Abnormal Detection of Wireless Power Terminals in Untrusted Environment Based on Double Hidden Markov Model

The wireless power terminals are deployed in harsh public places and lack strict control, facing security problems. Thus, they faced with problems such as illegal counterfeit terminal access, unlawful control of connected terminals, etc. intrusion detection system based on machine learning artificial intelligence significantly improve the side’s abnormal capacity. In this article, we aim at identifying behavior a double Hidden Markov Model (HMM), which solves computational complexity problem caused by high dimensions systems using single HMM. lower-layer HMM is used to identify discrete network behavior. Simultaneously, upper-layer can obtain more extended period attack multiple independent events identified low-level. experiment results indicate that proposed effectively detect terminal’s for an period.