A New Feature Selection Approach For Network Intrusion Detection Systems
| dc.contributor.author | CHADOULI, Youssouf | |
| dc.contributor.author | Supervised: Saoudi, lalia | |
| dc.date.accessioned | 2023-05-21T14:34:22Z | |
| dc.date.available | 2023-05-21T14:34:22Z | |
| dc.date.issued | 2014-06-10 | |
| dc.description.abstract | Processing huge amounts of network data is one of the largest challenges for network-based intrusion detection system (IDS). Usually these data contain lots ofirrelevant or redundantfeatures. To improve the efficiency ofIDS, relevantfeatures are necessary to be ectractedfrom original data viafeature selection approaches. In this work, an effective feature selection approach based on Bayesian Network classifier is proposed. And With the same intrusion detecüon benchmark dataset (NSL-KDD), the performance of the proposed approach is evaluated and compared With Other commonly usedfeature selection methods. It is shown by empirical results thatfeatures selected by our approach have decreased the time to ddect attacks and increased the classification accuracy as well as the true positive rates significantly. | en_US |
| dc.identifier.uri | http://dspace.univ-msila.dz:8080//xmlui/handle/123456789/38410 | |
| dc.language.iso | en | en_US |
| dc.publisher | University of M'sila | en_US |
| dc.subject | Networks, intrusion detection systems, feature selection, data mining, classification, Bayesian networks, true positive. | en_US |
| dc.title | A New Feature Selection Approach For Network Intrusion Detection Systems | en_US |
| dc.type | Thesis | en_US |