面向监狱服刑人员的聚类与分类算法研究  

Clustering and classification algorithms for prisoners

作　　者：郭曼 张世春 程利 徐鹏[3] 王建元[4] 冷彪[4] GUO Man;ZHANG Shi chun;CHENG Li;XU Peng;WANG Jian yuan;LENG Biao(Torch High Technology Industry Development Center,Ministry of Science and Technology,Beijing 100045;Information Science and Technology Department,Chongqing Prison Administration,Chongqing 404100;Shandong Police Training Institute,Jinan 250014;School of Computer Science and Engineering,Beihang University,Beijing 100191,China)

机构地区：[1]科学技术部火炬高技术产业开发中心,北京100045 [2]重庆市监狱管理局信息科技处,重庆404100 [3]山东省警官培训学院,山东济南250014 [4]北京航空航天大学计算机学院,北京100191

出　　处：《计算机工程与科学》2018年第7期1323-1328,共6页Computer Engineering & Science

基　　金：国家科技支撑项目(2014BAK06B04)

摘　　要：分别提出了面向服刑人员的聚类和分类算法,针对服刑人员的表现特征在服刑期内连续变化和多样性的特点,分别采用隐马尔可夫模型为聚类模型和LDA主题模型为分类模型,对应急指挥综合管理平台中所收集到的多种服刑人员的业务管理信息进行综合聚类分类处理。实验表明,隐马尔可夫模型可以体现出各服刑人员在整个服刑阶段表现的时序变化,从而进行准确的聚类判断;LDA主题模型可以考虑到服刑人员的多种属性,从而对其进行准确的类别判断。We propose a clustering algorithm and a classification algorithm for prisoners.Considering that prisoners feature continuous changing and diversity,we use the hidden Markov model as the clustering model and the latent Dirichlet allocation（LDA）topic model as the classification model,and perform clustering and classification on the management information of various prisoners collected by the emergency command management platform.Experiments show that the hidden Markov model can reflect the temporal changes of each prisoner＇s performance in the entire sentence,so accurate clustering results can be obtained.The LDA topic model can accurately determine the class of the prisoners according to a variety of their attributes.

关 键 词：服刑人员 聚类 分类 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]