AAAI Publications, Twenty-Third International FLAIRS Conference

Font Size: 
Incrementally Learning Rules for Anomaly Detection
Denis Petrussenko, Philip K. Chan

Last modified: 2010-05-06


LERAD is a rule learning algorithm used for anomaly detection, with the requirement that all training data has to be present before it can be used. We desire to create rules incrementally, without needing to wait for all training data and without sacrificing accuracy. The algorithm presented accomplishes these goals by carrying a small amount of data between days and pruning rules after the final day. Experiments show that both goals were accomplished, achieving similar accuracy with fewer rules.


machine learning; anomaly detection; incremental; rule learning; lerad

Full Text: PDF