Discovering the backbone network with a novel designed ant colony algorithm

被引：0
|
作者：
Lyu F. [1 ,2 ]
Bai J. [1 ]
Huang J. [1 ,2 ]
Wang B. [1 ,2 ]
机构：
[1] School of Computer Science and Technology, Harbin Institute of Technology, Weihai
[2] Research Institute of Cyberspace Security, Harbin Institute of Technology, Weihai
来源：
Tongxin Xuebao/Journal on Communications | 2020年 / 41卷 / 11期
基金：
中央高校基本科研业务费专项资金资助;
关键词：
Ant colony algorithm; Backbone network; Interactive network; Path optimization; Update pheromone dynamically;
D O I：
10.11959/j.issn.1000-436x.2020207
中图分类号：
学科分类号：
摘要：
For the problem that in interactive network, the illegal and abnormal behaviors were becoming more hidden, moreover, the complex relation in real interactive network heightens the difficulty of detecting anomalous entities, an ant colony model was proposed for extracting the backbone network from the complex interactive network. The novel model simulated the relationships among entities based on the theory of path optimization, reduced the network size after quantifying the significance of each flow of information. Firstly, a strategy of initial location selection was proposed taking advantage of network centrality. Secondly, a novel path transfer mechanism was devised for the ant colony to fit the flow behavior of entities. Finally, an adaptive and dynamic pheromone update mechanism was designed for guiding the optimization of information flows. The experimental results show that the proposed model is superior to the traditional ant colony algorithm in both solving quality and solving performance, and has better coverage and accuracy than the greedy algorithm. © 2020, Editorial Board of Journal on Communications. All right reserved.
引用
收藏
页码：74 / 85
页数：11
相关论文
共 33 条
  • [1] ZHENG L S., China's Internet finance: models, impact, nature and risks, International Economic Review, 5, pp. 103-118, (2014)
  • [2] LI B, DONG L., The mode and development of Internet finance, China Finance, 10, pp. 19-21, (2013)
  • [3] ZHONG Q, LIU Y, AO X, Et al., Financial defaulter detection on online credit payment via multi-view attributed heterogeneous information network, The Web Conference 2020, pp. 785-795, (2020)
  • [4] ZHENG L T, LIU G J, YAN C G, Et al., Transaction fraud detection based on total order relation and behavior diversity, IEEE Transactions on Computational Social Systems, 5, 3, pp. 796-806, (2018)
  • [5] LAROCK T, NANUMYAN V, SCHOLTES I, Et al., Hypa: efficient detection of path anomalies in time series data on networks, 2020 SIAM International Conference on Data Mining, pp. 460-468, (2020)
  • [6] CAO B K, MAO M, VIIDU S, Et al., Collective fraud detection capturing inter-transaction dependency, KDD 2017 Workshop on Anomaly Detection in Finance, pp. 66-75, (2018)
  • [7] HELMY T H, ZAKI M, SALAH T, Et al., Design of a monitor for detecting money laundering and terrorist financing, Journal of Theoretical and Applied Information Technology, 85, 3, pp. 425-436, (2016)
  • [8] BRUSS C B, KHAZANE A, RIDER J, Et al., Deeptrax: embedding graphs of financial transactions, 2019 IEEE International Conference on Machine Learning and Applications, pp. 126-133, (2019)
  • [9] DORIGO M, MANIEZZO V, COLORNI A., Ant system: optimization by a colony of cooperating agents, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 26, 1, pp. 29-41, (1996)
  • [10] DORIGO M, GAMBARDELLA L M., Ant colonies for the travelling salesman problem, Biosystems, 43, 2, pp. 73-81, (1997)
1234