Abstract
Document clustering is widely studied in text mining. In this paper, document clustering algorithm based on Tree-Structured Growing Self-organizing Feature Map (TGSOM) is presented as an extended version of the clustering algorithm of Self-organizing Map (SOM) in neural network, which has a dynamic tree-structure generated during the training process. TGSOM ’s growth speed can be controlled through the function of the Spread Factor (SF), and the precision of clustering results is different because of the difference value of SF. The user can get the hierarchical clustering results through changing the size of SF in different steps during clustering.
Supported by the technology development Foundation of Tianjin (No: 043600411)
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Kohonen, T.: Self-organizing Maps. Springer, Berlin (1995)
Alahakoon, D., Halgamuge, S.K.: Dynamic Self-organizing Maps with Controlled Growth for Knowledge Discovery. IEEE Trans. on Neural Networks 11, 601–614 (2000)
Choi, D., Park, S.: Self-creating and Organizing Neural Networks. IEEE Trans. on Neural Networks 5, 561–575 (1994)
Chen, K.H., Chen, H.H.: Overview of CLIR Task at the Third NTCIR Workshop. In: NTCIR Workshop 3 Meeting, pp. 1–13 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zheng, X., Liu, W., He, P., Dai, W. (2004). Document Clustering Algorithm Based on Tree-Structured Growing Self-Organizing Feature Map. In: Yin, FL., Wang, J., Guo, C. (eds) Advances in Neural Networks – ISNN 2004. ISNN 2004. Lecture Notes in Computer Science, vol 3173. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28647-9_138
Download citation
DOI: https://doi.org/10.1007/978-3-540-28647-9_138
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22841-7
Online ISBN: 978-3-540-28647-9
eBook Packages: Springer Book Archive