Abstract
This paper introduces an algorithm for the multi-sensory integration of signals from the fluorescence microscopy. For the cluster analysis a Self-Organizing Feature Map (SOFM) is used. One basic property of these artificial neural nets is the smoothing of the input vectors and thus a certain insensitivity to clusters of low feature density. While classifying clusters of highly different feature density this property is undesirable. A modification of the learning algorithm of the SOFM, which makes a reproduction of low feature density clusters on a SOFM possible, is described.
This work was supported by the DFG/BMBF grant (Innovationskolleg 15/A1).
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Schubert, W.: Lymphocyte antigen Leu 19 as a molecular marker of regeneration in human skeletal muscle, Proc. Natl. Acad. Sc USA 86, pp. 307–311, 1989
Obermayr, K.; et.al.: Statistical-Mechanical Analysis of Self-Organization and Pattern Formation During the Development of Visual Maps, Physical Review A, Vol. 45 (10), pp. 7568–7589, 1992
Rethfeldt, Ch.; et.al.: Multi-Dimensional Cluster Analysis of Higher-Level Differentiation at Cell-Surfaces, Proc. 1. Kongress der Neurowissenschaftlichen Gesellschaft, p. 170, Spektrum Akademischer Verlag, Berlin 1996
Kohonen, T.: Self-Organizing Maps, Springer Series in Information Sciences, Springer, New York 1995
McInerney, M.; Dhawan, A.: Training the Self-Organizing Feature Map using Hybrids of Genetic and Kohonen methods, Proc. The 1994 IEEE Int. Conf. on Neural Networks, pp. 641–644, Orlando 1994
Bertsch, H.; et.al.: Das selbstlernende System der topologischen Merkmalskarte zur Klassifikation und Bildsegmentierung, Proc. 10. Symposium Deutsche Arbeitsgemeinschaft für Mustererkennung, pp. 298–303, Zurich 1988
Schünemann, St.; Michaelis, B.: A Self-Organizing Map for Analysis of High-Dimensional Feature Spaces with Clusters of Highly Differing Feature Density, Proc. 4th European Symposium on Artificial Neural Networks, pp. 79–84, Bruges 1996
Sklansky, J.: On the Hough Technique for Curve Detection, IEEE Trans. on Comp. 27 (10), pp. 923–926, 1978
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schünemann, S., Michaelis, B., Schubert, W. (1996). Analysis of multi-fluorescence signals using a modified Self-Organizing Feature Map. In: von der Malsburg, C., von Seelen, W., Vorbrüggen, J.C., Sendhoff, B. (eds) Artificial Neural Networks — ICANN 96. ICANN 1996. Lecture Notes in Computer Science, vol 1112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61510-5_98
Download citation
DOI: https://doi.org/10.1007/3-540-61510-5_98
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61510-1
Online ISBN: 978-3-540-68684-2
eBook Packages: Springer Book Archive