频繁子图在监控系统数据挖掘中的应用  

Application of Frequent Subgraph on Monitoring System Data Mining

作　　者：史伟奇[1] 

机构地区：[1]湖南警察学院信息技术(网监)系,长沙410138

出　　处：《价值工程》2015年第9期298-300,共3页Value Engineering

基　　金：湖南省教育规划课题阶段性成果(警察信息素质教育理念及实战能力培养研究XJK013CXX012);湖南省公安厅资助科研项目(No.2013);湖南警察学院院级教学改革研究项目(湘警院教(2014)9号)

摘　　要：监控系统数据挖掘研究近年来受到了国内外学者的逐渐关注,监控系统数据挖掘是发现基于视频原始底层数据对应于应用层的语义信息关联及对应关系。视频底层数据特征十分复杂,沿用传统数据挖掘思想去理解和看待监控系统数据挖掘还不够。与一般的数据比较,图能够表达更加丰富的语义。把监控系统视频数据转化为图模型,将频繁子图挖掘算法应用到监控系统语义挖掘中,提出一种新的监控系统语义挖掘方法,与现有的方法相比较,该方法具有有效性和可行性。In recent years, more and more researchers over the world show great interests in monitoring system data mining gradually.The purpose of the monitoring system data mining is to establish the mapping between the underlying video data to high-level semantic information. Because this mapping is more complex, most of the research follows the idea of traditional data mining to understand and look at the monitor data mining. Compared with other data, graph can express richer semantic meaning. Converted monitoring system video data to graph data model, which frequent subgraph mining algorithm is applied to the monitoring system data mining. A prototype based on the model had been developed, and validated the correctness of the model, which can provide enlightenment to the designers Who work at monitoring system data mining.

关 键 词：频繁子图 数据特征 监控系统 语义挖掘 

分 类 号：TP311.1[自动化与计算机技术—计算机软件与理论]