Tag: multi-class classification

Researchers have developed X-URL, a character-level deep learning framework that classifies malicious URLs into four threat categories with over 98 ...

Researchers have reformulated multi-class classification as a many-objective problem in which each class is a separate goal, using evolutionary neural ...

Researchers have developed a cross-temporal attention network that fuses short-term motion and long-term behavioral cues to recognize gun threats, aggression, ...

Researchers at Yantai University have developed SSAO, an adaptive oversampling method that uses Gaussian mixture model clustering and minimum enclosing ...