ARCHIVES

Massive amounts of real-time data are being generated by linked devices including sensors, smart systems, and industrial equipment as a result of the Internet of Things' (IoT) explosive growth. Although intelligent automation and monitoring are made possible by this data, problems with system security, dependability, and fault detection are also brought about. The goal of this study, "An Intelligent AI-Driven Framework for Real-Time Anomaly Detection in Internet of Things (IoT Systems)," is to effectively identify anomalous patterns and possible dangers in IoT environments.The suggested framework analyzes continuous data streams produced by IoT devices by combining cutting-edge AI and machine learning algorithms. To find departures from typical behavior, it uses real-time analytics, feature extraction, and data pretreatment. Clustering algorithms and autoencoders are examples of unsupervised and semi-supervised learning models that are used to find anomalies without the need for large labeled datasets. To facilitate low-latency processing and quicker reaction times, the framework also integrates edge computing capabilities.