Open Access Open Access  Restricted Access Subscription Access

System Identification using Modular Network SOM (mnSOM)

Muhammad Aziz Muslim, Goegoes Dwi Nusantoro

Abstract


In this paper, we proposed a new identification method for changing parameter system based on modular network SOM (mnSOM). mnSOM is a generalization of Self Organizing Maps (SOM) formed by replacing each vector unit of SOM with function module. The modular function could be a multi layer perceptron, a recurrent neural network or even SOM itself. For system identification purpose, we employed ARX modules with recursive least square (RLS) learning. Inherit SOM capability of interpolating among function modules and well-known powerful capability of least square methods for system identification our RLS-mnSOM provides promising results for
identification of changing parameter systems.

Full Text:

PDF

References


T. Kohonen, “Self-Organizing Maps,” Springer, 1995

Landau, Ioan dan Gianluca Zito,”Digital Control Systems Design, Identification and Implementation,” Germany: Springer-Verlag London Limited, 2006

K. Tokunaga, T. Furukawa, and S. Yasui, ''Modular Network SOM: Extension of SOM to the realm of function space," Proc. of Workshop on Self Organizing Maps (WSOM2003)}, pp. 173-178, 2003.

T. Furukawa, K. Tokunaga, S. Kaneko, K. Kimotsuki, and S. Yasui, ''Generalized self-organizing maps (mnSOM) for dealing with dynamical systems," Proc. of 2004 International Symposium on Nonlinear Theory and Its Application (NOLTA2004), Fukuoka, Japan, pp. 231-234, 2004.

M. Aziz Muslim, M. Ishikawa, and T. Furukawa, ''A New Approach to Task Segmentation in Mobile Robots by mnSOM," Proc. of 2006 IEEE World Congress on Computational Intelligence (IJCNN2006 Section), pp. 6542-6549, Vancouver, Canada, 2006.

M. Aziz Muslim, M. Ishikawa, and T. Furukawa, ''Task Segmentation in a Mobile Robot by mnSOM : A New Approach To Training Expert Modules," Neural Computing and Application, vol. 16, pp. 571-580, Springer, 2007.

M. Aziz Muslim, M. Ishikawa, and T. Furukawa, ”Task Segmentation in a Mobile Robot by mnSOM and Hierarchical Clustering,” International Workshop on Self-Organizing Maps (WSOM) 2007, Bielefeld, Germany, 2007

M. Aziz Muslim, Masumi Ishikawa, Tetsuo Furukawa, “Task Segmentation in a Mobile Robot by mnSOM and Clustering with Spatio-temporal Contiguity”, International Journal of Innovative Computing, Information & Control, vol. 5 No.4, pp. 865-875, April 2009

M. Aziz Muslim, Masumi Ishikawa, “Formation of Graph-based Maps for Mobile Robots using Hidden Markov Models”, Proc. of 2008 IEEE World Congress on Computational Intelligence (IJCNN2008 Section), Hongkong, 2008.

S. Nishida, K. Ishii, and T. Furukawa, “An Online Adaptation Control System Using mnSOM”, Lecture Notes in Computer Science(Edited book of 13th International Conference of Neural Information Processing (ICONIP2006)), Vol.4232, pp.935-942, 2006




DOI: http://dx.doi.org/10.21535%2FProICIUS.2010.v6.503

Refbacks

  • There are currently no refbacks.