Throughout the decades, guaranteeing security of systems has been a noteworthy concern; the open-finished nature of systems however advancing its usability and network has moreover contributed its security challenges. Interruption Detection System is one of fitting region for specialists since long. Quantities of scientists have worked for extending capability of Intrusion Detection Systems. However in the meantime various troubles are accessible in current Intrusion Detection Systems. One of the genuine challenges is controlling false positive rate. In this paper we have proposed a capable soft computing system for grouping of intrusion detection data set to diminish false positive rate. The proposed technique steps are portrayed as; input data is at first per-processed by the data transformation and normalization process. After the normalization process, estimated entropy for all the features and finally entropy based graph is constructed for the effective classification of data into intrusion or normal data. The experimental results will demonstrate that our proposed strategy outperforms other existing methods in terms of various performance analyses like accuracy, sensitivity, specificity, false discovery rate (FDR) and false positive rate (FPR).
Volume 11 | 02-Special Issue
Pages: 1-10