A negative selection algorithm with human-in-the-loop for anomaly detection

被引：0
作者：
Li C. [1 ,2 ]
Zhang Y. [2 ,3 ]
机构：
[1] School of Business, Changzhou University, Jiangsu Province,
[2] Jiangsu Provincial Institute of Technology Transfer (Changzhou University, Jiangsu Province
[3] School of Mechanical Engineering and Rail Transit, Changzhou University, Jiangsu Province
来源：
Journal of Intelligent and Fuzzy Systems | 2024年 / 46卷 / 04期
关键词：
anomaly detection; artificial immune algorithm; artificial immune system; human-in-the-loop; Negative selection algorithm;
D O I：
10.3233/JIFS-235724
中图分类号：
学科分类号：
摘要：
The existing negative selection algorithms can not improve their detection performance by human intervention during the testing process. This paper proposes a negative selection algorithm with human-in-the-loop for anomaly detection. It uses self-sample clusters to train detectors with a nonrandom strategy. Its detectors and self-sample clusters fully cover state space without overlapping each other. It locally adjusts detectors and self-sample clusters with human intervention to improve its detection performance during the testing process. Experiments were performed on two synthetic datasets and the Iris dataset from the UCI repository to assess its performance. The results show that it outperforms the other anomaly detection methods in most cases. © 2024 – IOS Press.
引用
收藏
页码：9367 / 9380
页数：13
相关论文
共 27 条
[1]  
Zhu J.L., Ge Z.Q., Song Z.H., Gao F.R., Review and big data perspectives on robust data mining approaches for in-dustrial process modeling with outliers and missing data, An-nual Reviews in Control, 46, pp. 107-133, (2018)
[2]  
Zhu K., Zhao C.H., Dynamic graph-based adaptive learn-ing for online industrial soft sensor with mutable spatial cou-pling relations, IEEE Transactions on Industrial Electronics, 70, 9, pp. 9614-9622, (2023)
[3]  
Lai X., Chen Q.W., Tang X.P., Zhou Y.Q., Gao F.R., Guo Y., Bhagat R., Zheng Y.J., Critical review of life cycle assess-ment of lithium-ion batteries for electric vehicles: A lifespan perspective, Etransportation, 12, 2022
[4]  
Wang C., Huang H.T., Pan H.M., A constrained many-objective evolutionary algorithm with learning vector quanti-zation-based reference point adaptation, Swarm and Evolu-tionary Computation, 82, 2023
[5]  
Li D., Gong L.L., Liu S.L., Sun X., Gu M., Qian K., Contin-ual learning classification method with single-label memory cells based on artificial immune system, Journal of Intelligent & Fuzzy Systems, 42, 4, pp. 3975-3991, (2022)
[6]  
Li D., Gu M., Liu S.L., Sun X., Gong L.L., Qian K., Contin-ual learning classification method with weighted k-nearest neighbor rule for time varying data space based on the artifi-cial immune system, Knowledge-based Systems, 240, 2022
[7]  
Chang S.C., Chen X., Zhao C.H., Flexible clockwork recurrent neural network for multirate industrial soft sensor, Journal of Process Control, 119, 2023, pp. 86-100
[8]  
Dasgupta D., Yu S.H., Nino F., Recent advances in artificial immune systems: models and applications, Applied Soft Computing, 11, 2, pp. 1574-1587, (2011)
[9]  
Aldhaheri S., Alghazzawi D., Cheng L., Barnawi A., Alzahrani B.A., Artificial immune systems approaches to secure the internet of things: a systematic review of the literature and recommendations for future research, Journal of Network and Computer Applications, 157, 2020
[10]  
Gupta K.D., Dasgupta D., Negative selection algorithm research and applications in the last decade: a review, IEEE Transaction on Artificial Intelligence, 3, 2, pp. 110-128, (2022)
123