基于共形几何代数的C-球壳聚类方法及其实现  

C-Spherical Shell Clustering Algorithm Based on Conformal Geometric Algebra and Its Realization

作　　者：李茂宽[1] 刘超[2] 

机构地区：[1]海军航空工程学院,山东烟台264001 [2]总参气象水文局,北京100081

出　　处：《现代电子技术》2010年第10期102-104,121,共4页Modern Electronics Technique

基　　金：国家自然科学基金(60672140;60802088);教育部新世纪优秀人才支持计划(NCET-05-0912)

摘　　要：提出一种新的基于共形几何代数的C-球壳聚类算法。首先C-球壳聚类分析中的模式和球壳原型,在共形几何代数中可以表示为矢量,而共形空间中模式与球壳的内积,等价于模式与球壳的距离,从而能够有效地表示球壳聚类分析中的目标函数,并且推导给出求解该目标函数最小化的新方法;介绍该算法基于VB和MatrixVB的实现,该方法将Matlab的强大计算功能与VB的windows用户界面开发方面优势结合起来,充分发挥了各自优势,缩短了软件的开发周期。实验结果表明,该算法能够有效地对球壳形数据进行聚类,计算方法正确、计算速度快、系统资源消耗少,能满足数据聚类的要求。A new C-spherical shell clustering algorithm based on conformal geometric algebra is proposed.According to the conformal geometric algebra theory,the patterns and prototypes in C-spherical shell clustering can be represented as vectors,the inner product of patterns and spherical shells in conformal space is equal to the distance from the patterns to spherical shells,and then the objective function for clustering analysis can be expressed effectively,thus a new solution to minimize the objective function is deduced.The realization of the algorithm by incorporating MatrixVB into VB is introduced.The superiority of Matlab′s powerful calculation function and Visual Basic′s friendly graphic user interface shortens the period of software development by taking the advantages of both.The experimental results show that the proposed algorithm can cluster the spherical shell data effectively,the calculating procedure is accurate and quick,and resource expenditure of computer is low.It can meet the requirement of the data clustering.

关 键 词：共形几何代数 球壳聚类 圆检测 MATRIXVB 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]