基于社会网络与事件关联的恐怖事件监测与识别

李泽; 孙多勇; 李博

PDF(4859 KB)

科技导报 ›› 2017, Vol. 35 ›› Issue (9) : 87-94.

研究论文

基于社会网络与事件关联的恐怖事件监测与识别

作者信息 -

国防科技大学信息系统与管理学院, 长沙 410073

作者简介:

李泽,博士研究生,研究方向为国家安全与危机管理,电子信箱:plalize@nudt.edu.cn

Terrorist events monitoring and identifying based on correlation between social networks and events

Author information -

College of Information System and Management, National University of Defense Technology, Changsha 410073, China

摘要

恐怖组织的社会网络结构变化与恐怖事件的发生具有一定的关联性。基于此关联，通过监测恐怖组织社会网络的变化，可以实时、有效地识别恐怖事件。将基于社会网络变化检测的恐怖事件监测与识别问题视为分类问题，并通过神经网络模型进行分类研究。以某一时刻是否发生恐怖事件为标准，对恐怖组织社会网络进行分类；通过网络分析技术，得出网络的参数指标，建立混合算法改进的神经网络模型；将网络的参数指标与恐怖事件发生情况分别作为输入和输出，对神经网络进行训练与测试。案例分析和对比结果表明，基于神经网络模型的社会网络变化检测方法具备较好的恐怖事件监测与识别能力；该方法可在一定程度上弥补现有方法正确率不高、通用性不强、检测结果与恐怖事件实际发生的相关性不高等不足。

Abstract

The social networks of terrorist organization and terrorist events are changing correlatively. Based on the correlation between social networks and events, detecting changes in the networks may effectively help monitor and identify terrorist events. Terrorist attack early-warning is regarded as a classification problem, and neural network is used to solve this problem. The time when any terrorist attack happens is identified as a "change" point. Then the corresponding network is labeled as a changed one. Accordingly, the time sequence networks are classified into two sets:"changed" and "unchanged". Measures of networks are obtained by social network analysis to represent networks. Hybrid heuristic algorithms are applied to optimizing the neural network. The classified network measures and the Boolean data of whether the terrorist events have happened are taken as the input and output, respectively. A real-world case study is given to show that detecting changes in terrorist networks based on neural network has the ability to monitor and identify terrorist events. Comparison results also show that the proposed approach can solve the problems such as versatility, accuracy and correlation encountered by the existing methods to some extent.

导出引用

李泽, 孙多勇, 李博. 基于社会网络与事件关联的恐怖事件监测与识别[J]. 科技导报, 2017, 35(9): 87-94

LI Ze, SUN Duoyong, LI Bo. Terrorist events monitoring and identifying based on correlation between social networks and events[J]. Science & Technology Review, 2017, 35(9): 87-94

参考文献

[1] Chen H, Chung W, Qin J, et al. Uncovering the dark web: A case study of Jihad on the web[J]. Journal of the American Society for Information Science and Technology, 2008, 59(8): 1347-1359.
[2] Carley Kathleen, Lee Ju-Sung, Krackhardt David. Destabilizing terror-ist networks[J]. Connections, 2001, 24(3): 79-92.
[3] Krebs V. Mapping networks of terrorist cells[J]. Connections, 2001, 24 (3):43-52.
[4] McCulloh I, Carley K, Webb M. Social network monitoring of Al-Qaeda[J]. Network Science, 2007(1): 25-30.
[5] McCulloh I, Carley K M. Detecting change in longitudinal social net-works[R]. New York: Military Academy West Point NY Network Sci-ence Center (NSC), 2011.
[6] 刘楝, 罗军勇, 刘琰. 社会网络的动态建模与变化检测技术[J]. 计算机工程, 2011, 37(19): 47-49. Liu Lian, Luo Junyong, Liu Yan. Dynamic modeling and change detec-tion technology of social network[J]. Computer Engineering, 2011, 37 (19): 47-49.
[7] Priebe C E, Conroy J M, Marchette D J, et al. Scan statistics on enron graphs[J]. Computational and Mathematical Organization Theory, 2005, 11(3): 229-247.
[8] Sun J, Faloutsos C, Papadimitriou S, et al. Graphscope: Parameter-free mining of large time-evolving graphs[C]//Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2007: 687-696.
[9] Peel L, Clauset A. Detecting change points in the large-scale structure of evolving networks[J]. arXiv, 2014: 1403.0989.
[10] Li S, Xie Y, Farajtabar M, et al. Detecting weak changes in dynamic events over networks[J]. arXiv, 2016: 1603.08981.
[11] 胡文斌, 彭超, 梁欢乐,等. 基于链路预测的社会网络事件检测方法[J]. 软件学报, 2015, 26(9): 2339-2355. Hu Wenbin, Peng Chao, Liang HuanLe, et al. Event detection method based on link prediction for social network evolution[J]. Journal of Soft-ware, 2015, 26(9): 2339-2355.
[12] Allanach J, Tu H, Singh S, et al. Detecting, tracking, and counteract-ing terrorist networks via hidden Markov models[C]//Aerospace Confer-ence. Big Sky, MT: IEEE, 2004, 5: 3246-3257.
[13] 张景阳, 潘光友. 多元线性回归与BP神经网络预测模型对比与运用研究[J]. 昆明理工大学学报(自然科学版), 2013, 6: 61-67. Zhang Jingyang, Pan Guangyou. Comparison and application of multi-ple regression and BP neural network prediction model[J]. Journal of Kunming University of Science and Technology ( Natural Science Edi-tion), 2013, 6: 61-67.
[14] Zhang G, Patuwo B E, Hu M Y. Forecasting with artificial neural net-works: The state of the art[J]. International Journal of Forecasting, 1998, 14(1): 35-62.
[15] Deepa S N. An intelligent computing model for wind speed prediction in renewable energy systems[J]. Procedia Engineering, 2012, 30: 380-385.
[16] 刘硕, 何永秀, 陶卫君,等. 遗传BP神经网络的煤价预测与煤价风险规避策略[J]. 华北电力大学学报(自然科学版), 2009, 36(6): 75-80. Liu Shuo, He Yongxiu, Tao Weijun, et al. Coal proce forecasting based on GABP neural network and risk resistance strategy[J]. Journal of North China Electric Power University (Natural Science Edition), 2009, 36(6): 75-80.
[17] 张佳伟, 张自嘉. 基于PSO-BP神经网络的短期光伏系统发电预测[J]. 可再生能源, 2012, 30(8): 28-32. Zhang Jiawei, Zhang Zijia. Short-term photovoltaic system power fore-casting based on PSO-BP neural network[J]. Renewable Energy Re-sources, 2012, 30(8): 28-32.
[18] 江祥奎, 范永青, 王婉. 基于粒子群遗传算法的BP神经网络摄像机标定[J]. 计算机科学与探索, 2014, 8(10): 1254-1262. Jiang Xiangkui, Fan Yongqing, Wang Wan, et al. BP neural network camera calibration based on particle swarm optimization genetic algo-rithm[J]. Journal of Frontiers of Computer Science and Technology, 2014, 8(10): 1254-1262.
[19] 潘勇, 郭晓东. 一种基于遗传算法改进的粒子群优化算法[J]. 计算机应用与软件, 2011, 28(9): 222-224. Pan Yong, Guo Xiaodong. An improved particle swarm optimisation al-gorithm based on genetic algorithm[J]. Computer Applications and Soft-ware, 2011, 28(9): 222-224.
[20] 高玉明, 张仁津. 一种GA-PSO算法优化BP网络的网络流量预测[J]. 计算机应用与软件, 2014, 31(4):106-110. Gao Yuming, Zhang Renjin. A network traffic prediction based on BP neural network optimized by a GA-PSO algorithm[J]. Computer Appli-cations and Software, 2014, 31(4): 106-110.
[21] Carley K M, Pfeffer J, Reminga J, et al. ORA user's guide 2013[R]. Pittsburgh: Institute for Software Research, Carnegie Mellon Universi-ty, 2013.
[22] 范高锋, 王伟胜, 刘纯. 基于人工神经网络的风电功率短期预测系统[J]. 电网技术, 2008, 32(22): 72-76. Fan Gaofeng, Wang Weisheng, Liu Chun. Artificial neural network based wind power short term prediction system[J]. Power System Tech-nology, 2008, 32(22): 72-76.
[23] 沈花玉, 王兆霞, 高成耀, 等. BP神经网络隐含层单元数的确定[J]. 天津理工大学学报, 2008, 24(5): 13-15. Shen Huayu, Wang Zhaoxia, Gao Chengyao, et al. Determine the num-ber of BP neural network hidden layer units[J]. Journal of Tianjin Uni-versity Technology, 2008, 24(5): 13-15.
[24] Zimmerman K. The Al Qaeda network: A new framework for defining the enemy [R/OL]. (2013-09-10) [2016-08-16]. http://www.criti-calthreats.org/al-qaeda/zimmerman-al-qaeda-network-new-frame-work-defining-enemy-september-10-2013.
[25] John Jay & ARTIS Transnational Terrorism Database[EB/OL]. [2016-08-20]. http://doitapps.jjay.cuny.edu/jjatt/data.php.
[26] Moon I C. Destabilization of adversarial organizations with strategic in-terventions[D]. Pittsburgh: School of Computer Science, Carnegie Mel-lon University, 2008.