Abstract
Recent progress in biology and medical sciences has led to an explosive growth of biomedical data. Extracting relevant knowledge from such volumes of data represents an enormous challenge and opportunity. This paper assesses several approaches to improving neural network-based biomedical pattern discovery and visualization. It focuses on unsupervised classification problems, as well as on interactive and iterative methods to display, identify and validate potential relevant patterns. Clustering and pattern visualization models were based on the adaptation of a self-adaptive neural network known as Growing Self Organizing Maps. These models provided the basis for the implementation of hierarchical clustering, cluster validity assessment and a method for monitoring learning processes (cluster formation). This framework was tested on an electrocardiogram beat data set and data consisting of DNA splice-junction sequences. The results indicate that these techniques may facilitate knowledge discovery tasks by improving key factors such as predictive effectiveness, learning efficiency and understandability of outcomes.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ideker, T., Thorsson, V., Ranish, J.A., Christmas, R., Buhler, J., Eng, J.K., Bumgarner, R., Goodlett, D.R., Aebersol, R., Hood, L.: Integrated Genomic and Proteomic Analyses of a Systematically Perturbated Metabolic Network. Science 292, 929–933 (2001)
Kohonen, T.: Self-Organizing Maps. Springer, Heidelberg (1995)
Azuaje, F.: A Computational Neural Approach to Support the Discovery of Gene Function and Classes of Cancer. IEEE Trans. on Biomedical Engineering 48(3), 332–339 (2001)
Baldi, P., Brunak, S.: Bioinformatics: The Machine Learning Approach. The MIT Press, London (2000)
Dybowski, R., Gant, V.: Clinical Applications of Artificial Neural Networks. Cambridge University Press, London (2001)
Alahakoon, D., Halgamuge, S.K., Srinivasan, B.: Dynamic Self-Oorganizing Maps with Controlled Growth for Knowledge Discovery. IEEE Transactions on Neural Networks 11(3), 601–614 (2000)
Wang, H., Azuaje, F., Black, N.: Improving Biomolecular Pattern Discovery and Visualization with Hybrid Self-Adaptive Networks. IEEE Transactions on Nanobioscience 1(4), 146–166 (2002)
Mark, R., Moody, G.: MIT-BIH Arrhythmia DataBase Directory. MIT, Cambridge (1988)
Brazdil, P., Gama, J.: DNA-Primate Splice-Junction Gene Sequences, with Associated Imperfect Domain Theory (June 2002), Available at http://porto.niaad.liacc.up.pt/niaad/statlog/datasets/dna/dna.doc.html
Bezdek, J.C., Pal, N.R.: Some New Indexes of Cluster Validity. IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics 28(3), 301–315 (1998)
Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice Hall, New Jersey (1994)
Wang, H., Azuaje, F., Black, N.: An Integrative and Interactive Framework for Improving Biomedical Pattern Discovery and Visualization. IEEE Transactions on Information Technology in Biomedicine 8(1), 16–27 (2004)
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
Wang, H., Azuaje, F., Black, N. (2004). Interactive GSOM-Based Approaches for Improving Biomedical Pattern Discovery and Visualization. In: Zhang, J., He, JH., Fu, Y. (eds) Computational and Information Science. CIS 2004. Lecture Notes in Computer Science, vol 3314. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30497-5_87
Download citation
DOI: https://doi.org/10.1007/978-3-540-30497-5_87
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-24127-0
Online ISBN: 978-3-540-30497-5
eBook Packages: Computer ScienceComputer Science (R0)