New methods for the initialisation of clusters

被引：46

作者：

AlDaoud, MB ^{[1
]}

Roberts, SA ^{[1
]}

机构：

[1] UNIV LEEDS, SCH COMP STUDIES, LEEDS LS2 9JT, W YORKSHIRE, ENGLAND

来源：

PATTERN RECOGNITION LETTERS | 1996年 / 17卷 / 05期

关键词：

clustering; cluster initialisation; k-means algorithm;

D O I：

10.1016/0167-8655(95)00119-0

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

One of the most widely used clustering techniques is the k-means algorithm. Solutions obtained from this technique are dependent on the initialisation of cluster centres. In this article, two initialisation methods are developed. These methods are particularly suited to problems involving very large data sets. The methods have been applied to different data sets and good results are obtained.

引用

页码：451 / 455

页数：5

共 14 条

[1] A NEAR-OPTIMAL INITIAL SEED VALUE SELECTION IN K-MEANS ALGORITHM USING A GENETIC ALGORITHM
BABU, GP
MURTY, MN
[J]. PATTERN RECOGNITION LETTERS, 1993, 14 (10) : 763 - 769
[2] SPEECH CODING BASED UPON VECTOR QUANTIZATION
BUZO, A
GRAY, AH
GRAY, RM
MARKEL, JD
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1980, 28 (05): : 562 - 574
[3] Chatfield C., 1980, INTRO MULTIVARIATE A
[4] Gersho A., 1992, Vector quantization and signal compression
[5] A comparison of several vector quantization codebook generation approaches
Huang, C. -M.
Harris, R. W.
[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 1993, 2 (01) : 108 - 112
[6] MULTIDIMENSIONAL DATA CLUSTERING UTILIZING HYBRID SEARCH STRATEGIES
ISMAIL, MA
KAMEL, MS
[J]. PATTERN RECOGNITION, 1989, 22 (01) : 75 - 89
[7] A New Initialization Technique for Generalized Lloyd Iteration
Katsavounidis, Ioannis
Kuo, C. -C. Jay
Zhang, Zhen
[J]. IEEE SIGNAL PROCESSING LETTERS, 1994, 1 (10) : 144 - 146
[8] Kaufman L, 1990, FINDING GROUPS DATA
[9] ALGORITHM FOR VECTOR QUANTIZER DESIGN
LINDE, Y
BUZO, A
GRAY, RM
[J]. IEEE TRANSACTIONS ON COMMUNICATIONS, 1980, 28 (01) : 84 - 95
[10] MacQueen J.B., 1967, P 5 BERKELEY S MATH, V1, P281

← 1 2 →