila. © 2026. 20 pages.
Manjunath Singh H., R. Tanuja. © 2026. 28 pages.
Body Bottom