Analysis Model of Terrorist Attacks Based on Big Data

• Main Authors: Zhenkai, LIN, Yimin, DOU, Jinping, LI
• Format: Conference Proceeding
• Language: English
• Subjects: Analytical models; anti-terrorism warning; cascade network with attention mechanism; Correlation; data modeling; Data models; Feature extraction; Hazards; K-means; Predictive models; SVD; Terrorism
• ISSN: 1948-9447
• DOI: 10.1109/CCDC49329.2020.9164626

With the continuous deepening of international anti-terrorism movement the anti-terrorism has entered a new stage 5 and it is facing new challenges. One of the new challenges is to extract useful and valuable information from massive data efficiently. The anti-terrorism system model based on local shallow information is imperfect, which is not conducive to obtaining accurate prediction results. The shortcomings of existing research are the lack of comprehensive analysis and deeper mining of data. In order to improve the efficiency and accuracy of the present anti-terrorism system 5 we propose an effective method for risk assessment and prediction based on machine learning by using Global Terrorism Database (GTD). There are four basic steps: first, we reduce the data dimension through correlation calculation and Singular Value Decomposition(SVD) then the function is established to rank the harmfulness of terrorist attacks; second, the cascaded network with attention mechanism is used to predict suspects; third, k-means is used to cluster the regions of terrorist attacks 5 and then we establish a generalized linear regression model to predict the situation of terrorist attacks. We verify the feasibility of the model by comparing with the real data. The experimental results show that the proposed method can analyze and predict the information related to terrorist attacks comprehensively and accurately.