Wk-fnn design for detection of anomalies in the computer network traffic

Anomaly-based intrusion detection systems identify abnormal computer network traffic based on deviations from the derived statistical model that describes normal behavior. The basic problem with anomaly is deciding what considered normal. Supervised machine learning can be viewed as binary classification, since models are trained and tested a data set containing label to detect anomalies. Weighted k-Nearest Neighbor Feedforward Neural Network high-precision classifiers for decision-making. However, their decisions sometimes differ. In this paper, we present WK-FNN hybrid of opposite decisions. It shown results improved xor bitwise operation. sum ?ones? used decide whether additional alerts activated or not.