Abstract
The utilisation of clustering algorithms based on the optimisation of prototypes in neural networks is demonstrated for unsupervised learning. Stimulated by common clustering methods of this type (learning vector quantisation [LVQ, GLVQ] and K-means) a globally operating algorithm was developed to cope with known shortcomings of existing tools. This algorithm and K-means (for the common methods) were applied to the problem of clustering EEG patterns being pre-processed. It can be shown that the algorithm based on global random optimisation may find an optimal solution repeatedly, whereas K-means provides different sub-optimal solutions with respect to the quality measure defined as objective function. The results are presented. The performance of the algorithms is discussed.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Kohonen T. Self-Organization and Associative Memory. 3rd edn. Springer, Berlin Heidelberg, 1984
Pal NR, Bezdek JC, Tsao ECK. Generalized clustering networks and Kohonen's self-organizing scheme. IEEE Transactions on Neural Networks 1993; 4(4) July
Matyas J. Random optimization method. Automation and Remote Control 1965; 26: 246–253
Solis FJ, Wets JB. Minimization by random search techniques. Mathematics of Operations Research 1981; 6: 19–30
SPSS Inc. Statistical package. Professional Statistics Release 6.0, 1993
Anderberg MR. Cluster Analysis for Applications. Academic Press, New York, 1973
Dillon WR, Goldstein M. Multivariate Analysis. Methods and Applications. John Wiley & Sons, Inc. New York, 1984
Polak E, Mayne DQ, Wardi Y. On the extension of constrained optimization algorithms from differentiable to nondifferentiable problems. SIAM J Contr Optimiz 1983; 21: 179–203
Polak E, Mayne DQ. Algorithm models for nondifferentiable optimization. Proc. IEEE Cont. Decision and Control 1983; IX: 934–939
Baba N et al. A modified convergence theorem for a random optimisation method. Information Sciences 1977; 17: 159–166
Baba N et al. A hybrid algorithm for finding the global minimum of error function of neural networks and its applications. Neural Networks 1994; 7(8): 1253–1265
černy V. Thermodynamical approach to the travelling salesman problem: an efficient simulation algorithm. JOTA 1985; 45: 41–51
German S, Hwang C. Diffusion for global optimization. SIAM Journal of Control and Optimization 1986; 24: 1031–1043
Styblinski MA, Tang TS. Experiments in nonconvex optimization: stochastic approximation with function smoothing and simulated annealing. Neural Networks 1990; 3(4): 467–483
Tang Z, Koehler GJ. Deterministic global optimal FNN training algorithms. Neural Networks 1994; 7(2): 301–311
Baba N. A new approach for finding the global minimum of error function of neural networks. Neural Networks 1989; 2(2): 367–373
Kaufman L, Rousseeuw PJ. Finding Groups in Data: An introduction to cluster analysis. John Wiley & Sons, New York, 1990
Krajča V, Petránek S, Patáková I, VÄrri A. Automatic identification of significant graphoelements in multichannel EEG-recordings by adaptive segmentation and fuzzy clustering. Int J Biomed Comput 1991; 28: 71–89
Bodenstein G, Schneider W, Malsburg Cvd. Computerized EEG pattern classification by adaptive segmentation and probability-density-function classification. Description of the method. Comput Biol Med 1985; 15(5): 297–313
VÄrri A. Digital processing of EEG in epilepsy. Licentiate Thesis. Tampere University of Technology, Tampere, Finland, 1988
Krajča V, Petránek S, PietilÄ T, Frey H. ‘Wave-Finder’: A new system for an automatic processing of long-term EEG-recordings. In: Rother M, Zweiner U (eds), Quantitative EEG analysis — clinical utility and new methods, UniversitÄtsverlag Jena, 1993
Duda R, Hart P. Pattern Classification and Scene Analysis. John Wiley & Sons, New York 1973
Jain A, Dubes R. Algorithms that Cluster Data. Englewood Cliffs, Prentice Hall, New Jersey
Kruse H. Programmierung Neuronaler Netze. Addison-Wesley, Bonn, München, 1991
Abramowitz M, Steugen I. Handbook of Mathematical Functions with Formulas, Graphs and Mathematical tables, 7th printing. US Govt. Printing Office, Washington, DC
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Galicki, M., Möller, U. & Witte, H. Neural clustering networks based on global optimisation of prototypes in metric spaces. Neural Comput & Applic 5, 2–13 (1997). https://doi.org/10.1007/BF01414098
Issue Date:
DOI: https://doi.org/10.1007/BF01414098