• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 人工智能与数据挖掘 • 上一篇    下一篇

面向监狱服刑人员的聚类与分类算法研究

郭曼1,张世春2,程利2,徐鹏3,王建元4,冷彪4

 
  

  1. (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)
  • 收稿日期:2016-03-02 修回日期:2016-08-31 出版日期:2018-07-25 发布日期:2018-07-25
  • 基金资助:

    国家科技支撑项目(2014BAK06B04)

Clustering and classification algorithms for prisoners

GUO Man1,ZHANG Shichun2,CHENG Li2,XU Peng3,WANG Jianyuan4,LENG Biao4   

  1. (1.Torch High Technology Industry Development Center,Ministry of Science and Technology,Beijing 100045;
    2.Information Science and Technology Department,Chongqing Prison Administration,Chongqing 404100;
    3.Shandong Police Training Institute,Jinan 250014;
    4.School of Computer Science and Engineering,Beihang University,Beijing 100191,China)
     
  • Received:2016-03-02 Revised:2016-08-31 Online:2018-07-25 Published:2018-07-25

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。

关键词: 服刑人员, 聚类, 分类

Abstract:

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.
 

Key words: prisoners, clustering, classification