FAST K-MEANS-LIKE CLUSTERING IN METRIC-SPACES

被引：10
作者：
JUAN, A
VIDAL, E
机构：
[1] Departamento de Sistemas Informáticos y Computación, Universidad Politécnica de Valencia, Valencia
来源：
PATTERN RECOGNITION LETTERS | 1994年 / 15卷 / 01期
关键词：
CLUSTERING; K-MEANS-LIKE ALGORITHMS; METRIC; FAST NEAREST-NEIGHBOR SEARCHING; AESA;
D O I：
10.1016/0167-8655(94)90096-5
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A fast K-means-like algorithm is proposed for the case in which data cannot be adequately represented in a suitable vector space, though a metric is available to measure the dissimilarity between data points. Experimental results comparing the proposed algorithm with a direct K-means-like method show a substantial reduction of the cost in terms of distance computations required.
引用
收藏
页码：19 / 25
页数：7
相关论文
共 17 条
  • [1] AIBAR P, 1991, NATO ASI F, V75, P519
  • [2] [Anonymous], 1988, ALGORITHMS CLUSTERIN
  • [3] JUAN A, 1991, APLICACION TECNICAS
  • [4] JUAN A, 1992, 4TH P PORT C PATT RE, P11
  • [5] KITLER J, 1988, PATTERN RECOGN, V21, P169
  • [6] A NEW VERSION OF THE NEAREST-NEIGHBOR APPROXIMATING AND ELIMINATING SEARCH ALGORITHM (AESA) WITH LINEAR PREPROCESSING TIME AND MEMORY REQUIREMENTS
    MICO, ML
    ONCINA, J
    VIDAL, E
    [J]. PATTERN RECOGNITION LETTERS, 1994, 15 (01) : 9 - 17
  • [7] MICO ML, 1992, 11TH P ICPR HAG, V2, P557
  • [8] ORCHARD MD, 1991, P ICASSP INT C AC SP, V4, P2297
  • [9] SPEAKER-INDEPENDENT RECOGNITION OF ISOLATED WORDS USING CLUSTERING TECHNIQUES
    RABINER, LR
    LEVINSON, SE
    ROSENBERG, AE
    WILPON, JG
    [J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1979, 27 (04): : 336 - 349
  • [10] DYNAMIC-PROGRAMMING ALGORITHM OPTIMIZATION FOR SPOKEN WORD RECOGNITION
    SAKOE, H
    CHIBA, S
    [J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1978, 26 (01): : 43 - 49
12