查看文章

Anomaly detection techniques have attracted more attention in research and industrial areas. Anomaly detection methods have been implemented in many tenders, such as detecting malicious traffic in networks and systems, discovering vulnerabilities in security systems, detecting fraud transactions in credit cards, detecting anomalies in imaging processing, and analyzing and visualizing data in various domains. The IoT ecosystem involves applications like intelligent homes, smart cities, and smart transportation systems. With the increasing necessity for analyzing IoT network behavior, it becomes difficult to efficiently apply traditional anomaly detection techniques. The conventional techniques that use deep learning (DL) or machine learning (ML) do not detect or monitor the IoT ecosystem efficiently and effectively because they do not consider the nature of the IoT ecosystem. Another issue with traditional anomaly detection techniques is that they recalculate training whenever any change from the start points. Furthermore, they depend on a static threshold throughout the training period. This does not fit with the nature of the IoT ecosystem, which is characterized by a dynamic environment. This chapter will discuss the autonomous anomaly detection system for the Internet of Things (IoT) using ML. Specifically, we focus on the dynamic threshold that can be adapted during the training time, such as the local–global ratio technique (LGR) method, which activates the rehabilitating merely when it is essential and precludes any superfluous variations from immaterial differences in the local profiles.