Bayesian Online Classification using RAO-Blackwellised SMC and Its Application

T. Kudo, Y. Nakada, and T. Matsumoto (Japan)


On-line classification, on-line Bayesian learning, Rao Blackwellised sequential Monte Carlo, and computer in trusion detection


This paper proposes a Bayesian online classification method using Rao-Blackwellised Sequential Monte Carlo. The method is validated by testing it against a numerical example. As an example of a real-world application, the method is also applied to a computer intrusion detection problem. The proposed method has succeeded in reducing the false alarm rate when compared with a previous work.

Important Links:

Go Back