• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International journal of data mining, modelling and management >Country crime analysis using the self-organising map, with special regard to economic factors
【24h】

Country crime analysis using the self-organising map, with special regard to economic factors

机译：使用自组织地图对国家犯罪进行分析，并特别考虑经济因素

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Data mining techniques have not been broadly applied in the study of crime. Criminologists and law enforcement need an instrument to efficiently analyse these data. We applied the self-organising map (SOM) to mapping countries with different economic situations of crime. The dataset was comprised of 50 countries and 30 variables. After initial processing of the data with the SOM, four clusters of countries were identified. Then the dataset was re-processed by ScatterCounter and four weak variables were removed. It was found that some roughly defined patterns of crime situation can be identified in traditionally economically homogeneous countries. Among different countries, positive correlation on crime in some countries may have negative correlation in other countries. Results of the study proved that, after the validation of ScatterCounter's separation power function, A-means clustering and nearest neighbour searching, the SOM can be a new tool for mapping criminal phenomena through processing of multivariate data.
机译：数据挖掘技术尚未广泛应用于犯罪研究。犯罪学家和执法部门需要一种工具来有效地分析这些数据。我们将自组织地图（SOM）应用于绘制具有不同经济状况的犯罪国家的地图。数据集由50个国家和30个变量组成。在使用SOM初步处理数据之后，确定了四个国家类别。然后，数据集由ScatterCounter重新处理，并删除了四个弱变量。研究发现，在传统上经济上均一的国家中，可以确定一些大致定义的犯罪情况模式。在不同国家之间，某些国家的犯罪正相关在其他国家可能具有负相关。研究结果证明，在验证了ScatterCounter的分离能力函数，A均值聚类和最近邻搜索之后，SOM可以成为通过处理多元数据来映射犯罪现象的新工具。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号