A dual-stream deep learning architecture for business impact scoring and alert escalation
Mohammed Saad Javeed, Mst Moushumi Khatun, Jobayar Alom, Rahomotul Islam, Hashibul Ahsan Shoaib · 2026
Read A dual-stream deep learning architecture for business impact scoring and alert escalation by Mohammed Saad Javeed, Mst Moushumi Khatun, Jobayar Alom, Rahomotul Islam, Hashibul Ahsan Shoaib (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0350676.txt.
Description
Javeed and colleagues built a two-stream AI system for sorting network alerts by business importance in a 2026 study. Control centers drown in alerts, and raw oddity scores ignore how much a failure would hurt services. One stream learns time patterns in performance data, while the other reads context about risk and service value.
Merged scores decide which alerts to escalate first, weighted by business impact rather than oddity alone. Tests on public network data plus a factory data set for severity context showed earlier, sharper escalation of serious events and lower running costs. The design speaks to a daily pain in operations: too many alarms, too little guidance on which matter.
Catalog record
| CREATOR | Mohammed Saad Javeed, Mst Moushumi Khatun, Jobayar Alom, Rahomotul Islam, Hashibul Ahsan Shoaib |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60870 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |