Visual assessment of clustering tendency for incomplete data

Laurence A. F. Park; James C. Bezdek; Christopher Leckie; Kotagiri Ramamohanarao; James Bailey; Marimuthu Palaniswami

doi:10.1109/TKDE.2016.2608821

Visual assessment of clustering tendency for incomplete data

Laurence A. F. Park, James C. Bezdek, Christopher Leckie, Kotagiri Ramamohanarao, James Bailey, Marimuthu Palaniswami

Western Sydney University

Research output: Contribution to journal › Article › peer-review

11 Citations (Scopus)

Abstract

The iVAT (asiVAT) algorithms reorder symmetric (asymmetric) dissimilarity data so that an image of the data may reveal cluster substructure. Images formed from incomplete data don't offer a very rich interpretation of cluster structure. In this paper, we examine four methods for completing the input data with imputed values before imaging. We choose a best method using contaminated versions of the complete Iris data, for which the desired results are known. Then, we analyze two real world data sets from social networks that are incomplete using the best imputation method chosen in the juried trials with Iris: (i) Sampson's monastery data, an incomplete, asymmetric relation matrix; and (ii) the karate club data, comprising a symmetric similarity matrix that is about 86 percent incomplete.

Original language	English
Pages (from-to)	3409-3422
Number of pages	14
Journal	IEEE Transactions on Knowledge and Data Engineering
Volume	28
Issue number	12
DOIs	https://doi.org/10.1109/TKDE.2016.2608821
Publication status	Published - 1 Dec 2016

Bibliographical note

Publisher Copyright:
© 1989-2012 IEEE.

Keywords

cluster heat maps
incomplete data
visualization

Access to Document

10.1109/TKDE.2016.2608821

Cite this

@article{3532535b61084b6db3b1ec14e01085b6,

title = "Visual assessment of clustering tendency for incomplete data",

abstract = "The iVAT (asiVAT) algorithms reorder symmetric (asymmetric) dissimilarity data so that an image of the data may reveal cluster substructure. Images formed from incomplete data don't offer a very rich interpretation of cluster structure. In this paper, we examine four methods for completing the input data with imputed values before imaging. We choose a best method using contaminated versions of the complete Iris data, for which the desired results are known. Then, we analyze two real world data sets from social networks that are incomplete using the best imputation method chosen in the juried trials with Iris: (i) Sampson's monastery data, an incomplete, asymmetric relation matrix; and (ii) the karate club data, comprising a symmetric similarity matrix that is about 86 percent incomplete.",

keywords = "cluster heat maps, incomplete data, visualization",

author = "Park, {Laurence A. F.} and Bezdek, {James C.} and Christopher Leckie and Kotagiri Ramamohanarao and James Bailey and Marimuthu Palaniswami",

note = "Publisher Copyright: {\textcopyright} 1989-2012 IEEE.",

year = "2016",

month = dec,

day = "1",

doi = "10.1109/TKDE.2016.2608821",

language = "English",

volume = "28",

pages = "3409--3422",

journal = "IEEE Transactions on Knowledge and Data Engineering",

issn = "1041-4347",

publisher = "IEEE Computer Society",

number = "12",

}

TY - JOUR

T1 - Visual assessment of clustering tendency for incomplete data

AU - Park, Laurence A. F.

AU - Bezdek, James C.

AU - Leckie, Christopher

AU - Ramamohanarao, Kotagiri

AU - Bailey, James

AU - Palaniswami, Marimuthu

PY - 2016/12/1

Y1 - 2016/12/1

N2 - The iVAT (asiVAT) algorithms reorder symmetric (asymmetric) dissimilarity data so that an image of the data may reveal cluster substructure. Images formed from incomplete data don't offer a very rich interpretation of cluster structure. In this paper, we examine four methods for completing the input data with imputed values before imaging. We choose a best method using contaminated versions of the complete Iris data, for which the desired results are known. Then, we analyze two real world data sets from social networks that are incomplete using the best imputation method chosen in the juried trials with Iris: (i) Sampson's monastery data, an incomplete, asymmetric relation matrix; and (ii) the karate club data, comprising a symmetric similarity matrix that is about 86 percent incomplete.

AB - The iVAT (asiVAT) algorithms reorder symmetric (asymmetric) dissimilarity data so that an image of the data may reveal cluster substructure. Images formed from incomplete data don't offer a very rich interpretation of cluster structure. In this paper, we examine four methods for completing the input data with imputed values before imaging. We choose a best method using contaminated versions of the complete Iris data, for which the desired results are known. Then, we analyze two real world data sets from social networks that are incomplete using the best imputation method chosen in the juried trials with Iris: (i) Sampson's monastery data, an incomplete, asymmetric relation matrix; and (ii) the karate club data, comprising a symmetric similarity matrix that is about 86 percent incomplete.

KW - cluster heat maps

KW - incomplete data

KW - visualization

UR - http://handle.uws.edu.au:8081/1959.7/uws:37761

U2 - 10.1109/TKDE.2016.2608821

DO - 10.1109/TKDE.2016.2608821

M3 - Article

SN - 1041-4347

VL - 28

SP - 3409

EP - 3422

JO - IEEE Transactions on Knowledge and Data Engineering

JF - IEEE Transactions on Knowledge and Data Engineering

IS - 12

ER -

Visual assessment of clustering tendency for incomplete data

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this