Enhanced Visual Analysis for Cluster Tendency Assessment and Data Partitioning

CASIA OpenIR > 智能感知与计算研究中心

	Enhanced Visual Analysis for Cluster Tendency Assessment and Data Partitioning
	Wang, Liang1 ; Geng, Xin 3,4; Bezdek, James 2; Leckie, Christopher 2; Ramamohanarao, Kotagiri 2
发表期刊	IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
	2010-10-01
卷号	22 期号:10 页码:1401-1414
文章类型	Article
摘要	Visual methods have been widely studied and used in data cluster analysis. Given a pairwise dissimilarity matrix D of a set of n objects, visual methods such as the VAT algorithm generally represent D as an n x n image I((D) over bar) where the objects are reordered to reveal hidden cluster structure as dark blocks along the diagonal of the image. A major limitation of such methods is their inability to highlight cluster structure when D contains highly complex clusters. This paper addresses this limitation by proposing a Spectral VAT algorithm, where D is mapped to D' in a graph embedding space and then reordered to (D) over tilde using the VAT algorithm. A strategy for automatic determination of the number of clusters in I (D) over tilde' is then proposed, as well as a visual method for cluster formation from I((D) over tilde)' based on the difference between diagonal blocks and off-diagonal blocks. A sampling-based extended scheme is also proposed to enable visual cluster analysis for large data sets. Extensive experimental results on several synthetic and real-world data sets validate our algorithms.
关键词	Clustering Vat Cluster Tendency Spectral Embedding Out-of-sample Extension
WOS标题词	Science & Technology ; Technology
关键词[WOS]	LARGE DATA SETS ; ALGORITHMS ; VALIDITY ; INDEXES ; NUMBER ; AID
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Engineering, Electrical & Electronic
WOS记录号	WOS:000281000500005
引用统计	被引频次：29[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/9948
专题	智能感知与计算研究中心
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Melbourne, Dept Comp Sci & Software Engn, Melbourne, Vic 3010, Australia 3.Southeast Univ, Sch Engn & Comp Sci, Nanjing 210096, Peoples R China 4.Monash Univ, Sch Math Sci, Clayton, Vic 3800, Australia
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Wang, Liang,Geng, Xin,Bezdek, James,et al. Enhanced Visual Analysis for Cluster Tendency Assessment and Data Partitioning[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2010,22(10):1401-1414.
APA	Wang, Liang,Geng, Xin,Bezdek, James,Leckie, Christopher,&Ramamohanarao, Kotagiri.(2010).Enhanced Visual Analysis for Cluster Tendency Assessment and Data Partitioning.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,22(10),1401-1414.
MLA	Wang, Liang,et al."Enhanced Visual Analysis for Cluster Tendency Assessment and Data Partitioning".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 22.10(2010):1401-1414.