Extraction of Special Time Periods from Automated Monitoring Big Data Based on Statistical Analysis: Differential Analysis and Algorithm Research for Data Across Different Monitoring Periods
Automated monitoring systems significantly impact modern industries and daily life. Currently, most commercially available automated monitoring systems identify the maximum or minimum monitoring values by comparing data points at specific time instances, rather than comparing the average values of o...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | E3S Web of Conferences |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/37/e3sconf_emer2025_02006.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Automated monitoring systems significantly impact modern industries and daily life. Currently, most commercially available automated monitoring systems identify the maximum or minimum monitoring values by comparing data points at specific time instances, rather than comparing the average values of one time period against others. To identify time periods within automated monitoring big data that exhibit significant anomalies compared to others—or to detect such periods within each cycle—this study groups the collected big data by time periods or aggregates monitoring data from identical periods across multiple cycles into datasets. Differential analysis is then performed on these datasets (or data groups). The results demonstrate the feasibility of the research objective in algorithm design, which necessitates the application of mathematical tools such as variance analysis, least squares algorithms, iterative methods, and combinatorial theory. |
|---|---|
| ISSN: | 2267-1242 |