Definition
One of the unsupervised clustering techniques that is widely used for data dimensionality reduction with topological preservation is Kohonen’s self-organizing map (SOM). It is a subtype of artificial neural networks. Therefore, SOM is used for visualizing low-dimensional views of high-dimensional data such as classification or grouping. SOM networks are based on competitive learning, i.e., the “winner takes all” approach (Haykin 1999). In this process, the individuality of the data is rarely lost; rather it is preserved within the winning output neurons of the clusters. It is based on human brain and sensory input (Haykin 1999; Pandya and Macy 1996). This characteristical approach of the system (SOM) makes it superior or at best competitive to other unsupervised classification techniques used in image classification, data reduction, or clustering mechanism.
Historical Background
Unlike most...
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bhandarkar SM, Koh J, Suk M (1997) Multi scale image segmentation using a hierarchical self-organizing map. Neurocomputing 14:241–272
Everly B (2002) Personal communication. Product support, help@neuralware.com. Contacted 18 Mar 2002
Haykin S (1999) Neural networks: a comprehensive foundation. Prentice Hall Inc, Upper Saddle River
Honkela T (1997) Self-organizing map in natural language processing. http://citeseer.ist.psu.edu/123560.html. Accessed 30 Dec 2006
Hubel D, Wiesel T (1962) Receptive fields, binocular interaction & functional architecture in the cat’s visual cortex. J Physiol (London) 160:106–154
Kangas J, Kohonen T (1996) Development and applications of self-organizing map and related algorithms. Math Comput Simul 41:3–12
Kass M, Witkin A, Terzopoulos D (1987) Snakes: active contour models. Int J Comput Vis 1(4):321–331
Kohonen T (1990) The self-organizing map. IEEE 78:1464–1480
Kohonen T (1995) Self-organizing maps. Springer-Verlag, New York
Kohonen T (2001) SOM-tool box home. http://www.cis.hut.fi/projects/somtoolbox/. Cited 4 Feb 2001
Lawrence S, Giles CL, Tsoi AC, Back AD (1997) Face recognition: a convolutional neural network approach. IEEE Trans Neural Netw 8(1):1–27
Panda S (2003) Data mining application in production management of crop. Dissertation, North Dakota State University
Pandya AS, Macy RB (1996) Pattern recognition with neural networks in C++. CRC Press, Boca Raton
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this entry
Cite this entry
Panda, S. (2017). Self-Organizing Map (SOM) Usage in LULC Classification. In: Shekhar, S., Xiong, H., Zhou, X. (eds) Encyclopedia of GIS. Springer, Cham. https://doi.org/10.1007/978-3-319-17885-1_1181
Download citation
DOI: https://doi.org/10.1007/978-3-319-17885-1_1181
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-17884-4
Online ISBN: 978-3-319-17885-1
eBook Packages: Computer ScienceReference Module Computer Science and Engineering