Intrusion Detection Using Ensemble Wrapper Filter Based Feature Selection with Stacking Model

作     者：D.Karthikeyan V.Mohan Raj J.Senthilkumar Y.Suresh 

作者机构：Department of ECEKongunaduCollege of Engineering and TechnologyTrichy621215India Department of ITSona College of TechnologySalem636005India 

出 版 物：《Intelligent Automation & Soft Computing》 (智能自动化与软计算（英文）)

年 卷 期：2023年第35卷第1期

页      面：645-659页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Intrusion detection system(IDS) ensemble wrapperfilter(EWF) stacking model with significant rule power factor(SMSRPF) classifier 

摘      要：The number of attacks is growing tremendously in tandem with the growth of internet *** a result,protecting the private data from prying eyes has become a critical and tough *** intrusion detection solutions have been offered by researchers in order to decrease the effect of these *** attack detection,the prior system has created an SMSRPF(Stacking Model Significant Rule Power Factor)*** provide creative instance detection,the SMSRPF combines the detection of trained classifiers such as DT(Decision Tree)and RF(Random Forest).Nevertheless,it does not generate any accuratefindings that are *** suggested system has built an EWF(Ensemble Wrapper Filter)feature selection with SMSRPF classifier for attack detection so as to overcome this *** UNSW-NB15 dataset is used as an input in this proposed research ***,min–max normalization approach is used to pre-process the incoming *** feature selection is then carried out using *** on the selected features,SMSRPF classifiers are utilized to detect the *** SMSRPF is integrated with the trained classi-fiers such as DT and RF to create creative instance *** that,the testing data is classified using MCAR(Multi-Class Classification based on Association Rules).The SRPF judges the rules correctly even when the confidence and the lift measures *** accuracy,precision,recall,f-measure,computation time,and error,the experimental findings suggest that the new system outperforms the prior systems.