基于数字微分的函数化树突状细胞算法模型

doi:10.19678/j.issn.1000-3428.0055380

摘要/Abstract

摘要： 树突状细胞算法（DCA）是一种模拟人体免疫系统中抗原提呈的算法，可以快速有效地将输入数据分为正常和异常，然而现有DCA模型普遍存在形式化描述不清晰且信号提取受人工经验影响的不足。为此，在hDCA模型的基础上，提出一种基于数字微分的函数化DCA模型。在预处理阶段引入数字微分方法，根据数据变化趋势自适应提取信号并随机动态采样抗原，去除对时序敏感的数据序列。在此基础上，对输入信号加以融合得到决策信号，并进行抗原背景环境分类处理。将ndhDCA、DCA和hDCA应用于WBC和KDD99数据集进行对比，实验结果表明，ndhDCA对有序数据集和无序数据集均具有高准确率和低误报率，同时可降低输入数据顺序的敏感性。

关键词: 树突状细胞算法, hDCA模型, 数字微分, 人工免疫系统, 特征提取

Abstract: The Dendritic Cell Algorithm(DCA) is an algorithm for simulating antigen presentation in the human immune system,which can divide input data into normal and abnormal data quickly and effectively.However,the existing DCA models are generally lack of clear formal description and their signal extraction is affected by artificial experience.To address the problems,this paper proposes a numerical differentiation-based functional dendritic cell model,named ndhDCA,by improving the hDCA model.In the preprocessing stage,the numerical differentiation method is introduced to extract the signal adaptively according to the trend of data change and to randomly and dynamically sample the antigen to remove the time-sensitive data sequence.On this basis,the input signal is fused to obtain the decision signal,and the antigen background environment is classified.ndhDCA,DCA and hDCA are compared on WBC and KDD99 data sets.The experimental results show that ndhDCA has higher accuracy and lower false positive rate in both ordered data sets and unordered data sets,and overcomes the sensitivity of the data sequence.

Key words: Dendritic Cell Algorithm(DCA), hDCA model, numerical differentiation, Aritifical Immune System(AIS), feature extraction

中图分类号:

TP18

张艺, 周雯, 梁意文, 谭成予. 基于数字微分的函数化树突状细胞算法模型[J]. 计算机工程, 2020, 46(9): 54-60.

ZHANG Yi, ZHOU Wen, LIANG Yiwen, TAN Chengyu. Model of Functional Dendritic Cell Algorithm Based on Numerical Differentiation[J]. Computer Engineering, 2020, 46(9): 54-60.

http://www.ecice06.com/CN/Y2020/V46/I9/54

图/表 7

20200915134542

20200915134546

20200915134549

20200915134553

20200915134559

20200915134602

20200915134606

参考文献

[1] CASTRO L R D,TIMMIS J.Artificial immune systems:a new computational intelligence paradigm[M].Berlin,Germany:Springer,2002.
[2] LU Tianliang,ZHANG Lu,CAI Manchun,et al.shellcode detection algorithm inspired by hyper-ellipsoids immune theory[J].Journal of Chinese Computer Systems,2018,39(6):1255-1259.(in Chinese)芦天亮,张璐,蔡满春,等.一种超椭球免疫理论启发的shellcode检测算法[J].小型微型计算机系统,2018,39(6):1255-1259.
[3] DUDEK G.Artificial immune system with local feature selection for short-term load forecasting[J].IEEE Transactions on Evolutionary Computation,2017,21(1):116-130.
[4] GREENSMITH J,AICKELIN U.Dendritic cells for SYN scan detection[C]//Proceedings of Conference on Genetic and Evolutionary Computation.New York,USA:ACM Press,2007:49-56.
[5] AL-HAMMADI Y,AICKELIN U,GREENSMITH J.DCA for bot detection[C]//Proceedings of IEEE World Congress on Computational Intelligence.Washington D.C.,USA:IEEE Press,2008:1-10.
[6] OATES R,GREENSMITH J,AICKELIN U,et al.The application of a dendritic cell algorithm to a robotic classifier[C]//Proceedings of International Conference on Artificial Immune Systems.Berlin,Germany:Springer,2007:204-215.
[7] SILVA G C,CAMINHAS W M,ERRICO L D.Dendritic cell algorithm applied to ping scan investigation revisited:detection quality and performance analysis[J].IEEE Transactions on Emerging Topics in Computational Intelligence,2017,1(4):236-247.
[8] IGBE O,AJAYI O,SAADAWI T.Detecting denial of service attacks using a combination of dendritic cell algorithm and the negative selection algorithm[C]//Proceedings of IEEE International Conference on Smart Cloud.Washington D.C.,USA:IEEE Press,2017:1-6.
[9] IGBE O,DARWISH I,SAADAWI T.Deterministic dendritic cell algorithm application to smart grid cyber-attack detection[C]//Proceedings of IEEE International Conference on Cyber Security and Cloud Computing.Washington D.C.,USA:IEEE Press,2017:1-5.
[10] GAN Ying,LIANG Yiwen,TAN Chengyu,et al.Earthquake prediction method based on danger theory[J].Computer Engineering,2019,45(1):278-283.(in Chinese)甘颖,梁意文,谭成予,等.基于危险理论的地震预测方法[J].计算机工程,2019,45(1):278-283.
[11] YANG Chao,QIN Tingdong,FAN Bo,et al.Study on detection of Weibo spammers based on danger theory in artificial immunity system[J].Computer Science,2018,45(11):145-149,166.(in Chinese)杨超,秦廷栋,范波,等.基于人工免疫危险理论的微博水军用户检测研究[J].计算机科学,2018,45(11):145-149,166.
[12] GREENSMITH J,AICKELIN U,CAYZER S.Introducing dendritic cells as a novel immune-inspired algorithm for anomaly detection[C]//Proceedings of International Conference on Artificial Immune Systems.New York,USA:ACM Press,2005:153-167.
[13] GREENSMITH J,AICKELIN U,TWYCROSS J.Articulation and clarification of the dendritic cell algorithm[C]//Proceedings of International Conference on Artificial Immune Systems.New York,USA:ACM Press 2006:404-407.
[14] GU F,GREENSMITH J,AICKELIN U.The dendritic cell algorithm for intrusion detection[EB/OL].[2019-05-10].https://arxiv.org/ftp/arxiv/papers/1305/1305.7416.pdf.
[15] GREENSMITH J,AICKELIN U.The deterministic dendritic cell algorithm[C]//Proceedings of International Conference on Artificial Immune Systems.Berlin,Germany:Springer,2008:291-302.
[16] YANG Chen,LIANG Yiwen,TAN Chengyu,et al.Optimized dendritic cell algorithm combined with XGBoost[J].Computer Engineering,2019,45(9):194-197,203.(in Chinese)杨晨,梁意文,谭成予,等.结合XGBoost改进的树突状细胞算法[J].计算机工程,2019,45(9):194-197,203.
[17] WANG Shuyang,MU Xiaodong,ZHANG Li.Improved dendritic cell algorithm integrated with principal component analysis[J].Computer Engineering and Design,2017,38(6):1414-1417.(in Chinese)王舒洋,慕晓冬,张力.集成PCA的改进树突状细胞算法[J].计算机工程与设计,2017,38(6):1414-1417.
[18] GU F,GREENSMITH J,AICKELIN U.Theoretical formulation and analysis of the deterministic dendritic cell algorithm[J].Biosystems,2013,111(2):127-135.
[19] GREENSMITH J,GALE M B.The functional dendritic cell algorithm:a formal specification with Haskell[C]//Proceedings of IEEE Congress on Evolutionary Computation.Washington D.C.,USA:IEEE Press,2017:1787-1794.
[20] CHELLY Z,ELOUEDI Z.A new data pre-processing approach for the dendritic cell algorithm based on fuzzy rough set theory[C]//Proceedings of GECCO'13.New York,USA:ACM Press,2013:163-164.
[21] LIANG Yiwen,CAO Linglin,CAI Ying.Introduction to danger sensed through numerical differential[J].Journal of Harbin Engineering University,2006,27(s1):228-232.(in Chinese)梁意文,曹玲林,蔡瀛.危险感知的数字微分初步[J].哈尔滨工程大学学报,2006,27(s1):228-232.
[22] YANG Chao,LI Tao.Research of danger signal extraction based on changes in danger theory[J].Computer Science,2015,42(8):170-174.(in Chinese)杨超,李涛.计算机免疫危险理论中危险信号的提取研究[J].计算机科学,2015,42(8):170-174.
[23] ZHOU Wen,LIANG Yiwen,DONG Hongbin,et al.A numerical differentiation based dendritic cell model[C]//Proceedings of IEEE International Conference on Tools with Artificial Intelligence.Washington D.C.,USA:IEEE Press,2017:1-5.
[24] XIAO Zhenhua,LIANG Yiwen,TAN Chengyu,et al.Dendritic cell fault detection method based on numerical differentiation[J].Acta Electronica Sinica,2019,47(5):1029-1035.(in Chinese)肖振华,梁意文,谭成予,等.基于数值微分的树突状细胞故障检测方法[J].电子学报,2019,47(5):1029-1035.
[25] CHELLY Z,ELOUEDI Z.FDCM:a fuzzy dendritic cell method[C]//Proceedings of International Conference on Artificial Immune Systems.Berlin,Germany:Springer,2010:102-115.
[26] GU Feng.Theoretical and empirical extensions of the dendritic cell algorithm[D].Nottingham,UK:University of Nottingham,2011.
[27] OATES R,KENDALL G,GARIBALDI J.Frequency analysis for dendritic cell population tuning:decimating the dendritic cell[J].Evolutionary Intelligence,2008,1:145-157.
[28] STIBOR T,OATES R,KENDALL G,et al.Geometrical insights into the dendritic cell algorithm[C]//Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation.New York,USA:ACM Press,2009:1275-1282.
[29] GU F,FEYEREISL J,OATES R,et al.Quiet in class:classification,noise and the dendritic cell algorithm[C]//Proceedings of International Conference on Artificial Immune Systems.Berlin,Germany:Springer,2010:173-186.
[30] MUSSELLE C J.Insights into the antigen sampling component of the dendritic cell algorithm[C]//Proceedings of International Conference on Artificial Immune Systems.Berlin,Germany:Springer,2010:88-101.

选择文件类型/文献管理软件名称

选择包含的内容