AKM$^2$D : An Adaptive Framework for Online Sensing and Anomaly Quantification
This work addresses the challenge of online anomaly quantification in high-cost sensing applications like coordinate measuring machines, offering a domain-specific improvement for inspection processes.
The paper tackles the problem of efficiently detecting sparse anomalies in point-based sensing systems by developing the AKM^2D framework, which uses an adaptive sequential sampling scheme to balance exploration and exploitation, resulting in faster inspection and anomaly detection as validated through simulations and a case study.
In point-based sensing systems such as coordinate measuring machines (CMM) and laser ultrasonics where complete sensing is impractical due to the high sensing time and cost, adaptive sensing through a systematic exploration is vital for online inspection and anomaly quantification. Most of the existing sequential sampling methodologies focus on reducing the overall fitting error for the entire sampling space. However, in many anomaly quantification applications, the main goal is to estimate sparse anomalous regions in the pixel-level accurately. In this paper, we develop a novel framework named Adaptive Kernelized Maximum-Minimum Distance AKM$^2$D to speed up the inspection and anomaly detection process through an intelligent sequential sampling scheme integrated with fast estimation and detection. The proposed method balances the sampling efforts between the space-filling sampling (exploration) and focused sampling near the anomalous region (exploitation). The proposed methodology is validated by conducting simulations and a case study of anomaly detection in composite sheets using a guided wave test.