2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于天牛群优化与改进正则化极限学习机的网络入侵检测

王振东 刘尧迪 杨书新 王俊岭 李大海

王振东, 刘尧迪, 杨书新, 王俊岭, 李大海. 基于天牛群优化与改进正则化极限学习机的网络入侵检测. 自动化学报, 2022, 48(12): 3024−3041 doi: 10.16383/j.aas.c190851
引用本文: 王振东, 刘尧迪, 杨书新, 王俊岭, 李大海. 基于天牛群优化与改进正则化极限学习机的网络入侵检测. 自动化学报, 2022, 48(12): 3024−3041 doi: 10.16383/j.aas.c190851
Wang Zhen-Dong, Liu Yao-Di, Yang Shu-Xin, Wang Jun-Ling, Li Da-Hai. Network intrusion detection based BSO and improved RELM. Acta Automatica Sinica, 2022, 48(12): 3024−3041 doi: 10.16383/j.aas.c190851
Citation: Wang Zhen-Dong, Liu Yao-Di, Yang Shu-Xin, Wang Jun-Ling, Li Da-Hai. Network intrusion detection based BSO and improved RELM. Acta Automatica Sinica, 2022, 48(12): 3024−3041 doi: 10.16383/j.aas.c190851

基于天牛群优化与改进正则化极限学习机的网络入侵检测

doi: 10.16383/j.aas.c190851
基金项目: 国家自然科学基金(61562037, 61562038, 61563019, 61763017), 江西省自然科学基金(20171BAB202026, 20181BBE58018)资助
详细信息
    作者简介:

    王振东:博士, 江西理工大学信息工程学院副教授. 主要研究方向为无线传感器网络, 智能物联网, 认知计算, 大数据和信息安全.E-mail: wangzhendong@hrbeu.edu.cn

    刘尧迪:江西理工大学信息工程学院硕士研究生. 主要研究方向为网络安全, 入侵检测, 群智能优化算法, 机器学习与深度学习. 本文通信作者.E-mail: liuyaodi@yeah.net

    杨书新:博士, 江西理工大学信息工程学院副教授. 主要研究方向为数据管理, 信息检索和生物信息学.E-mail: yimuyunlang@sina.com

    王俊岭:博士, 江西理工大学信息工程学院副教授. 主要研究方向为分布式计算, 容错, 计算机视觉.E-mail: wangjunling@jxust.edu.cn

    李大海:博士, 江西理工大学信息工程学院副教授. 主要研究方向为分布式系统服务质量控制, 分布式系统自学资源调度控制.E-mail: dlai6535@aliyun.com

Network Intrusion Detection Based BSO and Improved RELM

Funds: Supported by National Natural Science Foundation of China (61562037, 61562038, 61563019, 61763017) and Natural Science Foundation of Jiangxi Province (20171BAB202026, 20181BBE58018)
More Information
    Author Bio:

    WANG Zhen-Dong Ph.D., associate professor at the School of Information Engineering, Jiangxi University of Science and Technology. His research interest covers wireless sensor networks, smart internet of things, cognitive computing, and big data and information security

    LIU Yao-Di Master student at the School of Information Engineering, Jiangxi University of Science and Technology. Her research interest covers network security, intrusion detection, swarm intelligence optimization algorithm, machine learning, and deep learning. Corresponding author of this paper

    YANG Shu-Xin Ph.D., associate professor at the School of Information Engineering, Jiangxi University of Science and Technology. His research interest covers data management, information retrieval, and bioinformatics

    WANG Jun-Ling Ph.D., associate professor at the School of Information Engineering, Jiangxi University of Science and Technology. His research interest covers distributed computing, fault tolerance, and computer vision

    LI Da-Hai Ph.D., associate professor at the School of Information Engineering, Jiangxi University of Science and Technology. His research interest covers distributed system quality of service (QoS) control, and distributed system self-learning resource scheduling control

  • 摘要: 正则化极限学习机(Regularized extreme learning machine, RELM)因其极易于实现、训练速度快等优点在诸多领域均取得了成功应用. 对此, 本文将RELM引入到入侵检测中, 设计了天牛群优化算法(Beetle swarm optimization, BSO), 并针对RELM由于随机初始化参数带来的潜在缺陷, 提出基于天牛群优化与改进正则化极限学习机(BSO-IRELM)的网络入侵检测算法. 使用LU分解求解RELM的输出权值矩阵, 进一步缩短了RELM的训练时间, 同时利用BSO对RELM的权值和阈值进行联合优化. 为避免BSO算法陷入局部最优, 引入Tent映射反向学习、莱维飞行的群体学习与动态变异策略提升优化性能. 实验结果表明, 在机器学习UCI数据集上, 相比于RELM、IRELM、GA-IRELM、PSO-IRELM等算法, BSO-IRELM的数据分类性能提升明显. 最后, 将BSO-IRELM应用于网络入侵检测数据集NSL-KDD, 并与BP (Back propagation)、LR (Logistics regression)、RBF (Radial basis function)、AB (AdaBoost)、SVM (Support vector machine)、RELM、IRELM等算法进行了对比, 结果证明BSO-IRELM算法在准确率、精确率、真正率和假正率等指标上均具有明显优势.
  • 图  1  莱维飞行轨迹示意图

    Fig.  1  Levy flight path diagram

    图  2  柯西变异概率分布图

    Fig.  2  Cauchy variation probability distribution map

    图  3  天牛群算法流程图

    Fig.  3  Flow chart of BSO algorithm

    图  4  算法测试结果图

    Fig.  4  Test result graph of algorithm

    图  5  BSO-IRELM算法入侵检测框架图

    Fig.  5  BSO-IRELM Algorithm intrusion detection framework

    图  6  部分算法在UCI数据集上的检测结果

    Fig.  6  The detection results of part algorithm on UCI dataset

    图  7  2元分类混淆矩阵

    Fig.  7  Binary classification confusion matrix

    图  8  2元分类ROC曲线对比图

    Fig.  8  Binary classification of ROC curve comparison diagram

    图  9  多元分类混淆矩阵

    Fig.  9  Multiple classification confusion matrix

    图  10  多元分类ROC曲线对比图

    Fig.  10  Multiple classification ROC curve comparison diagram

    表  1  群智能算法参数

    Table  1  Swarm intelligence algorithm parameters

    参数参数
    自学习因子2.4群体学习因子1.6
    交叉概率0.7遗传概率0.5
    惯性权重0.8种群数量50
    比例系数0.4, 0.6惩罚因子0.5
    下载: 导出CSV

    表  2  UCI数据集

    Table  2  UCI dataset

    数据集维度类别数样本总数测试样本数
    Iris4315030
    Wine13317830
    下载: 导出CSV

    表  3  各算法在UCI数据集上的准确率(%)

    Table  3  Accuracy of each algorithm on UCI dataset (%)

    数据集RELMIRELMGA-IRELMPSO-IRELMBSO-RELMBSO-IRELM
    Iris76.6667 (23/30)90 (27/30)96.6667 (29/30)100 (30/30)100 (30/30)100 (30/30)
    Wine80 (24/30)90 (27/30)93.3333 (28/30)93.3333 (28/30)93.3333 (28/30)96.6666 (29/30)
    下载: 导出CSV

    表  4  各算法在Iris数据集上的性能评价指标

    Table  4  Performance evaluation index of each algorithm on Iris dataset

    算法类别精确率 (%)TPR (%)FPR (%)F值 (%)AUC
    RELM1100 (9/9)81.8182 (9/1)0 (0/14)900.9091
    250 (5/10)83.3333 (5/6)21.7391 (5/23)62.50.8125
    381.8182 (9/11)69.2308 (9/13)12.5 (2/16)750.7873
    IRELM1100 (8/8)100 (8/8)0 (0/19)1001
    275 (9/12)100 (9/9)14.2857 (3/21)85.71430.9286
    3100 (10/10)76.9231 (10/13)0 (0/17)86.95650.8846
    GA-IRELM1100 (13/13)100 (13/13)0 (0/16)1001
    2100 (7/7)87.5 (7/8)0 (0/22)93.33330.9375
    390 (9/10)100 (9/9)4.7619 (1/21)94.73680.9762
    PSO-IRELM1100 (8/8)100 (8/8)0 (0/22)1001
    2100 (12/12)100 (12/12)0 (0/28)1001
    3100 (10/10)100 (10/10)0 (0/20)1001
    BSO-RELM1100 (13/13)100 (13/13)0 (0/17)1001
    2100 (10/10)100 (10/10)0 (0/20)1001
    3100 (7/7)100 (7/7)0 (0/23)1001
    BSO-IRELM1100 (12/12)100 (12/12)0 (0/18)1001
    2100 (5/5)100 (5/5)0 (0/25)1001
    3100 (13/13)100 (13/13)0 (0/17)1001
    下载: 导出CSV

    表  5  各算法在Wine数据集上的性能评价指标

    Table  5  Performance evaluation index of each algorithm on Wine dataset

    算法类别精确率 (%)TPR (%)FPR (%)F值 (%)AUC
    RELM181.8182 (9/11)100 (9/9)11. 7647 (2/17)900.9524
    266.6667 (8/12)80 (8/10)20 (4/20)72.72730.8000
    3100 (7/7)63.6364 (7/11)0 (0/17)77.77780.8182
    IRELM188.8889 (8/9)88.8889 (8/9)5 (1/20)88.88890.9206
    290.9091 (10/11)83.3333 (10/12)5.5556 (1/18)86.95650.8889
    390 (9/10)100 (9/9)5.2632 (1/19)94.73680.9762
    GA-IRELM187.5 (7/8)100 (7/7)4. 5455 (1/22)93. 33330.9783
    2100 (16/16)88. 8889 (16/18)0 (0/12)94.11760.9444
    383.3333 (5/6)100 (5/5)4.1667 (1/24)90.90910.9800
    PSO-IRELM190 (9/10)100 (9/9)5 (1/20)94.73680.9762
    290. 9091 (10/11)90.9091 (10/11)5.2632 (1/19)90.90910.9282
    3100 (9/9)90 (9/10)0 (0/19)94.73680.9500
    BSO-RELM190.9091 (10/11)100 (10/10)5.2632 (1/19)95.23810.9750
    287.5 (7/8)87.5 (7/8)4.5455 (1/22)87.50.9148
    3100 (11/11)91.6667 (11/12)0 (0/17)95.65220.9583
    BSO-IRELM1100 (12/12)92.3077 (12/13)0 (0/17)960.9615
    292.3077 (12/13)100 (12/12)5.5556 (1/18)960.9722
    3100 (5/5)100 (5/5)0 (0/24)1001
    下载: 导出CSV

    表  6  各算法的准确率(%)

    Table  6  Accuracy of each algorithm (%)

    算法 准确率
    BP 78.1 (1562/2000)
    LR 81.3 (1626/2000)
    RBF 88.9 (1778/2000)
    AB 86.15 (1723/2000)
    SVM 91.15 (1823/2000)
    RELM 81.45 (1629/2000)
    IRELM 83.9 (1678/2000)
    GA-IRELM 89.5 (1790/2000)
    PSO-IRELM 90.45 (1809/2000)
    BSO-IRELM 91.25 (1825/2000)
    下载: 导出CSV

    表  7  各算法的性能评价指标

    Table  7  Performance evaluation index of each algorithm

    算法类别精确率 (%)TPR (%)FPR (%)F值 (%)AUC
    BP145.2915 (303/669)80.8 (303/375)22.5231 (366/1625)58.0460.7914
    294.5905 (1259/1331)77.4769 (1259/1625)19.2 (72/375)85.18270.7914
    LR185.7143 (6/7)1.5831 (6/379)0.06169 (1/1621)3.10880.5076
    281.2845 (1620/1993)99.9383 (1620/1621)98.4169 (373/379)89.65140.5076
    RBF167.8663 (264/389)73.1302 (264/361)7.6266 (125/1639)70.40.8275
    293.9789 (1514/1611)92.3734 (1514/1639)26.8698 (97/361)93.16920.8275
    AB167.9825 (155/228)43.1755 (155/359)4.4485 (73/1641)52.81090.6936
    288.4876 (1568/1772)95.5515 (1568/1641)56.8245 (204/359)91.8840.6936
    SVM189.7674 (193/215)55.4598 (193/348)1.3317 (22/1652)68.56130.7706
    291.3165 (1630/1785)98.6683 (1630/1652)44.5402 (155/348)94.85020.7706
    RELM153.6339 (140/261)35.8974 (140/390)7.5155 (121/1610)43.00880.6711
    285.6239 (1489/1739)92.4844 (1489/1610)64.1025 (250/390)88.92200.7076
    IRELM155.5556 (145/261)41.3105 (145/351)7.0346 (116/1649)47.38560.6714
    288.1541 (1533/1739)92.9654 (1533/1649)58.6894 (206/351)90.49580.7280
    GA-IRELM188.8412 (207/233)52.9412 (20/391)1.6159 (26/1609)66.34620.7566
    289.5868 (1583/1767)98.3840 (1583/1609)47.0588 (184/391)93.77920.7955
    PSO-IRELM184.5588 (230/272)60.686 (230/379)2.5910 (42/1621)70.66050.7905
    291.3773 (1579/1728)97.4090 (1579/1621)39.3139 (149/379)94.29670.8066
    BSO-IRELM186.747 (216/249)60.3352 (216/358)2.0097 (33/1642)71.16970.7916
    291.9428 (1609/1751)97.9902 (1609/1642)39.6648 (142/358)94.87020.8416
    下载: 导出CSV

    表  8  不同算法检测准确率(%)

    Table  8  Accuracy of different algorithms (%)

    算法 准确率
    BP 73.1 (1462/2000)
    LR 47.2 (944/2000)
    RBF 81.95 (1639/2000)
    AB 76.05 (1521/2000)
    SVM 83.15 (1663/2000)
    RELM 62.7 (1254/2000)
    IRELM 71.9 (1438/2000)
    GA-IRELM 86.35 (1727/2000)
    PSO-IRELM 86.15 (1723/2000)
    BSO-IRELM 88.7 (1774/2000)
    下载: 导出CSV

    表  9  各算法在Normal上的性能评价指标

    Table  9  Performance evaluation index of each algorithm on Normal

    算法精准率 (%)TPR (%)FPR (%)F值 (%)AUC
    BP77.7778 (14/18)3.8674 (14/362)0.27548 (4/1452)7.36840.5181
    LR76.4706 (13/17)3.6723 (13/354)0.42781 (4/935)7.00810.5172
    RBF66.9377 (247/369)73.5119 (247/336)8.0581 (122/1514)70.07090.8301
    AB52.3517 (256/489)66.8407 (256/383)15.5541 (233/1498)58.71560.7622
    SVM91.2863 (220/241)63.0372 (220/349)1.4344 (21/1464)74.57630.8088
    RELM89.5238 (188/210)53.4091 (188/352)2.0221 (22/1088)66.90390.7604
    IRELM49.7619 (209/420)58.3799 (209/358)14.6528 (211/1440)53.72750.7277
    GA-IRELM88.9706 (242/272)64.191 (242/377)1.9802 (30/1515)74.57630.8117
    PSO-IRELM80.3571 (225/280)61.3079 (225/367)3.5415 (55/1553)69.55180.7897
    BSO-IRELM83.9552 (225/268)66.1765 (225/340)2.701 (43/1592)74.01320.8179
    下载: 导出CSV

    表  10  各算法在Probe上的性能评价指标

    Table  10  Performance evaluation index of each algorithm on Probe

    算法精准率 (%)TPR (%)FPR (%)F值 (%)AUC
    BP82.9787 (390/470)97.5 (390/400)6.9444 (80/1152)89.65520.9625
    LR62.6039 (226/361)56.7839 (226/398)15.8265 (135/853)59.5520.7418
    RBF99.5902 (243/244)59.7052 (243/407)0.071582 (1/1397)74.65440.7982
    AB89.6359 (320/357)82.4742 (320/388)2.9887 (37/1238)85.9060.9009
    SVM73.3728 (372/507)88.7828 (372/419)9.467 (135/1426)80.34560.9012
    RELM51.7661 (425/821)97.7011 (425/435)32.3265 (396/1225)67.67520.8620
    IRELM79.9065 (342/428)91.4439 (342/374)7.2758 (86/1182)85.28680.9308
    GA-IRELM89.8851 (391/435)92.435 (391/423)3.1884 (44/1380)91.14220.9482
    PSO-IRELM89.7638 (3422/381)94.4751 (342/362)2.7465 (39/1420)92.05920.9605
    BSO-IRELM89.6629 (399/445)93.8824 (399/425)3.2372 (396/1225)91.72410.9548
    下载: 导出CSV

    表  11  各算法在DoS上的性能评价指标

    Table  11  Performance evaluation index of each algorithm on DoS

    算法精准率 (%)TPR (%)FPR (%)F值 (%)AUC
    BP93.0233 (600/645)81.5217 (600/736)4.9614 (45/907)86.89360.8898
    LR42.1687 (665/1577)87.5 (665/760)76.5743 (912/1191)56.91060.5698
    RBF99.4074 (671/675)90.9214 (671/738)0.41152 (4/972)94.97520.9530
    AB90.3509 (515/570)70.6447 (515/729)5.1838 (55/1061)79.29180.8316
    SVM84.7118 (676/798)90.1333 (676/750)11.0009 (122/1109)87.33850.9019
    RELM96.7391 (178/184)25.0704 (178/710)0.55453 (6/1082)39.8210.6230
    IRELM96.7059 (411/425)54.0079 (411/761)1.3449 (14/1041)69.30860.7644
    GA-IRELM90.7539 (638/703)89.4811 (638/713)5.6326 (65/1154)90.1130.9222
    PSO-IRELM93.5302 (665/711)89.502 (665/742)4.1667 (16/1104)91.47180.9292
    BSO-IRELM96.3636 (689/715)93.6141 (689/736)2.3402 (26/1111)94.9690.9578
    下载: 导出CSV

    表  12  各算法在R2L上的性能评价指标

    Table  12  Performance evaluation index of each algorithm on R2L

    算法精准率 (%)TPR (%)FPR (%)F值 (%)AUC
    BP87.5 (14/16)31.1111 (14/45)0.13793 (2/1450)45.90160.5150
    LRNaN (0/0)0 (0/32)0 (0/944)NaN0
    RBF68 (17/25)56.6667 (17/30)0.4908 (8/1630)61.81820.7813
    ABNaN (0/0)0 (0/36)0 (0/1521)NaN0
    SVMNaN (0/0)0 (0/36)0 (0/1663)NaN0
    RELM50 (1/2)3.4483 (1/29)0.079745 (1/1254)6.45160.5147
    IRELM81.8182 (9/11)39.1304 (9/23)0.13976 (2/1431)52.94120.6951
    GA-IRELM90.9091 (20/22)57.1429 (20/35)0.11703 (2/1709)70.17540.7852
    PSO-IRELM90.9091 (20/22)54.0541 (20/37)0.1173 (2/1705)67.79660.7698
    BSO-IRELM92.3077 (24/26)82.7586 (24/29)0.39728 (7/1762)69.09090.8258
    下载: 导出CSV

    表  13  各算法在U2R上的性能评价指标

    Table  13  Performance evaluation index of each algorithm on U2R

    算法精准率 (%)TPR (%)FPR (%)F值 (%)AUC
    BP52.1739 (44/851)97.1554 (444/457)28.5614 (407/1425)67.88990.8539
    LR88.8889 (40/45)8.7719 (40/456)0.55006 (5/909)15.96810.5422
    RBF67.1033 (461/687)94.274 (461/489)16.0969 (226/1404)78.40140.8966
    AB73.6301 (430/584)92.6724 (430/464)12.3695 (154/1245)82.06110.9132
    SVM87.0044 (395/454)88.565 (395/446)4.4461 (59/1327)87.77780.9238
    RELM59.0038 (462/783)97.4684 (462/474)28.841 (321/1113)73.50840.8822
    IRELM65.2235 (467/716)96.4876 (467/484)20.4098 (249/1220)77.83330.9003
    GA-IRELM76.7606 (436/568)96.4602 (436/452)9.2762 (132/1423)85.49020.9397
    PSO-IRELM77.7228 (471/606)95.9267 (471/491)9.7332 (135/1387)85.87060.9349
    BSO-IRELM80.9524 (442/546)94.0426 (442/470)7.2423 (104/1436)87.00790.9362
    下载: 导出CSV
  • [1] Tsai C F, Hsu Y F, Lin C Y, Lin W Y. Intrusion detection by machine learning: A review. Expert Systems With Applications, 2009, 36(10): 11994-12000 doi: 10.1016/j.eswa.2009.05.029
    [2] 任家东, 刘新倩, 王倩, 何海涛, 赵小林. 基于KNN离群点检测和随机森林的多层入侵检测方法. 计算机研究与发展, 2019, 56(3): 566-575

    Ren Jia-Dong, Liu Xin-Qian, Wang Qian, He Hai-Tao, Zhao Xiao-Lin. An multi-level intrusion detection method based on KNN outlier detection and random forests. Journal of Computer Research and Development, 2019, 56(3): 566-575
    [3] 高妮, 高岭, 贺毅岳, 王海. 基于自编码网络特征降维的轻量级入侵检测模型. 电子学报, 2017, 45(3): 730-739

    Gao Ni, Gao Ling, HE Yi-Yue, Wang Hai. A lightweight intrusion detection model based on autoencoder network with feature reduction. Acta Electronica Sinica, 2017, 45(3): 730-739
    [4] Ahmad I, Basheri M, Iqbal M J, Rahim A. Performance comparison of support vector machine, random forest, and extreme learning machine for intrusion detection. IEEE Access, 2018, 6: 33789-33795 doi: 10.1109/ACCESS.2018.2841987
    [5] Mabu S, Gotoh S, Obayashi M, Kuremoto T. A random-forests-based classifier using class association rules and its application to an intrusion detection system. Artificial Life and Robotics, 2016, 21(3): 371-377 doi: 10.1007/s10015-016-0281-x
    [6] Shenfield A, Day D, Ayesh A. Intelligent intrusion detection systems using artificial neural networks. ICT Express, 2018, 4(2): 95-99 doi: 10.1016/j.icte.2018.04.003
    [7] Ding H W, Wan L. Research on intrusion detection based on KPCA-BP neural network. In: Proceedings of the 18th IEEE International Conference on Communication Technology (ICCT). Chongqing, China: IEEE, 2018. 911−915
    [8] Wang T, Wei L H, Ai J Q. Improved BP Neural Network for Intrusion Detection Based on AFSA. In: Proceedings of the 2015 International Symposium on Computers and Informatics (ISCI). Beijing, China: Atlantis Press, 2015. 373−380
    [9] Huang G, Song S J, Gupta J N D, Wu C. Semi-supervised and unsupervised extreme learning machines. IEEE Transactions on Cybernetics, 2014, 44(12): 2405-2417 doi: 10.1109/TCYB.2014.2307349
    [10] 陆慧娟, 安春霖, 马小平, 郑恩辉, 杨小兵. 基于输出不一致测度的极限学习机集成的基因表达数据分类. 计算机学报, 2013, 36(2): 341-348

    Lu Hui-Juan, An Chun-Lin, Ma Xiao-Ping, Zheng En-Hui, Yang Xiao-Bing. Disagreement measure based ensemble of extreme learning machine for gene expression data classification. Chinese Journal of Computers, 2013, 36(2): 341-348
    [11] 陈晓云, 廖梦真. 基于稀疏和近邻保持的极限学习机降维. 自动化学报, 2019, 45(2): 325-333

    Chen Xiao-Yun, Liao Meng-Zhen. Dimensionality reduction with extreme learning machine based on sparsity and neighborhood preserving. Acta Automatica Sinica, 2019, 45(2): 325-333
    [12] Yang Z X, Wang X B, Wong P K, Zhong J H. ELM based representational learning for fault diagnosis of wind turbine equipment. Proceedings of ELM-2015 Volume 2: Theory, Algorithms and Applications (II). Cham: Springer, 2016. 169−178
    [13] 邹伟东, 夏元清. 基于压缩动量项的增量型ELM虚拟机能耗预测. 自动化学报, 2019, 45(7): 1290-1297

    Zou Wei-Dong, Xia Yuan-Qing. Virtual machine power prediction using incremental extreme learning machine based on compression driving amount. Acta Automatica Sinica, 2019, 45(7): 1290-1297
    [14] Ku J H, Zheng B. Intrusion detection based on self-adaptive differential evolution extreme learning machine with gaussian kernel. In: Proceedings of the 8th International Symposium on Parallel Architecture, Algorithm and Programming. Haikou, China: Springer, 2017. 13−24
    [15] Deng W Y, Zheng Q H, Chen L. Regularized extreme learning machine. In: Proceedings of the 2009 IEEE Symposium on Computational Intelligence and Data Mining. Nashville, USA: IEEE, 2009. 389−395
    [16] Huang G B, Wang D H, Lan Y. Extreme learning machines: A survey. International Journal of Machine Learning and Cybernetics, 2011, 2(2): 107-122 doi: 10.1007/s13042-011-0019-y
    [17] Jiang X Y, Li S. BAS: Beetle antennae search algorithm for optimization problems [Online], available: https://arxiv.org/pdf/1710.10724.pdf, March 27, 2019
    [18] Jiang X Y. Li S. Beetle antennae search without parameter tuning (BAS-WPT) for multi-objective optimization. Filomat, 2020, 34(15): 5113−5119
    [19] 刘影, 钱志鸿, 贾迪. 室内环境中基于天牛须寻优的普适定位方法. 电子与信息学报, 2019, 41(7): 1565-1571 doi: 10.11999/JEIT181021

    Liu Ying, Qian Zhi-Hong, Jia Di. Universal localization algorithm based on beetle antennae search in indoor environment. Journal of Electronics & Information Technology, 2019, 41(7): 1565-1571 doi: 10.11999/JEIT181021
    [20] Wu Q, Ma Z P, Xu G, Li S, Chen D C. A novel neural network classifier using beetle antennae search algorithm for pattern classification. IEEE Access, 2019, 7: 64686-64696 doi: 10.1109/ACCESS.2019.2917526
    [21] Kaur G, Arora S. Chaotic whale optimization algorithm. Journal of Computational Design and Engineering, 2018, 5(3): 275-284 doi: 10.1016/j.jcde.2017.12.006
    [22] Ling Y, Zhou Y Q, Luo Q F. Lévy flight trajectory-based whale optimization algorithm for global optimization. IEEE Access, 2017, 5: 6168-6186 doi: 10.1109/ACCESS.2017.2695498
    [23] Sarangi A, Samal S, Sarangi S K. Analysis of Gaussian and Cauchy mutations in modified particle swarm optimization algorithm. In: Proceedings of the 5th International Conference on Advanced Computing and Communication Systems (ICACCS). Coimbatore, India: IEEE, 2019. 463−467
    [24] Rudolph G. Local convergence rates of simple evolutionary algorithms with Cauchy mutations. IEEE Transactions on Evolutionary Computation, 1997, 1(4): 249-258 doi: 10.1109/4235.687885
    [25] Gauthama Raman M R, Somu N, Kirthivasan K, Liscano R, Shankar Sriram V S. An efficient intrusion detection system based on hypergraph-Genetic algorithm for parameter optimization and feature selection in support vector machine. Knowledge-Based Systems, 2017, 134: 1-12 doi: 10.1016/j.knosys.2017.07.005
    [26] Mazini M, Shirazi B, Mahdavi I. Anomaly network-based intrusion detection system using a reliable hybrid artificial bee colony and AdaBoost algorithms. Journal of King Saud University-Computer and Information Sciences, 2019, 31(4): 541-553 doi: 10.1016/j.jksuci.2018.03.011
    [27] 王东风, 孟丽. 粒子群优化算法的性能分析和参数选择. 自动化学报, 2016, 42(10): 1552-1561 doi: 10.16383/j.aas.2016.c150774

    Wang Dong-Feng, Meng Li. Performance analysis and parameter selection of PSO algorithms. Acta Automatica Sinica, 2016, 42(10): 1552-1561 doi: 10.16383/j.aas.2016.c150774
    [28] UCI. UCI dataset [Online], available: https://archive.ics.uci.edu/ml/index.php, June 27, 2019
    [29] NSL-KDD dataset [Online], available: https://www.unb.ca/cic/datasets/nsl.html, June 27, 2019
    [30] Vinayakumar R, Alazab M, Soman K P, Poornachandran P, Al-Nemrat A, Venkatraman S. Deep learning approach for intelligent intrusion detection system. IEEE Access, 2019, 7: 41525-41550 doi: 10.1109/ACCESS.2019.2895334
  • 加载中
图(10) / 表(13)
计量
  • 文章访问数:  578
  • HTML全文浏览量:  196
  • PDF下载量:  142
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-12-16
  • 录用日期:  2020-04-07
  • 网络出版日期:  2022-11-29
  • 刊出日期:  2022-12-23

目录

    /

    返回文章
    返回