Deep Actor-Critic Reinforcement Learning for Anomaly Detection

Deep Actor-Critic Reinforcement Learning for Anomaly Detection
复制标题

用于异常检测的深度 Actor-Critic 强化学习

DOI:
--
复制
发表时间:
2019
期刊:
Global Communications Conference
影响因子:
--
通讯作者:
Senem Velipasalar
Senem Velipasalar
中科院分区:
--
文献类型:
--
作者:
Chen Zhong;M. C. Gursoy;Senem Velipasalar

文献摘要

参考文献

被引文献

相似文献

异常检测被广泛应用于各种领域,例如,智能家居系统,网络流量监控,物联网应用和传感器网络。本文研究了基于深度强化学习的主动序贯测试异常检测方法。我们假设一次有未知数量的异常进程,并且代理在每个采样步骤中只能使用一个传感器进行检查。为了最大化决策的置信水平并同时最小化停止时间,我们提出了一个深度行动者-评论家强化学习框架,可以根据后验概率动态选择传感器。我们提供了训练阶段和测试阶段的模拟结果,并比较了所提出的框架与索赔延迟和损失方面的Buckoff测试。
Anomaly detection is widely applied in a variety of domains, involving for instance, smart home systems, network traffic monitoring, IoT applications and sensor networks. In this paper, we study deep reinforcement learning based active sequential testing for anomaly detection. We assume that there is an unknown number of abnormal processes at a time and the agent can only check with one sensor in each sampling step. To maximize the confidence level of the decision and minimize the stopping time concurrently, we propose a deep actor-critic reinforcement learning framework that can dynamically select the sensor based on the posterior probabilities. We provide simulation results for both the training phase and testing phase, and compare the proposed framework with the Chernoff test in terms of claim delay and loss.
DOI: 10.1109/tsp.2017.2771722
发表时间: 2017-02
影响因子: 5.4
作者:
Jing Zhang;I. Paschalidis
通讯作者: Jing Zhang;I. Paschalidis
具有切换成本的主动异常检测
DOI: 10.1109/icassp.2019.8683450
发表时间: 2019
期刊: and Signal Processing
影响因子: --
作者:
Chen, Da;Huang, Qiwei;Feng, Hui;Zhao, Qing;Hu, Bo
通讯作者: Hu, Bo
DOI: 10.1109/tit.2018.2866257
发表时间: 2019-04-01
影响因子: 2.5
作者:
Huang, Boshuang;Cohen, Kobi;Zhao, Qing
通讯作者: Zhao, Qing