An improved Agglomerative levels K-means clustering algorithm

被引：1

作者：

Yu Jiankun ^{[1
]}

Guo Jun ^{[1
]}

机构：

[1] Yunnan Univ Finance & Econ, Sch Informat, Kunming, Peoples R China

来源：

2014 INTERNATIONAL CONFERENCE ON MANAGEMENT OF E-COMMERCE AND E-GOVERNMENT (ICMECG) | 2014年

关键词：

K-means; Agglomerative hierarchical clustering; initial cancroids; termination condition;

D O I：

10.1109/ICMeCG.2014.53

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The paper proposed a method which combines an improved hierarchical aggregation and K-means clustering algorithm, overcoming the selection problem of initial cluster centers and selection problem of termination condition. Application this method to cluster sina weibo topic and compare with tradition hierarchical aggregation and K-means clustering algorithm, finding the method can reduce false positives and missed rate.

引用

页码：221 / 224

页数：4

共 12 条

[1] THE IDENTIFICATION OF MULTIPLE OUTLIERS [J].

DAVIES, L ;

GATHER, U .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1993, 88 (423) :782-792

[2]

[洪宇 HONG Yu], 2007, [中文信息学报, Journal of Chinese Information Processing], V21, P71

[3]

Huang T., 2011, J COMPUTER TECHNIQUE, V21, P54

[4]

Jain A. K., 1988, Algorithms for Clustering Data

[5]

Knorr E.M., 1999, VLDB, P211

[6]

Luo H.W, 2003, NAT JOINT C COMP LIN, P560

[7]

Lv TY, 2005, LECT NOTES COMPUT SC, V3739, P464

[8]

Ma X., 2008, COMPUTER SCI, V34, P34

[9] Efficient algorithms for mining outliers from large data sets [J].

Ramaswamy, S ;

Rastogi, R ;

Shim, K .

SIGMOD RECORD, 2000, 29 (02) :427-438

[10]

Su T, 2004, PROC INT C TOOLS ART, P784

← 1 2 →