Design of an improved graph-based model for real-time anomaly detection in healthcare using hybrid CNN-LSTM and federated learning
G Muni Nagamani, Chanumolu Kiran Kumar · 2024
Read Design of an improved graph-based model for real-time anomaly detection in healthcare using hybrid CNN-LSTM and federated learning by G Muni Nagamani, Chanumolu Kiran Kumar (2024) 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/pmc-11696656.txt.
Description
Nagamani and Kumar design a live watch system that flags odd signs in health data while it guards patient privacy, in a paper from 2024. Most watch tools miss mixed patterns across scans and pulse streams, lag on big data, or leak who a patient is. The new design pairs an image net with a time net on a graph frame and trains it across sites without pooling raw data.
On a test set of ten thousand patients the system hit high hit rates with few false alarms. A fast stream pipe kept replies in a blink, even at huge flow. Training across sites held most of its skill while raw records stayed home. A fused read of text, scans, and sensor streams beat any single source by a clear margin.
Catalog record
| CREATOR | G Muni Nagamani, Chanumolu Kiran Kumar |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 110 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |