東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

The K-Means Tree.

Gao, Kun.

Linked to FindBook

Google Book

Amazon

博客來

The K-Means Tree.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	The K-Means Tree./
Author:	Gao, Kun.
Description:	73 p.
Notes:	Source: Dissertation Abstracts International, Volume: 64-03, Section: B, page: 1320.
Contained By:	Dissertation Abstracts International64-03B.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3084293

The K-Means Tree.
Gao, Kun.

The K-Means Tree. - 73 p.

Source: Dissertation Abstracts International, Volume: 64-03, Section: B, page: 1320.

Thesis (Ph.D.)--Yale University, 2003.

Due to the fast development and wide use of computer technologies in recent years, data sets have become increasingly large and complicated. There has been growing emphasis on exploratory analysis of very large datasets to discover clusters both to reduce the size of later calculations, and also to identify interesting subsets for further exploration. However, most existing clustering methods become slow and inefficient as the size of dataset increases.Subjects--Topical Terms:

626642
Computer Science.

The K-Means Tree.
LDR:01836nam 2200277 a 45 001 927443
005 20110425
008 110425s2003 eng d
035 $a (UnM)AAI3084293
035 $a AAI3084293
040 $a UnM $c UnM
100 1 $a Gao, Kun. $3 1251002
245 1 0 $a The K-Means Tree.
300 $a 73 p.
500 $a Source: Dissertation Abstracts International, Volume: 64-03, Section: B, page: 1320.
500 $a Supervisor: John Hartigan.
502 $a Thesis (Ph.D.)--Yale University, 2003.
520 $a Due to the fast development and wide use of computer technologies in recent years, data sets have become increasingly large and complicated. There has been growing emphasis on exploratory analysis of very large datasets to discover clusters both to reduce the size of later calculations, and also to identify interesting subsets for further exploration. However, most existing clustering methods become slow and inefficient as the size of dataset increases.
520 $a In this thesis, we propose a new fast clustering algorithm called the <italic> K</italic>-Means Tree. This method builds a tree iteratively by first passing data points into the previously constructed tree one at a time, and then refining the tree by further re-allocating the data points to the tree one-at-a-time. We compare the speed and cluster quality of the <italic>K</italic>-Means Tree with existing algorithms, and show that it has comparable speed to the fastest competing algorithm, and produces clusters of comparable quality to the <italic> K</italic>-Means clusters.
590 $a School code: 0265.
650 4 $a Computer Science. $3 626642
650 4 $a Statistics. $3 517247
690 $a 0463
690 $a 0984
710 2 0 $a Yale University. $3 515640
773 0 $t Dissertation Abstracts International $g 64-03B.
790 $a 0265
790 1 0 $a Hartigan, John, $e advisor
791 $a Ph.D.
792 $a 2003
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3084293