Primary Factor Investigation for Decreasing the Computational Complexity of LAMSTAR DDoS

Nowadays the security is very important for our Computer system networks. Here we use Distributed Denial of Services (DDoS) and it act as a second line of defense in a protected network and looking for threats and its data recorded in a computer. We developed LAMSTAR DDoS a neural network used to know methods of normal and intrusive activities, to classify observed system activities and compared the performance of LAMSTAR DDoS with other classification techniques using 5 classes of KDDCup99 data. LAMSTAR DDoS shows performance is better at a rate of high Computational Complexity, Training time and testing time, when compared to other classification techniques (Binary Tree classifier, RBF classifier, and Gaussian Mixture classifier). We reduce the Complexity of LAMSTAR DDoS by defining the dimension of the data using principal component analysis which in turn the training and testing time gets reduced with performance is same.