基于多域的互联网物理对象关联分析方法研究

Research on Correlation Analysis of Physical Objects on Internet Based on Multi-domain Fusion

随着物联网技术的发展应用,越来越多的物理对象能被远程主机感知发现,相关物理对象的属性信息能被搜集和表示,但目前对于物理对象属性信息的分析和研究还不够系统全面。为深入研究物理对象,把物理对象的属性信息分为社会域、信息域和物理域三个多域层次,通过融合分析物理对象的多域属性信息,发掘物理对象之间的关联特性,能找出网络空间中物理对象之间隐含的关联情况。综合物理对象不同域中的属性信息,建立不同的关联计算方法得出物理对象多域关联关系矩阵,最后结合改进的马尔可夫聚类算法综合分析物理对象之间的关联关系。实验结果表明,该方法在物理对象融合关联分析方面有较好的聚类效果。

With the development and application of Internet of Things,more and more physical objects can be discovered by remote computer,and their related attribute information can be collected and expressed.However,the analysis and research of physical object attribute information is not systematic and comprehensive.In order to research the physical objects in depth,we divide the physical object attribute into three layers of social domain,cyber domain and physical domain,and find out the implicit association between physical objects in cyberspace by exploring the correlation between physical objects with correlation analysis.In this paper,we establish different correlation calculation methods to get the multi-domain association relation matrix of physical objects in combination with the attribute information of the objects in the different domain.Finally,we combine the improved Markov clustering algorithm to analyze the correlation between physical objects.The experiments show that the method has a great clustering effect in the physical object fusion correlation analysis.