Social security event recognition based on plan recognition

被引：0
|
作者：
Ma Y. [1 ]
Qi C. [2 ]
Wang H. [1 ,2 ]
Wang L. [3 ]
机构：
[1] School of Automation, Huazhong University of Science and Technology, Wuhan
[2] School of Management, Huazhong University of Science and Technology, Wuhan
[3] Department of Public Security, China Criminal Police College, Shenyang
来源：
Xitong Gongcheng Lilun yu Shijian/System Engineering Theory and Practice | 2019年 / 39卷 / 10期
基金：
国家重点研发计划;
关键词：
Event recognition; Personnel gathering; Plan recognition; Social security event;
D O I：
10.12011/1000-6788-2018-2022-09
中图分类号：
学科分类号：
摘要：
Before a social security event occurs, it usually goes through a process of planning and preparation. The social security event that is brewing might be identified in advance according to the behavior and actions of the participants in the preparation process. Although the preparation actions hardly show abnormal characteristics separately, an underlying event might be found if multiple participants' actions and their relationships are comprehensively analyzed. The paper assumes that some of the actions of participants in the preparation process of some social security events can be observed. A social security event recognition method based on plan recognition is proposed. The social security event recognition model framework is constructed firstly. The domain knowledge and problem model of social security event recognition are described. Then the corresponding event recognition algorithm is proposed employing the method of plan recognition as planning (PRAP). The algorithm is capable of reasoning using domain knowledge, and identifying the possible event dynamically. Finally, an experimental example is designed based on the personnel gathering event, and the effectiveness of the method is tested. The experimental results show that the method can accurately identify the social security event corresponding to the participants' actions, and has strong ability to identify in advance. It can improve the monitoring and early warning capability of social security events. © 2019, Editorial Board of Journal of Systems Engineering Society of China. All right reserved.
引用
收藏
页码：2628 / 2636
页数：8
相关论文
共 22 条
  • [1] Chen J.H., Li G., A survival analysis of network public opinion evolution in social security emergency-Based on 70 major social security emergencies analysis, Journal of Intelligence, 35, 4, pp. 70-74, (2016)
  • [2] Du K., Wang W., Nian F., Et al., Concealed objects detection in active millimeter-ware images, Systems Engineering and Electronics, 38, 6, pp. 1462-1469, (2016)
  • [3] Wang C.Y., Weng W.G., Wang J.Y., Design and application for stampede accident risk analysis algorithm, Systems Engineering-Theory & Practice, 37, 3, pp. 691-699, (2017)
  • [4] Zhang J., Zhuang Y., View-independent human action recognition by action hypersphere in nonlinear subspace, Pacific-Rim Conference on Multimedia, pp. 108-117, (2007)
  • [5] Shao Z.F., Cai J.J., Wang Z.Y., Et al., Analytical processing method of big surveillance video data based on smart monitoring cameras, Journal of Electronics & Information Technology, 39, 5, pp. 1116-1122, (2017)
  • [6] Cao H., Fan T.J., Li S.X., CA-based dynamic risk assessment of toxic gas leakage accidents, Systems Engineering-Theory & Practice, 36, 1, pp. 253-262, (2016)
  • [7] Guo J., Zhao S.J., Huang C.F., A study on the systematic error and correction of the probabilistic risk of natural disaster, Systems Engineering-Theory & Practice, 37, 2, pp. 523-534, (2017)
  • [8] Kang H.W., Kang H.B., Prediction of crime occurrence from multi-modal data using deep learning, PLoS ONE, 12, 4, (2017)
  • [9] Hassani H., Huang X., Silva E.S., Et al., A review of data mining applications in crime, Statistical Analysis and Data Mining: The ASA Data Science Journal, 9, 3, pp. 139-154, (2016)
  • [10] Li G., Wang X., Ye G.H., A review of emergency early-warning researches in China, Information Studies: Theory & Application, 40, 7, pp. 138-144, (2017)
123