Novel adaptive Bayesian scheme for real-time simultaneous anomaly detection and system identification

Dukang Huang, Ke Huang, Lei Xiao, Yafei Ma, Ka-Veng Yuen, Lei Wang

Abstract: Highlights•A real-time anomaly detection scheme is proposed for system identification.•The method eliminates the need for fixed threshold settings in anomaly detection.•Statistical models characterize typical types of measurement anomalies.•Multiple anomaly types are detected using Bernoulli random vectors.•Bernoulli and structural parameters are updated online via Bayesian inference.

External IDs:doi:10.1016/j.ymssp.2025.113051