Improved TLBO-JAYA Algorithm for Subset Feature Selection and Parameter Optimisation in Intrusion Detection System

被引:21
作者
Aljanabi, Mohammad [1 ,2 ]
Ismail, Mohd Arfian [2 ]
Mezhuyev, Vitaly [3 ]
机构
[1] Aliraqia Univ, Coll Educ, Baghdad, Iraq
[2] Univ Malaysia Pahang, Fac Comp, Coll Comp & Appl Sci, Gambang, Malaysia
[3] FH Joanneum Univ Appl Sci, Inst Ind Management, Graz, Austria
关键词
LEARNING-BASED OPTIMIZATION;
D O I
10.1155/2020/5287684
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Many optimisation-based intrusion detection algorithms have been developed and are widely used for intrusion identification. This condition is attributed to the increasing number of audit data features and the decreasing performance of human-based smart intrusion detection systems regarding classification accuracy, false alarm rate, and classification time. Feature selection and classifier parameter tuning are important factors that affect the performance of any intrusion detection system. In this paper, an improved intrusion detection algorithm for multiclass classification was presented and discussed in detail. The proposed method combined the improved teaching-learning-based optimisation (ITLBO) algorithm, improved parallel JAYA (IPJAYA) algorithm, and support vector machine. ITLBO with supervised machine learning (ML) technique was used for feature subset selection (FSS). The selection of the least number of features without causing an effect on the result accuracy in FSS is a multiobjective optimisation problem. This work proposes ITLBO as an FSS mechanism, and its algorithm-specific, parameterless concept (no parameter tuning is required during optimisation) was explored. IPJAYA in this study was used to update the C and gamma parameters of the support vector machine (SVM). Several experiments were performed on the prominent intrusion ML dataset, where significant enhancements were observed with the suggested ITLBO-IPJAYA-SVM algorithm compared with the classical TLBO and JAYA algorithms.
引用
收藏
页数:18
相关论文
共 43 条
[1]   A novel weighted support vector machines multiclass classifier based on differential evolution for intrusion detection systems [J].
Aburomman, Abdulla Amin ;
Reaz, Mamun Bin Ibne .
INFORMATION SCIENCES, 2017, 414 :225-246
[2]   Deep Learning Approach Combining Sparse Autoencoder With SVM for Network Intrusion Detection [J].
Al-Qatf, Majjed ;
Yu Lasheng ;
Al-Habib, Mohammed ;
Al-Sabahi, Kamal .
IEEE ACCESS, 2018, 6 :52843-52856
[3]  
Aljarah I, 2013, 2013 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), P955
[4]   Anomaly-based intrusion detection system through feature selection analysis and building hybrid efficient model [J].
Aljawarneh, Shadi ;
Aldwairi, Monther ;
Yassein, Muneer Bani .
JOURNAL OF COMPUTATIONAL SCIENCE, 2018, 25 :152-160
[5]   A review on the recent application of Jaya optimization algorithm [J].
Alsajri, Mohammad ;
Ismail, Mohd Arfian ;
Salamn, Saba Abdul-baqi .
2018 1ST ANNUAL INTERNATIONAL CONFERENCE ON INFORMATION AND SCIENCES (AICIS 2018), 2018, :129-132
[6]   An effective intrusion detection framework based on MCLP/SVM optimized by time-varying chaos particle swarm optimization [J].
Bamakan, Seyed Mojtaba Hosseini ;
Wang, Huadong ;
Tian Yingjie ;
Shi, Yong .
NEUROCOMPUTING, 2016, 199 :90-102
[7]   A note on teaching-learning-based optimization algorithm [J].
Crepinsek, Matej ;
Liu, Shih-Hsi ;
Mernik, Luka .
INFORMATION SCIENCES, 2012, 212 :79-93
[8]   Novel hybrid SVM-TLBO forecasting model incorporating dimensionality reduction techniques [J].
Das, Shom Prasad ;
Achary, N. Sangita ;
Padhy, Sudarsan .
APPLIED INTELLIGENCE, 2016, 45 (04) :1148-1165
[9]   A novel hybrid model using teaching-learning-based optimization and a support vector machine for commodity futures index forecasting [J].
Das, Shom Prasad ;
Padhy, Sudarsan .
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2018, 9 (01) :97-111
[10]  
Dash M., 1997, Intelligent Data Analysis, V1