{"created":"2020-08-30T13:55:54.078138+00:00","id":3112,"links":{},"metadata":{"_buckets":{"deposit":"d00d9f87-46e1-4c4b-b7e3-6a2374a5ed63"},"_deposit":{"id":"3112","owners":[],"pid":{"revision_id":0,"type":"recid","value":"3112"},"status":"published"},"_oai":{"id":"oai:meral.edu.mm:recid/3112","sets":["1582963413512:1596119372420"]},"communities":["ytu"],"item_1583103067471":{"attribute_name":"Title","attribute_value_mlt":[{"subitem_1551255647225":"Association Rule Pattern Mining Approaches Network Anomaly Detection","subitem_1551255648112":"en"}]},"item_1583103085720":{"attribute_name":"Description","attribute_value_mlt":[{"interim":"
The research area for intrusion detection is becoming growth with new challenges of attack day by
\nday. Intrusion detection system includes identifying a set of malicious actions that compromise the integrity,
\nconfidentiality, and availability of information resources. The major objective of this paper is to apply
\nassociation rule pattern mining approaches for network intrusion detection system. In this paper, traditional FP-
\ngrowth algorithm, one of the association algorithms is modified and used to mine itemsets from large database.
\nThe required statistics from large databases are gathered into a smaller data structure (FP-tree). The itemsets
\ngenerated from FP-tree are used as profiles to check anomaly detection in the proposed system.