一种基于近邻表示的聚类方法  

Clustering Method Based on Nearest Neighbors Representation

作　　者：周国兵[1] 吴建鑫[1] 周嵩[1] 

机构地区：[1]计算机软件新技术国家重点实验室(南京大学),江苏南京210023

出　　处：《软件学报》2015年第11期2847-2855,共9页Journal of Software

基　　金：国家自然科学基金(61422203)

摘　　要：当今社会处在信息急剧膨胀的时代,数据的规模和维度都在不断增大,传统的聚类方法有很多难以适应这一趋势.尤其是移动计算平台的高速发展,其平台自身的特性限制了算法的内存使用规模,因此,以往的很多方法若不进行改进,在这类平台上将无法运行.提出了一种基于近邻表示的聚类方法,该方法基于近邻的思想构造出新的表示形式,这种表示可以进行压缩,因此有效地减少了聚类所需要的存储开销.实现了直接对近邻表示压缩后的数据进行聚类的算法,称为Bit k-means.实验结果表明,该方法取得了较好的效果,在提高准确率的同时,大幅度降低了存储空间开销.With the rapid expansion of information, scale and dimensionality of data are constantly increasing. Traditional clustering methods are difficult to adapt to this trend. Especially, given the fast development of mobile computing platforms, its propcrtics limit the scale of memory that algorithms can use, so many algorithms cannot run on such platforms without making improvements. This paper proposes a clustering method based on nearest neighbor representation. This method uses the idea of nearest neighbors to construct the new representation. This new representation is compressible, thus effectively reducing the storage cost required for clustering. An algorithm called Bit k-means in implemented to perform clustering directly on the compressed nearest neighbors representation. Experimental results show that the new method achieves higher accuracy and substantially reduces the storage cost.

关 键 词：近邻 聚类 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]