The computation time and the accuracy rate are the two main measurements for evaluating the performance of the IDS. So our goal is to focus on reducing the computation time and finding an efficient detection mechanism to improve the accuracy rate of the proposed algorithm for recognizing the network traffic.
A. Overview The algorithm consists two phases: the classification phase and clustering phase. In the classification phase, the artificial neural network, one of the core methods of Computational Intelligence is used to create the classifier from the known network traffic data. The neural network it identifies the input pattern and tries to output the corresponding class. It can map input patterns to their associated output patterns using their mapping capabilities. They can be trained with known examples of a problem …show more content…
• The iterative learning process in which the input data are presented to the network one by one, and the weights associated with the input values are adjusted each time. After all input values are present, the process starts over again. During this phase, the network learns by adjusting the weights so as to be able to predict the correct class label of input samples. The very first thing that classification algorithm does is to determine attributes (fields) of the labeled patterns that are to be used in the Classification Phase. This is because each pattern may contain a large number of attributes, classification based on all of them is a time consuming task, especially when the number of patterns becomes large. Then, the major procedure of the classification is performed to create the initial classifier based on the set of labeled patterns given.

Algorithm 2: clasification