A NEGATIVE SELECTION ALGORITHM BASED ON HIERARCHICAL CLUSTERING OF DETECTOR SETS

Jun He

Abstract


Background- For the anomaly detection problem, the negative selection algorithm (NSA) has a significant detection effect. However, the traditional negative selection process requires a lot of time in the detection phase to calculate the distance from the sample point to the detector.

Methods- This paper proposes a new negative selection algorithm based on hierarchical clustering of detector sets. Hierarchical clustering of detector sets to reduce the number of detector sets is the primary goal, thereby reducing the time spent in the test phase.

Result- Compared with RNSA and V-detector, the results show that in most cases, the algorithm can improve the detector rate and reduce the false detection rate.


Keywords


anomaly detection; negative selection algorithm; hierarchical clustering;

Full Text:

PDF

References


Li Dong, Liu Shulin, Liu Yinghui, Zhang Hongli. (2014), “A Method for Equipment Abnormality Detection Based on Adaptive Super-Circle Detector.” Journal of Mechanical Engineering ,50(12):17-24.

Mao Jiali, Jin Cheqing, Zhang Zhigang, Zhou Aoying. (2017) “Trajectory Big Data Anomaly Detection: Research Progress and System Framework.” Journal of Software ,28(01):17-34.

Ying Wang, Yongjun Shen, Guidong Zhang. “Research on Intrusion Detection System Using Ensemble Learning Methods.” 2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS2016), Beijing, China.

Lin Weining, Chen Mingzhi, Zhan Yunqing, Liu Chuanwei. (2017) “Research on Intrusion Detection Algorithm Based on PCA and Random Forest Classification.” Information Network Security, 11, 50-54.

Xia Yuming, Hu Shaoyong, Zhu Shaomin, Liu Lili. ( 2017) “Research on Network Attack Detection Method Based on Convolutional Neural Network.” Information Network Security, 11,32-36.

González F A, Dasgupta D. (2003) “Anomaly Detection Using Real-Valued Negative Selection.” Genetic Programming & Evolvable Machines, 4(4):383-403.

Gonzalez F A. (2003) “A study of artificial immune systems applied to anomaly detection.” The University of Memphis.

Zhou J, Dasgupta D. (2009) “V-detector: an efficient negative selection algorithm with probably adequate detector coverage.” Inform sciences, 19: 1390–1406

Gong M, Zhang J, Ma J, et al. (2012) “Short Communication: An efficient negative selection algorithm with further training for anomaly detection.” Knowledge-Based Systems , 30(2):185-191.

Xiao X, Li T, Zhang R.. (2015) “An immune optimization based real-valued negative selection algorithm.” Kluwer Academic Publishers.


Refbacks

  • There are currently no refbacks.