Nonlinear Time Series Analysis for Anomaly Detection in Cybersecurity using Cloud IoT

Abstract

The CloudIoT is an extensive network that hosts several IoT gadgets and apps. This comprises the servers and the storage space required for real-time processing and operations. For commercial purposes, data gathered by IoT devices may be safely saved and handled on the cloud. CloudIoT allows for the scalable distribution of software. IoT devices capture information using built-in sensors and monitors. After collection, it is sent to a central location where data from other Internet of Things devices is kept. Cloud storage offers a scalable, cost-effective alternative for maintaining and administering IoT data—the capacity to grow or change quickly. More and more Internet of Things devices means a greater need for data storage and processing capacity. The cloud computing solution is scalable and adaptable enough to meet these shifting requirements.  Hence, this paper proposes a nonlinear time series analysis for enhancing anomaly detection in cybersecurity based on Cloud-Internet of Things (CloudIoT-CS). Statistics like precision and positive and negative results are considered part of assessing the suggested methodology by comparing it against conventional anomaly detection techniques. The study also looks at the system's resistance to hostile assaults, guaranteeing its efficacy in practical cybersecurity settings. This study's findings provide a holistic and flexible approach that accounts for the unique challenges posed by CloudIoT settings. As well as improving the precision of anomaly identification, integrating nonlinear time series evaluation with CloudIoT creates a scalable and robust framework for protecting vital systems from ever-evolving cyber threats.