Research on Anti-terrorism Intelligence Mining Method Based on Attention Neural Networks

被引:1
|
作者
Bai, Caitong [1 ,4 ]
Li, Ai [1 ,4 ]
Gao, Zhiqiang [1 ,3 ,4 ]
Cui, Xiaolong [2 ,4 ]
机构
[1] Engn Univ PAP, Grad Grp, Xian 710086, Peoples R China
[2] Engn Univ PAP, Lu Mu Campus, Urumqi 830049, Xinjiang, Peoples R China
[3] Engn Univ PAP, Coll Informat Engn, Xian 710086, Peoples R China
[4] Armed Police Engn Univ, Antiterrorism Command Informat Engn Res Team, Xian, Peoples R China
来源
PROCEEDINGS OF 2020 IEEE 2ND INTERNATIONAL CONFERENCE ON CIVIL AVIATION SAFETY AND INFORMATION TECHNOLOGY (ICCASIT) | 2020年
基金
中国国家自然科学基金;
关键词
Global anti-terrorism Data Set; Open Source Intelligence Mining Neural Network; Attention Mechanism;
D O I
10.1109/ICCASIT50869.2020.9368596
中图分类号
V [航空、航天];
学科分类号
08 ; 0825 ;
摘要
In order to improve the intelligence and prediction accuracy of anti-terrorism intelligence mining, this paper applies a medium of attraction neural network based on attention mechanism and investors will own a Complete set of open Source Intelligence Data Mining and takes the analysis of casualties and terrorist organizations as examples and a prediction model of casualties and potential about organizations is constructed. It has had been experimentally verified that its prediction ability is significantly improved compared to support vector machine algorithm, logistic regression algorithm, multi-layer perceptron and attention neural network.
引用
收藏
页码:458 / 464
页数:7
相关论文
共 50 条
  • [21] Research on Fire Department Command System of Multi-Region Anti-Terrorism and Emergency Rescue
    Cheng, Xiaohong
    Kang, Qingchun
    Jiang, Lianrui
    Jia, Dingduo
    Xia, Dengyou
    Liu, Jing
    THEORY AND PRACTICE OF RISK ANALYSIS AND CRISIS RESPONSE, PROCEEDINGS, 2008, : 672 - 677
  • [22] Research on the Structural Effectiveness of Overseas Anti-terrorism Operational Command System Supported by Space Information
    Li, Yang
    Luo, Xiao Ming
    Wang, Yan Qiu
    PROCEEDINGS OF THE 2019 31ST CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2019), 2019, : 1786 - 1791
  • [23] Rampart: A Service and Agent-Based Architecture for Anti-Terrorism Planning and Resource Allocation
    Haynes, Steven R.
    Kannampallil, Thomas George
    Cohen, Mark A.
    Soares, Andrey
    Ritter, Frank E.
    INTELLIGENCE AND SECURITY INFORMATICS, PROCEEDINGS, 2008, 5376 : 260 - +
  • [24] A Case Study of Tibet's "3.14" Anti-terrorism Based on Social Network Analysis
    Jiang, Lingzhi
    Wu, Qiwu
    PROCEEDINGS OF THE 5TH ANNUAL INTERNATIONAL CONFERENCE ON SOCIAL SCIENCE AND CONTEMPORARY HUMANITY DEVELOPMENT (SSCHD 2019), 2019, 376 : 633 - 637
  • [25] Evaluation of important buildings anti-terrorism capability based on fuzzy analytic hierarchy process
    Ren Cai-qing
    Huo Li-fei
    Hu Qi-gao
    PROCEEDINGS OF THE 2017 2ND INTERNATIONAL CONFERENCE ON CIVIL, TRANSPORTATION AND ENVIRONMENTAL ENGINEERING (ICCTE 2017), 2017, 135 : 251 - 256
  • [26] Visual Simulation of Anti-Terrorism Emergency Response Based on Unity3D
    Rehman, Muhammad Aziz Ur
    Yan, Huang Yan
    PROCEEDINGS OF THE 2019 IEEE 16TH INTERNATIONAL CONFERENCE ON NETWORKING, SENSING AND CONTROL (ICNSC 2019), 2019, : 132 - 137
  • [27] A Graph Based Model for UAVs Group-Wide Collaboration Applied on an Anti-terrorism Scenario
    Gassara, Amal
    Rodriguez, Ismael Bouassida
    RISKS AND SECURITY OF INTERNET AND SYSTEMS (CRISIS 2019), 2020, 12026 : 311 - 324
  • [28] Urban Anti-terrorism Environment Modeling and Simulation Application Based on Unity3D
    Sun, Wei-zheng
    Mao, Sheng-jie
    Lai, Zhen
    Huang, Yan-yan
    2018 3RD INTERNATIONAL CONFERENCE ON COMPUTATIONAL MODELING, SIMULATION AND APPLIED MATHEMATICS (CMSAM 2018), 2018, 310 : 6 - 13
  • [29] Text Classification Research with Attention-based Recurrent Neural Networks
    Du, C.
    Huang, L.
    INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, 2018, 13 (01) : 50 - 61
  • [30] A Neural Attention Based Approach for Clickstream Mining
    Chandramohan, T. N.
    Ravindran, Balaraman
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, PT II, 2017, 10614 : 776 - 777