A hybrid approach to clustering in very large databases

Aoying Zhou; Weining Qian; Hailei Qian; Jin Wen; Shuigeng Zhou; Ye Fan

doi:10.1007/3-540-45357-1_55

A hybrid approach to clustering in very large databases

Aoying Zhou
, Weining Qian
, Hailei Qian
, Jin Wen
, Shuigeng Zhou
, Ye Fan

Fudan University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Current clustering methods always have such problems: 1) High I/O cost and expensive maintenance; 2) Pre-specifying the uncertain parameter k; 3) Lacking good efficiency in treating arbitrary shape under very large data set environment. In this paper, we first present a hybrid-clustering algorithm to solve these problems. It combines both distance and density strategies, and makes full use of statistics information while keeping good cluster quality. The experimental results show that our algorithm outperforms other popular algorithms in terms of efficiency, cost, and even get much more speedup as the data size scales up.

Original language	English
Title of host publication	Advances in Knowledge Discovery and Data Mining - 5th Pacific-Asia Conference, PAKDD 2001, Proceedings
Editors	David Cheung, Graham J. Williams, Qing Li
Publisher	Springer Verlag
Pages	519-524
Number of pages	6
ISBN (Print)	3540419101, 9783540419105
DOIs	https://doi.org/10.1007/3-540-45357-1_55
State	Published - 2001
Externally published	Yes
Event	5th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2001 - Kowloon, Hong Kong Duration: 16 Apr 2001 → 18 Apr 2001

Publication series

Name	Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume	2035
ISSN (Print)	0302-9743

Conference

Conference	5th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2001
Country/Territory	Hong Kong
City	Kowloon
Period	16/04/01 → 18/04/01

Access to Document

10.1007/3-540-45357-1_55

Cite this

Zhou, A., Qian, W., Qian, H., Wen, J., Zhou, S., & Fan, Y. (2001). A hybrid approach to clustering in very large databases. In D. Cheung, G. J. Williams, & Q. Li (Eds.), Advances in Knowledge Discovery and Data Mining - 5th Pacific-Asia Conference, PAKDD 2001, Proceedings (pp. 519-524). (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science); Vol. 2035). Springer Verlag. https://doi.org/10.1007/3-540-45357-1_55

Zhou, Aoying ; Qian, Weining ; Qian, Hailei et al. / A hybrid approach to clustering in very large databases. Advances in Knowledge Discovery and Data Mining - 5th Pacific-Asia Conference, PAKDD 2001, Proceedings. editor / David Cheung ; Graham J. Williams ; Qing Li. Springer Verlag, 2001. pp. 519-524 (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)).

@inproceedings{f88ddd2adaa44077b58912376222688f,

title = "A hybrid approach to clustering in very large databases",

abstract = "Current clustering methods always have such problems: 1) High I/O cost and expensive maintenance; 2) Pre-specifying the uncertain parameter k; 3) Lacking good efficiency in treating arbitrary shape under very large data set environment. In this paper, we first present a hybrid-clustering algorithm to solve these problems. It combines both distance and density strategies, and makes full use of statistics information while keeping good cluster quality. The experimental results show that our algorithm outperforms other popular algorithms in terms of efficiency, cost, and even get much more speedup as the data size scales up.",

author = "Aoying Zhou and Weining Qian and Hailei Qian and Jin Wen and Shuigeng Zhou and Ye Fan",

note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2001.; 5th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2001 ; Conference date: 16-04-2001 Through 18-04-2001",

year = "2001",

doi = "10.1007/3-540-45357-1\_55",

language = "英语",

isbn = "3540419101",

series = "Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)",

publisher = "Springer Verlag",

pages = "519--524",

editor = "David Cheung and Williams, \{Graham J.\} and Qing Li",

booktitle = "Advances in Knowledge Discovery and Data Mining - 5th Pacific-Asia Conference, PAKDD 2001, Proceedings",

address = "德国",

}

Zhou, A , Qian, W, Qian, H, Wen, J, Zhou, S & Fan, Y 2001, A hybrid approach to clustering in very large databases. in D Cheung, GJ Williams & Q Li (eds), Advances in Knowledge Discovery and Data Mining - 5th Pacific-Asia Conference, PAKDD 2001, Proceedings. Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science), vol. 2035, Springer Verlag, pp. 519-524, 5th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2001, Kowloon, Hong Kong, 16/04/01. https://doi.org/10.1007/3-540-45357-1_55

A hybrid approach to clustering in very large databases. / Zhou, Aoying ; Qian, Weining; Qian, Hailei et al.
Advances in Knowledge Discovery and Data Mining - 5th Pacific-Asia Conference, PAKDD 2001, Proceedings. ed. / David Cheung; Graham J. Williams; Qing Li. Springer Verlag, 2001. p. 519-524 (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science); Vol. 2035).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A hybrid approach to clustering in very large databases

AU - Zhou, Aoying

AU - Qian, Weining

AU - Qian, Hailei

AU - Wen, Jin

AU - Zhou, Shuigeng

AU - Fan, Ye

N1 - Publisher Copyright: © Springer-Verlag Berlin Heidelberg 2001.

PY - 2001

Y1 - 2001

N2 - Current clustering methods always have such problems: 1) High I/O cost and expensive maintenance; 2) Pre-specifying the uncertain parameter k; 3) Lacking good efficiency in treating arbitrary shape under very large data set environment. In this paper, we first present a hybrid-clustering algorithm to solve these problems. It combines both distance and density strategies, and makes full use of statistics information while keeping good cluster quality. The experimental results show that our algorithm outperforms other popular algorithms in terms of efficiency, cost, and even get much more speedup as the data size scales up.

AB - Current clustering methods always have such problems: 1) High I/O cost and expensive maintenance; 2) Pre-specifying the uncertain parameter k; 3) Lacking good efficiency in treating arbitrary shape under very large data set environment. In this paper, we first present a hybrid-clustering algorithm to solve these problems. It combines both distance and density strategies, and makes full use of statistics information while keeping good cluster quality. The experimental results show that our algorithm outperforms other popular algorithms in terms of efficiency, cost, and even get much more speedup as the data size scales up.

UR - https://www.scopus.com/pages/publications/84942933944

U2 - 10.1007/3-540-45357-1_55

DO - 10.1007/3-540-45357-1_55

M3 - 会议稿件

AN - SCOPUS:84942933944

SN - 3540419101

SN - 9783540419105

T3 - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

SP - 519

EP - 524

BT - Advances in Knowledge Discovery and Data Mining - 5th Pacific-Asia Conference, PAKDD 2001, Proceedings

A2 - Cheung, David

A2 - Williams, Graham J.

A2 - Li, Qing

PB - Springer Verlag

T2 - 5th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2001

Y2 - 16 April 2001 through 18 April 2001

ER -

Zhou A , Qian W, Qian H, Wen J, Zhou S, Fan Y. A hybrid approach to clustering in very large databases. In Cheung D, Williams GJ, Li Q, editors, Advances in Knowledge Discovery and Data Mining - 5th Pacific-Asia Conference, PAKDD 2001, Proceedings. Springer Verlag. 2001. p. 519-524. (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)). doi: 10.1007/3-540-45357-1_55

A hybrid approach to clustering in very large databases

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this