本文選題：基尼系數(shù) + 反恐　； 參考：《情報(bào)雜志》2017年04期

【摘要】：[目的/意義]利用數(shù)據(jù)挖掘技術(shù)對恐怖分子的各種日常信息,如購物、社交、交通、通話記錄、視頻等行為進(jìn)行分析,對涉恐線索進(jìn)行預(yù)警和排查,越來越成為國際反恐的通用手段之一。如何利用數(shù)據(jù)挖掘?qū)Υ罅康纳婵只A(chǔ)數(shù)據(jù)進(jìn)行快速分類成為當(dāng)前涉恐情報(bào)分析的研究熱點(diǎn)。[方法/過程]將研究如何利用基于基尼系數(shù)的特征選擇方法對涉恐人員的情報(bào)信息進(jìn)行快速分類。分類步驟分為多個(gè)層次的屬性分裂,其中每個(gè)層次中包括三個(gè)步驟,分別為計(jì)算樣本集的基尼系數(shù),計(jì)算不同屬性的基尼系數(shù),通過比較基尼系數(shù)選擇分裂屬性。[結(jié)果/結(jié)論]該方法可以對大量涉恐情報(bào)基礎(chǔ)數(shù)據(jù)進(jìn)行快速分類,提高反恐預(yù)警的效率。
[Abstract]:[objective / significance] using data mining technology to analyze the daily information of terrorists, such as shopping, social, traffic, phone records, video, etc., and to warn and search for terrorist clues. Increasingly, it has become one of the universal means of international terrorism. How to use data mining to quickly classify a large number of basic data has become a hot topic in the field of information analysis. Methods / processes will be studied how to use the Gini coefficient based feature selection method to quickly classify the intelligence information of persons involved in terrorism. The classification steps are divided into multiple levels of attribute splitting, in which each level consists of three steps, one is to calculate the Gini coefficient of the sample set and the other is to calculate the Gini coefficient of different attributes, and the other is to choose the split attribute by comparing the Gini coefficient. [results / conclusion] this method can quickly classify a large amount of terrorist intelligence data and improve the efficiency of anti-terrorism early warning.
【作者單位】： 中國人民公安大學(xué);湖南財(cái)經(jīng)工業(yè)職業(yè)技術(shù)學(xué)院;
【基金】：中國人民公安大學(xué)基本科研業(yè)務(wù)費(fèi)項(xiàng)目“大數(shù)據(jù)環(huán)境下反恐怖情報(bào)的數(shù)據(jù)挖掘分類方法研究”(編號:2015JKF01223) 國家社會科學(xué)基金項(xiàng)目“反恐維穩(wěn)背景下邊疆地區(qū)維穩(wěn)戰(zhàn)略研究”(編號:14BZZ028)的研究成果之一
【分類號】：C934;G350

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 佟賀豐;馬崢;曹燕;于潔;黃慕萱;;中國高校論文產(chǎn)出的基尼系數(shù)研究[J];高教發(fā)展與評估;2012年03期

，

本文編號：1970853