Radware Ltd.
System and method for real-time tuning of inference systems

Abstract:

A system and method for real-time tuning of inference systems based on quality of incoming data. The method comprises: periodically receiving traffic data collected by a plurality of collectors deployed in a network; determining at least a normalized variance of a current sample of the received traffic data; estimating, based in part on the normalized variance, a standard deviation of the received traffic data and a fading coefficient of a baseline filter; determining a current baseline value based on a previous baseline value, the fading coefficient, and the current sample of the traffic data; and dynamically setting at least one membership function of the inference system based in part on the current baseline value and the standard deviation.