Contextual neural gas for spatial clustering and analysis

• Verfasst von: Hagenauer, Julian [VerfasserIn]
• Verfasst von: Helbich, Marco [VerfasserIn]
• Titel: Contextual neural gas for spatial clustering and analysis
• Verf.angabe: Julian Hagenauer and Marco Helbich
• Jahr: 2013
• Jahr des Originals: 2012
• Umfang: 16 S.
• Fussnoten: Published online: 26 Apr 2012 ; Gesehen am 23.02.2021
• Titel Quelle: Enthalten in: International journal of geographical information science
• Ort Quelle: London : Taylor & Francis, 1987
• Jahr Quelle: 2013
• Band/Heft Quelle: 27(2013), 2, Seite 251-266
• ISSN Quelle: 1365-8824
• DOI: doi:10.1080/13658816.2012.667106
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: machine learning
• Sach-SW: self-organizing maps
• Sach-SW: spatial cluster analysis
• K10plus-PPN: 1749061740

Abstract

This study aims to introduce contextual Neural Gas (CNG), a variant of the Neural Gas algorithm, which explicitly accounts for spatial dependencies within spatial data. The main idea of the CNG is to map spatially close observations to neurons, which are close with respect to their rank distance. Thus, spatial dependency is incorporated independently from the attribute values of the data. To discuss and compare the performance of the CNG and GeoSOM, this study draws from a series of experiments, which are based on two artificial and one real-world dataset. The experimental results of the artificial datasets show that the CNG produces more homogenous clusters, a better ratio of positional accuracy, and a lower quantization error than the GeoSOM. The results of the real-world dataset illustrate that the resulting patterns of the CNG are theoretically more sound and coherent than that of the GeoSOM, which emphasizes its applicability for geographic analysis tasks.