期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2015
卷号：6
期号：3
页码：3073-3076
出版社：TechScience Publications
摘要：Data mining is a technique of analyzing the dataset so that some meaningful information can be extracted so that it can be used for various applications. KDDCup 99 is one of the network based dataset which contains a set of attributes of packets and instances which classifies the packets contains anomalous behavior or not. The existing data mining based classification algorithms are used for the classification of packets but the algorithm implemented contain less correctly classified instances and more error rate which needs to be minimized and accuracy is improved, Hence in the paper an efficient technique for the classification of intrusion using improved form of the classification is implemented which is more efficient as compared to the existing classification algorithm. The proposed technique not only improves the classification accuracy but also minimizes the computational time. The proposed algorithm is based on the concept of applying clustering on the KDDCup 99 and then these clusteres values are classified using Grid partition based decision tree
