Asymptotically Optimal Anomaly Detection via Sequential Testing

DOI10.1109/TSP.2015.2416674MaRDI QIDQ4580605zbMATH OpenFDO

Authors Kobi Cohen, Qing Zhao

Publication date 22 August 2018

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1405.4659

Mathematics Subject Classification ID

Detection theory in information and communication theory (94A13) Shift register sequences and sequences over finite alphabets in information and communication theory (94A55)

Abstract: Sequential detection of independent anomalous processes among K processes is considered. At each time, only M processes can be observed, and the observations from each chosen process follow two different distributions, depending on whether the process is normal or abnormal. Each anomalous process incurs a cost per unit time until its anomaly is identified and fixed. Switching across processes and state declarations are allowed at all times, while decisions are based on all past observations and actions. The objective is a sequential search strategy that minimizes the total expected cost incurred by all the processes during the detection process under reliability constraints. Low-complexity algorithms are established to achieve asymptotically optimal performance as the error constraints approach zero. Simulation results demonstrate strong performance in the finite regime.

Cited in

(2)

• Asymptotically optimal sequential multiple testing with asynchronous decisions
• Active Hypothesis Testing for Anomaly Detection

This page was built for publication: Asymptotically Optimal Anomaly Detection via Sequential Testing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4580605)