Published Online:July 2025
Product Name:The IUP Journal of Computer Sciences
Product Type:Article
Product Code:IJCS010725
DOI:10.71329/IUPJCS/2025.19.3.7-20
Author Name:Nikhith Gowda S, Girish G R and Sagar K G
Availability:YES
Subject/Domain:Engineering
Download Format:PDF
Pages:7-20
The paper investigates advanced methods for complete thread analysis, using machine learning (ML) algorithms, real-time data processing, and adaptive computational strategies. The proposed methodology combines multidimensional analysis approaches to investigate computational threads, system relationships, and potential security implications, all at the same time. The goal is to improve cyber-physical infrastructure resilience and reliability by developing intelligent algorithms capable of dynamic threat detection, predictive modeling, and autonomous reaction mechanisms. Innovative pattern recognition approaches, anomaly detection methodologies, and a novel computational model for thread behavior prediction are among the most significant advances. Experimental validation indicates the success of the approach in a variety of cyber-physical systems (CPS) areas, including industrial control systems, smart infrastructure, and autonomous networks. The study considerably increases the understanding of thread-level interactions, providing a solid framework for comprehensive system monitoring and proactive risk mitigation. The suggested intelligent thread analysis methodology is a game-changer that ensures the integrity and performance of the increasingly interconnected CPS.
Cyber-physical systems (CPS) are becoming more common, seamlessly combining computer elements and physical processes across a wide range of sectors, including smart grids, autonomous vehicles, medical devices, and industrial automation (Ashibani & Mahmoud, 2017; Harkat et al., 2024; Nastaran Jadidi & Mohsen Varmazyar, 2022; Rajkumar et al., 2010; Sakinat et al., 2023).