TY - GEN
T1 - A Scalable Algorithm for Anomaly Detection via Learning-Based Controlled Sensing
AU - Joseph, Geethu
AU - Gursoy, M. Cenk
AU - Varshney, Pramod K.
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/6
Y1 - 2021/6
N2 - We address the problem of sequentially selecting and observing processes from a given set to find the anomalies among them. The decision maker observes one process at a time and obtains a noisy binary indicator of whether or not the corresponding process is anomalous. In this setting, we develop an anomaly detection algorithm that chooses the process to be observed at a given time instant, decides when to stop taking observations, and makes a decision regarding the anomalous processes. The objective of the detection algorithm is to arrive at a decision with an accuracy exceeding a desired value while minimizing the delay in decision making. Our algorithm relies on a Markov decision process defined using the marginal probability of each process being normal or anomalous, conditioned on the observations. We implement the detection algorithm using the deep actor-critic reinforcement learning framework. Unlike prior work on this topic that has exponential complexity in the number of processes, our algorithm has computational and memory requirements that are both polynomial in the number of processes. We demonstrate the efficacy of our algorithm using numerical experiments by comparing it with the state-of-the-art methods.
AB - We address the problem of sequentially selecting and observing processes from a given set to find the anomalies among them. The decision maker observes one process at a time and obtains a noisy binary indicator of whether or not the corresponding process is anomalous. In this setting, we develop an anomaly detection algorithm that chooses the process to be observed at a given time instant, decides when to stop taking observations, and makes a decision regarding the anomalous processes. The objective of the detection algorithm is to arrive at a decision with an accuracy exceeding a desired value while minimizing the delay in decision making. Our algorithm relies on a Markov decision process defined using the marginal probability of each process being normal or anomalous, conditioned on the observations. We implement the detection algorithm using the deep actor-critic reinforcement learning framework. Unlike prior work on this topic that has exponential complexity in the number of processes, our algorithm has computational and memory requirements that are both polynomial in the number of processes. We demonstrate the efficacy of our algorithm using numerical experiments by comparing it with the state-of-the-art methods.
KW - Active hypothesis testing
KW - actor-critic algorithm
KW - anomaly detection
KW - deep learning
KW - quickest state estimation
KW - reinforcement learning
KW - sequential decision-making
KW - sequential sensing
UR - http://www.scopus.com/inward/record.url?scp=85115696772&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85115696772&partnerID=8YFLogxK
U2 - 10.1109/ICC42927.2021.9500644
DO - 10.1109/ICC42927.2021.9500644
M3 - Conference contribution
AN - SCOPUS:85115696772
T3 - IEEE International Conference on Communications
BT - ICC 2021 - IEEE International Conference on Communications, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Conference on Communications, ICC 2021
Y2 - 14 June 2021 through 23 June 2021
ER -