2026-06-25T05:50:23Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/4468 2021-12-13T01:58:46Z 1582963302567:1597824273898 user-ucsy

A Framework for Intrusion Detection System Using Random Forests and Support Vector Machine Oo, May Mar Yi, Aye Mon Due to continuous growth of the Internettechnology, it needs to establish securitymechanism. However, many current intrusiondetection systems (IDSs) are rule-based systems,which have limitations to detect novel intrusions.Moreover, encoding rules is time-consuming andhighly depends on the knowledge of knownintrusions. Therefore, we propose new systematicframework that apply a data mining algorithmcalled random forests (RF) and Support VectorMachine (SVM). This system uses RandomForests (RF) for feature selection and parameteroptimization and Support Vector Machine (SVM)for intrusion detection. RF provides the variableimportance by numeric values so that theirrelevant features can be eliminated. SupportVector Machines (SVM) as a classical patternrecognition tool have been widely used forintrusion detection. First, RF is utilized topreprocess the data and select the mostimportant features to eliminate the insignificantfeatures and optimize parameters. Second, SVMmodel is used to learn and detect intrusion usingselected important features. 2012-02-28 http://hdl.handle.net/20.500.12678/0000004468 https://meral.edu.mm/records/4468