可调控误报率和漏报率的树突状细胞算法

J4 ›› 2014, Vol. 36 ›› Issue (01): 99-104.

可调控误报率和漏报率的树突状细胞算法

袁嵩

（1.武汉科技大学计算机科学与技术学院，湖北武汉 430065;
2.智能信息处理与实时工业系统湖北省重点实验室,湖北武汉 430065）

收稿日期:2012-07-21 修回日期:2012-10-22 出版日期:2014-01-25 发布日期:2014-01-25
基金资助:
国家自然科学基金资助项目(60975031)

Dendritic cell algorithm with adjustable
false positives and false negatives

YUAN Song

(1.College of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065;
2.Hubei Province Key Laboratory of Intelligent Information Processing and Realtime Industrical System,Wuhan 430065,China)

Received:2012-07-21 Revised:2012-10-22 Online:2014-01-25 Published:2014-01-25

摘要/Abstract

摘要：

了解决传统树突状细胞算法（DCA）对环境评判的盲目性，分析DCA权值矩阵对检测结果的影响，提出两种可调控误报率和漏报率的DCA。一种是改进的投票制DCA，即在树突状细胞（DC）状态转换准则中融入倾向因子，以求得对环境评判的公平，并通过对倾向因子的微调控制检测结果的误报率和漏报率；另一种是评分制DCA，即在DC状态转化阶段忽略对细胞环境的评判，改为直接对抗原进行评分，最后根据抗原的平均分分布调整异常阈值，以达到调控误报率和漏报率的目的。实验表明，两种算法均有效地实现了结果可控性，相比而言，评分制DCA可实现更为直观的调控。

关键词: 树突状细胞算法, 异常检测, 倾向因子, 人工免疫, 数据融合

Abstract:

In order to overcome the blindness of evaluation of the context in the classical Dendritic Cell Algorithm (DCA), how the weight matrix of DCA influences the detection results is analyzed, and two kinds of DCAs are proposed, which can adjust the false positives and false negatives. The first one is the improved voting DCA. The Tendency Factor (TF) is involved in the Dendritic Cell (DC) state transition to assess the context fairly, and through the fine adjustment of the TF the false positives and false negatives of the detection results are controlled. The other one is the scoring DCA. In DC state transition phase, the evaluation of the context is ignored, instead, the antigen is directly given a score, then according to the distribution of average scores of antigens the anomaly threshold value can be adjusted to control the false positives and false negatives. Experiments show that the two algorithms can both effectively realize controlling the results. Comparatively, the scoring DCA can realize more intuitive control.

Key words: dendritic cell algorithm;anomaly detection;tendency factor;artificial immune;data fusion

袁嵩. 可调控误报率和漏报率的树突状细胞算法[J]. J4, 2014, 36(01): 99-104.

YUAN Song. Dendritic cell algorithm with adjustable
false positives and false negatives[J]. J4, 2014, 36(01): 99-104.

参考文献［11］

［1］	Greensmith J,Aickelin U,Twycross J.Articulation and clarification of the dendritic cell algorithm［C］∥Proc of the 5th International Conference on Artificial Immune Systems,2006:404417.
［2］	Oates R,Kendall G,Garibaldi J.Frequency analysis for dendritic cell population tuning［J］.Evolutionary Intelligence,2009,1(2):145157.
［3］	Greensmith J,Aickelin U.Artificial dendritic cells:Multifaceted perspectives［M］.Berlin:SpringerVerlog, 2009.
［4］	Greensmith J,Aickelin U,Tedesco G.Information fusion for anomaly detection with the dendritic cell algorithm［J］.Information Fusion,2010,11(1):2134.
［5］	Twycross J. Integrated innate and adaptive artificial immune systems applied to process anomaly detection［D］.Nottingham:University of Nottingham,2007.
［6］	Ni Jiancheng, Li Zhishu, Sun Jirong, et al.Research on differentiation model and application of dendritic cells in artificial immune system［J］.Acta Electronica Sinica,2008,36(11):22102215.(in Chinese)
［7］	Yang Chenxu, Wu Gengfeng, Hu Min. Improved dendritic cells algorithm［J］.Computer Engineering,2009,35(23):194200.(in Chinese)
［8］	Greensmith J, Aickelin U. The deterministic dendritic cell algorithm［C］∥Proc of the 7th International Conference on Artificial Immune Systems,2008:291303.
［9］	Greensmith J. The dendritic cell algorithm［D］.Nottingham:University of Nottingham,2007.
［10］	Greensmith J, Aickelin U, Cayzer S. Detecting danger:The dendritic cell algorithm［M］∥Robust Intelligent Systems, London:Springer,2008:89112.
［11］	Chen Yuebing, Feng Chao, Zhang Quan, et al. Principles and application of dendritic cell algorithm［J］.Computer Engineering,2010,36(8):173176.(in Chinese)
	附中文参考文献：
［6］	倪建成,李志蜀,孙继荣，等.树突状细胞分化模型在人工免疫系统中的应用研究［J］.电子学报,2008,36(11):22102215.
［7］	杨晨旭,吴耿锋,胡珉.一种改进的树突状细胞算法［J］.计算机工程,2009,35(23):194200.
［11］	陈岳兵,冯超,张权，等.树突状细胞算法原理及其应用［J］.计算机工程,2010,36(8):173176.

[1]	尹春勇, 冯梦雪. 基于注意力机制的半监督日志异常检测方法[J]. 计算机工程与科学, 2023, 45(08): 1405-1415.
[2]	杨斌, 王敬宇, 刘世超, 邵明山, 肖伟, 陈起, 何晓斌, 刘卫国, 薛巍, . Beacon+：面向E级超级计算机的轻量级端到端I/O性能监控与分析诊断系统[J]. 计算机工程与科学, 2022, 44(09): 1521-1531.
[3]	何平, 李刚, 李慧斌, . 基于深度学习的视频异常检测方法综述[J]. 计算机工程与科学, 2022, 44(09): 1620-1629.
[4]	郭思雨, 王磊. 基于编译时插桩的浮点异常检测方法[J]. 计算机工程与科学, 2022, 44(06): 979-985.
[5]	王思齐, 胡婧韬, 余广, 祝恩, 蔡志平. 智能视频异常事件检测方法综述[J]. 计算机工程与科学, 2020, 42(08): 1393-1405.
[6]	夏火松, 孙泽林. 基于自编码器和集成学习的半监督异常检测算法[J]. 计算机工程与科学, 2020, 42(08): 1440-1447.
[7]	仇开1,2，姜瑛1,2. 加权LOF结合上下文判断的云环境中服务运行数据异常检测方法[J]. 计算机工程与科学, 2020, 42(06): 951-958.
[8]	尤诚诚, 冯旭鹏, 刘利军, 黄青松, . 基于主题模型的胸部X光片诊断报告异常检测方法[J]. 计算机工程与科学, 2020, 42(04): 741-748.
[9]	杨杰，张东月，周丽华，黄皓，丁海燕. 基于网格耦合的数据流异常检测[J]. 计算机工程与科学, 2020, 42(01): 25-35.
[10]	王腾1，焦学伟2，高阳2. 一种基于Attention-GRU和iForest的周期性时间序列异常检测算法[J]. 计算机工程与科学, 2019, 41(12): 2217-2222.
[11]	张曼,於志文,郭斌,任思源,岳超刚. 一种基于快递大数据的异常检测系统[J]. 计算机工程与科学, 2019, 41(02): 224-232.
[12]	王鹏飞1，杨余旺1，柯亚琪2. 密度峰值快速聚类算法优化研究[J]. 计算机工程与科学, 2018, 40(08): 1503-1510.
[13]	蔡武越1,王珂2，郝玉洁2，段晓冉2. 一种Hadoop集群下的行为异常检测方法[J]. 计算机工程与科学, 2017, 39(12): 2185-2191.
[14]	李娟1，张冰怡1，冯志勇1，徐超2，张铮3. 基于隐马尔可夫模型的视频异常场景检测[J]. 计算机工程与科学, 2017, 39(07): 1300-1308.
[15]	俞家宗，刘波. 基于粒子群优化算法的属性异常检测[J]. 计算机工程与科学, 2017, 39(06): 1186-1192.