Paper
23 August 2023 Two-phase control chart monitoring binomial high-dimensional data streams
Zhifang Mu, Xuemin Zi
Author Affiliations +
Proceedings Volume 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023); 127842R (2023) https://doi.org/10.1117/12.2692812
Event: 2023 2nd International Conference on Applied Statistics, Computational Mathematics and Software Engineering (ASCMSE 2023), 2023, Kaifeng, China
Abstract
In many practical applications, the research object can only produce two results, and their distribution follows binomial distribution. In the age of big data, the scale of data streams available for monitoring will continue to grow, and there is an unprecedented demand for an efficient monitoring scheme for high-dimensional binomial data streams . However, the existing monitoring scheme is to directly apply the error detection rate (FDR) control program to the data at each time point. The generated process will not control the global FDR, and users will not be able to obtain the desired controlled average running length(IC ARL). In order to solve these problems, this paper adopts a two-phase monitoring scheme motivated by Li(2018) that constructed the two-phase control chart for normal distribution concerning both global FDR and pointwise FDR. In the first stage, it detects whether there is a data flow that is out of control, and in the second stage, it detects the specific location of the data flow that is out of control. Numerical simulation show that the proposed two-phase monitoring scheme based on binomial distribution outperforms the existing methods.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhifang Mu and Xuemin Zi "Two-phase control chart monitoring binomial high-dimensional data streams", Proc. SPIE 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023), 127842R (23 August 2023); https://doi.org/10.1117/12.2692812
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Fourier transforms

Lithium

Numerical simulations

Process control

Algorithm development

Error analysis

Medical statistics

Back to Top