Visualization of the adaptive learning process showing drift detection and model updating.

<p>Visualization of the adaptive learning process showing drift detection and model updating.</p>

Saved in:

Bibliographic Details
Main Author:	Jun Wang (5906) (author)
Other Authors:	Ning Huang (623370) (author), Houzhong Zhang (22521907) (author), Luyun Liu (18972569) (author), Qiang Fu (129583) (author), Kerang Cao (21602045) (author), Xiwang Guo (22521910) (author), Hoekyung Jung (21602051) (author)
Published:	2025
Subjects:	Developmental Biology Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified term memory networks representing significant improvements new attack patterns knowledge preservation strategy key contributions include 20 hours post network anomaly detection maintains detection capabilities anomaly detection systems temporal traffic patterns day simulated period learning model fusion adaptive learning mechanism proposed framework offers div >< p cicids2017 datasets respectively 4 ± 0 metric drift detection learning mechanism detection rate transformer model proposed cnn framework ’ day attacks anomalous traffic transformer models synergistic two study presents recent methods rapid evolution promising direction normal vs hybrid cnn handling dynamic experiments demonstrate evolving threats developing efficient detect drifts binary classification average accuracy autonomously responds
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items