The self-organizing map, the Geo-SOM, and relevant variants for geosciences

被引：76

作者：

Baçao, F

Lobo, V

Painho, M

机构：

[1] Univ Nova Lisboa, Inst Super Estatist & Gestao Informacao, P-1200 Lisbon, Portugal

[2] Portuguese Naval Acad, Almada, Portugal

来源：

COMPUTERS & GEOSCIENCES | 2005年 / 31卷 / 02期

关键词：

Self-Organizing Map; geo-SOM; SOM variants; geo-referenced data;

D O I：

10.1016/j.cageo.2004.06.013

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In this paper we explore the advantages of using Self-Organized Maps (SOMs) when dealing with geo-referenced data. The standard SOM algorithm is presented, together with variants which are relevant in the context of the analysis of geo-referenced data. We present a new SOM architecture, the Geo-SOM, which was especially designed to take into account spatial dependency. The strengths and weaknesses of the different variants proposed are shown through a set of tests based on artificial data. A real world application of these techniques is given through the analysis of geodemographic data from Lisbon's metropolitan area. (C) 2004 Elsevier Ltd. All rights reserved.

引用

页码：155 / 163

页数：9

共 24 条

[1]

[Anonymous], 1997, Data exploration using self-organizing maps, DOI DOI 10.1111/fwb.12264

[2]

BEHME H, 1993, P INT C ART NEUR NET, P416

[3]

Fu L, 1994, NEURAL NETWORKS COMP

[4]

Gahegan M, 2003, INT J GEOGR INF SCI, V17, P69, DOI 10.1080/13658810210157778

[5]

Ichiki H., 1991, IJCNN-91-Seattle: International Joint Conference on Neural Networks (Cat. No.91CH3049-4), P357, DOI 10.1109/IJCNN.1991.155203

[6]

JIANG X, 1994, WORLD C NEUR NETW WC, P595

[7]

KANGAS J, 1992, ARTIFICIAL NEURAL NE, V2, P117

[8]

Kangas J A, 1990, IEEE Trans Neural Netw, V1, P93, DOI 10.1109/72.80208

[9]

KEMKE C, 1993, P WORLD C NEUR NETW, V3, P45

[10]

KOHONEN T, 1991, ARTIFICIAL NEURAL NETWORKS, VOLS 1 AND 2, P1357

← 1 2 3 →