Transparent Sequential Learning for Online Monitoring of Multivariate Data Streams
Author | : Xiulin Xie |
Publisher | : |
Total Pages | : 0 |
Release | : 2023 |
ISBN-10 | : OCLC:1401937430 |
ISBN-13 | : |
Rating | : 4/5 (30 Downloads) |
Download or read book Transparent Sequential Learning for Online Monitoring of Multivariate Data Streams written by Xiulin Xie and published by . This book was released on 2023 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: Data stream monitoring has received considerable attention in a variety of fields including environmental monitoring, disease surveillance, manufacturing industry, business management, and many more. To sequentially monitor these processes, a major statistical tool is statistical process control (SPC) chart, whose major goal is to check whether a process has a significant distributional shift over time. However, traditional SPC charts are developed mainly for monitoring production lines in the manufacturing industry under the assumptions that process observations at different observation times are independent and identically distributed with a parametric (e.g., normal) distribution when the process is stable. Nevertheless, these assumptions are rarely valid in real-world applications. In this dissertation, we propose a novel learning framework called "Transparent Sequential Learning", which is utilized to develop several new methods for monitoring multivariate data streams. These methods can properly accommodate the longitudinal pattern of the process under monitoring and account for serial correlation in the observed data. They also are not limited to parametric distributional families. These properties make them flexible and effective in monitoring various types of data streams. Numerical studies and real data applications show that the proposed methods work well.