报告题目：Large-Scale Datastreams Surveillance via Pattern-Oriented-Sampling

报告所属学科：管理科学与工程

报告人：Chen Nan（National University of Singapore）

报告时间：2023年11月9日 15:00-17:00

报告地点：经管学院702室

报告摘要：

Monitoring large-scale data streams with limited resources has become increasingly important for real-time detection of abnormal activities in many applications. Despite the availability of large datasets, the challenges associated with designing an efficient change-detection when clustering or spatial pattern exists are not yet well addressed. In this paper, a design-adaptive testing procedure is developed when only a limited number of streaming observations can be accessed at each time. We derive an optimal sampling strategy, the pattern-oriented-sampling, with which the proposed test possesses asymptotically and locally best power under alternatives. Then, a sequential change-detection procedure is proposed by integrating this test with generalized likelihood ratio approach. Benefiting from dynamically estimating the optimal sampling design, the proposed procedure is able to improve the sensitivity in detecting clustered changes compared with existing procedures. Its advantages are demonstrated in numerical simulations and a real data example. Ignoring the neighboring information of spatially structured data will tend to diminish the detection effectiveness of traditional detection procedures.

报告人简介：

Chen Nan is currently an Associate Professor at the department of Industrial Systems Engineering and Management at NUS. He is also the deputy head in charge of the graduate programs in the department. He obtained his Bachelor degree from Tsinghua University, Master and PhD degree from University of Wisconsin Madison. His research focused on data driven modelling, monitoring, and process improvement, with applications in manufacturing and service systems. He is currently, or has been the department editor of IISE Transactions, associate editor of INFORMS Journal on Data Science, associate editor of Technimetrics, etc.