東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Fractal clustering and its applicati...

Chen, Ping.

FindBook

Google Book

Amazon

博客來

Fractal clustering and its applications to projected clustering and deviation tracking.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Fractal clustering and its applications to projected clustering and deviation tracking./
作者:	Chen, Ping.
面頁冊數:	120 p.
附註:	Director: Daniel Barbara.
Contained By:	Dissertation Abstracts International62-04A.
標題:	Information Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3011630
ISBN:	0493205802

Fractal clustering and its applications to projected clustering and deviation tracking.
Chen, Ping.

Fractal clustering and its applications to projected clustering and deviation tracking. - 120 p.

Director: Daniel Barbara.

Thesis (Ph.D.)--George Mason University, 2001.

Clustering is a widely used knowledge discovery technique. It helps uncovering structures in data that were not previously known. The clustering of large datasets has received a lot of attention in recent years. However, clustering is still a challenging task since many published algorithms fail to do well in (1) scaling with the size of dataset or the number of dimensions that describe the points; (2) finding arbitrary shapes of clusters; (3) dealing effectively with the presence of noise.

ISBN: 0493205802Subjects--Topical Terms:

1017528
Information Science.

Fractal clustering and its applications to projected clustering and deviation tracking.
LDR:03398nam 2200301 a 45 001 932521
005 20110505
008 110505s2001 eng d
020 $a 0493205802
035 $a (UnM)AAI3011630
035 $a AAI3011630
040 $a UnM $c UnM
100 1 $a Chen, Ping. $3 684355
245 1 0 $a Fractal clustering and its applications to projected clustering and deviation tracking.
300 $a 120 p.
500 $a Director: Daniel Barbara.
500 $a Source: Dissertation Abstracts International, Volume: 62-04, Section: A, page: 1252.
502 $a Thesis (Ph.D.)--George Mason University, 2001.
520 $a Clustering is a widely used knowledge discovery technique. It helps uncovering structures in data that were not previously known. The clustering of large datasets has received a lot of attention in recent years. However, clustering is still a challenging task since many published algorithms fail to do well in (1) scaling with the size of dataset or the number of dimensions that describe the points; (2) finding arbitrary shapes of clusters; (3) dealing effectively with the presence of noise.
520 $a We propose a new clustering algorithm, based on self-similarity property of the datasets. Self-similarity is the property of being invariant with respect to the scale used to look at the dataset. While fractals are self-similar at every scale used to look at them, many datasets exhibit self-similarity over a range of scales. Self-similarity can be measured using the fractal dimension. The new algorithm which we call Fractal Clustering (FC) places points incrementally in the cluster for which the change in the factual dimension after adding the point is the least. This is a very natural way of clustering points, since points in the same cluster have a greater degree of self-similarity among them (and much less self-similarity with respect to points in other clusters). FC requires one scan of the data, is suspendable at will, providing the best answer possible at that point, and effectively deals with large datasets, high-dimensionality and noise and is capable of recognizing clusters of arbitrary shape. Also we present two applications of factual clustering: (1) projected clustering; (2) deviation detection in envolving datasets.
520 $a Projected clustering aims at very high dimensional data sets. Clusters in those datasets often only occupy some dimensions potentially of the whole space. The factual dimension of a cluster is a very good estimation of how much of the space is occupied. We combined SVD and FC to perform Projected Fractal Clustering (PFC.) on those datasets. PFC is effective and efficient shown by our experiments.
520 $a Organizations today accumulate data at an astonishing rate. Finding out when patterns change in the data opens the possibility of making better decisions and discovering new interesting facts. Measuring and tracking deviation in evolving datasets is an important and neglected area. Using statistical chernoff bounds we can detect when the structure of clusters has changed. We also present our experiment results.
590 $a School code: 0883.
650 4 $a Information Science. $3 1017528
690 $a 0723
710 2 0 $a George Mason University. $3 1019450
773 0 $t Dissertation Abstracts International $g 62-04A.
790 $a 0883
790 1 0 $a Barbara, Daniel, $e advisor
791 $a Ph.D.
792 $a 2001
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3011630