Research on Application of Compressed Pattern Mining in the Field of Counter-Terrorism Intelligence

Abstract

Abstract: It is necessary to compress the information which is deduced from mass counter-terrorism
data to reduce the data volume. According to the demands and features of counter-terrorism intelligence
analysis, we need to modify the ways of generating the a priori knowledge, deducing frequent item sets and
filtrating special rules. This method of mining compressed patterns is helpful to reduce the data volume of
intelligence information and improve the veracity and targeted degree of intelligence in the field of counter
terrorism.

Key words: Compressed pattern, Counter terrorism intelligence, Redundant rule, General rule, Maximal
frequent pattern

Li Yongnan. Research on Application of Compressed Pattern Mining in the Field of Counter-Terrorism Intelligence [J]. Libraly Journal, 2019, 38(6): 69-75.

References

[ 1 ] 程聪慧, 郭俊华. 网络恐怖主义的挑战及其防范[J].情报杂志, 2015(3): 10-15.
[ 2 ] 谢邦昌. 放眼大数据[J]. 中国统计, 2018(1): 9-10.
[ 3 ] 人民网 . 郭声琨调研国家反恐情报信息平台: 反恐坚持情报先行[EB/OL]. [2018-08-08].http://legal.people.com.cn/n/2015/1126/c42510-27858719.html.
[ 4 ] 徐腾跃. 构建公安派出所为基点的反恐工作模式的思考[J]. 安徽警官职业学院学报, 2014, 13(5):62-64.
[ 5 ] Ball L. Automating social network analysis: A powertool for counter- terrorism[J]. Security Journal, 2016,29(2): 147-168.
[ 6 ] Neo L S, Khader M, Ang J, et al. Developing an earlyscreening guide for jihadi terrorism: A behaviouralanalysis of 30 terror attacks[J]. Security Journal,2017, 30(1): 227-246.
[ 7 ] Merrick J R W, Leclerc P. Modeling adversaries incounterterrorism decisions using prospect theory[J].Risk Analysis, 2016, 36(4): 681-693.
[ 8 ] Ide T. Terrorism in the textbook: a comparativeanalysis of terrorism discourses in Germany, India,Kenya and the United States based on school textbooks[J]. Cambridge Review of InternationalAffairs, 2017, 30(1): 44-66.
[ 9 ] Stewart M G, Mueller J. A risk and cost–benefitanalysis of police counter-terrorism operationsat Australian airports[J]. Journal of Policing,Intelligence and Counter Terrorism, 2014, 9(2):98-116.
[10] 李勇男, 梅建明. 基于频繁模式树的涉恐情报关联分析[J]. 情报科学, 2017, 35(9): 141-145, 152.
[11] 李勇男, 梅建明. 先验原理在涉恐情报分析中的应用研究[J]. 情报杂志, 2017, 36(8): 23-26.
[12] 陈鹏, 瞿珂, 陈刚, 等. 反恐背景下的个人特征数据构成与涉恐个体的挖掘分析[J]. 情报杂志,2018, (4): 38-41, 68.
[13] Zaki M J. Mining Non-Redundant AssociationRules[J]. Data Mining & Knowledge Discovery,2004, 9(3): 223-248.
[14] Calders T, Goethals B. Mining All Non-derivableFrequent Itemsets[C]// European Conference onPrinciples of Data Mining and Knowledge Discovery.Springer-Verlag, 2002: 74-85.
[15] 刘君强, 孙晓莹, 庄越挺, 等. 挖掘闭合模式的高性能算法[J]. 软件学报, 2004, 15(1): 94-102.
[16] Bayardo R J. Efficiently mining long patternsfrom databases[C]// ACM SIGMOD InternationalConference on Management of Data. ACM, 1998:85-93.
[17] 但红卫. 基于偏序的频繁序列模式压缩算法研究[D].杭州: 浙江大学, 2007.
[18] 张心静. 最大频繁项集挖掘算法的研究[D]. 长春:长春工业大学, 2016.
[19] Shaw G, Xu Y, Geva S. Utilizing Non-redundantAssociation Rules from Multi-level Datasets[C]//Ieee/wic/acm International Conference on WebIntelligence and Intelligent Agent Technology, 2008.Wi-Iat. IEEE, 2008: 681-684.
[20] 网易新闻. 国信办专题片揭示暴恐音视频与暴恐活动之间的联系[EB/OL]. [2018-08-08]. http://news.163.com/14/0624/11/9VGIV4UF00014JB5.html.
[21] 王娜. 一种冗余规则删减方法及其应用[D]. 大连:大连理工大学, 2011.
[22] 新疆维吾尔自治区人民政府. 新疆维吾尔自治区去极端化条例[EB/OL]. [2018-08-08]. http:// www.xinjiang.gov.cn/2017/03/30/128831.html.
[23] 新疆统一战线. 识别宗教极端活动(75种具体表现)基础知识 [EB/OL]. [2018-08-08]. http://www.xjtzb.gov.cn/2017-06/19/c_1121167461.htm.
[24] 李勇男, 梅建明, 秦广军. 反恐情报分析中的数据预处理研究[J]. 情报科学, 2017, 35(11): 103-107,113.
[25] 秦亮曦, 史忠植. SFP-Max——基于排序FP-树的最大频繁模式挖掘算法[J]. 计算机研究与发展,2005, 42(2): 217-223.
[26] Pipino L, Kopcso D. Data Mining, Dirty Data, andCosts[C]// International Conference on InformationQuality. DBLP, 2004: 164-169.
[27] 李勇男. 基于频繁序列模式挖掘的反恐情报关联分析[J]. 情报理论与实践. 2018, 41(10): 100-104, 46.
[28] 李勇男. 空间模式挖掘在反恐情报分析中的应用研究[J]. 情报杂志, 2018, 37(4): 33-37.
[29] 李勇男.时空轨迹频繁模式在反恐情报分析中的应用研究[J]. 情报杂志, 2018, 37(8): 51-55.