• Version
• Download 19
• File Size 561.86 KB
• File Count 1
• Create Date 29 April 2025
• Last Updated 29 April 2025

WIRELESS NETWORK SECURITY ENHANCEMENT WITH ZITA

Authors:

Ms. HARSHINI A¹, Mr. SANKARA NARAYANAN S T ²,

¹ Ms. HARSHINI.A, M.sc CFIS, Department of Computer Science Engineering,

harshiniaruljustin@gmail.com 9361471854, Dr. DR. M.G.R Educational and Research Institute, Chennai, India   

²Mr. SANKARA NARAYANAN S.T, Assistant Professor, Center of Excellence in Digital Forensics, Chennai, India.

Abstract - With the growing cybersecurity threats, predictive maintenance has turned out to be a critical approach for ensuring reliability and efficiency in wireless networks. In this paper, we demonstrate the use of supervised machine learning methods in predictive maintenance for the detection and mitigation of attacks on wireless networks. Using past network data containing different network metrics and security attacks, our developed model predicts possible network attacks. To pass this intercept, users use the supervised learning; this means that the model is trained on labelled datasets, where instances of network attacks were explicitly identified. Save relevant network features using feature engineering and selection to improve model prediction ability. The trained model is then deployed to monitor network traffic continually in real-time to detect anomalous patterns that can indicate potential attacks. By detecting such threats at an early stage, proactive measures such as network reconfiguration, traffic filtering, and incident response can be initiated, minimizing the impact of a cyberattack and maintaining operational continuity. By integrating prediction into maintenance strategy, the book segment combines predictive analytics with traditional maintenance practices, thus facilitating a proactive maintenance framework capable of adjusting to the evolving threat landscape, thereby directly contributing to the literature on future-proofing wireless networks.

KeyWords: Predictive maintenance, supervised machine learning, Wireless networks, Cybersecurity, Predictive modelling, Anomaly detection, Real-time monitoring, Network security management