Abstract
Automatic classification of electron-microscopy images is an important step in the complex task of determination of the structure of biologial macromolecules. The process of 3D reconstruction from the images implies its previous classification in different classes corresponding to the main different views. In this paper a neural network classification algorithm has been used to perform the classification of electron microscopy samples in two classes. Using two labeled sets as a refference, the parameters and architecture of the classifier were optimized using a genetic algorithm. The global automatic process of training and optimization is implemented using the previously described g-lvq algorithm, and compared to a non-optimized version of the algorithm, Kohonen's LVQ. Using a part of the sample as training set, the results presented here show an efficient (90%) classification of unknown samples in two classes. The implication of this kind of automatic classification algorithms in determination of three dimensional structure of biological particles is finaly discused.
Preview
Unable to display preview. Download preview PDF.
References
San Martin C., Gruss C., and Carazo J.M. Six molecules of sv40 large T antigen assemble in a propeller-shaped particle around a channel. Journal of Molecular biology, page in press, 1997.
Jose-Jesus Fernández and Jose-Maria Carazo. Analysis of structural variability within two-dimensional biological crystals by a combination of patch averaging techniques and self-organizing maps. Ultramicroscopy, 65:81–93, 1996.
R. Marabini and J.M. Carazo. Pattern recognition and classification of images of biological macromolecules using artificial neural networks. Biophysics Journal 66:1804–1814, 1994.
J. J. Merelo and A. Prieto. g-lvq, a combination of genetic algorithms and lvq. In N.C.Steele D.W.Pearson and R.F.Albrecht, editors, Artificial neural Nets and Genetic Algorithms, pages 92–95. Springer-Verlag, 1995.
T. Kohonen. The self-organizing map. Procs. IEEE, 78:1464 ff., 1990.
W. Schiffman, M. Joost, and R. Werner. Optimization of the backpropagation algorithm for training multilayer perceptrons. Technical report, University of Koblenz, Institute of Physics, 1994.
F. Murtagh and M. Hernández Pajares. The kohonen self-organizing map method: An assesment. Technical report, European Space Agency/UPC, 1993.
R. Huang. Systems control with the genetic algorithm and the nearest neighbour classification. CC-AI, 9(2–3):225–236, 1992.
Jr. James D. Kelly and Lawrence Davis. Hybridizing the genetic aglorithm and the k nearest neighbors classification algorithms. In Richard K. Belew and Lashon B. Booker, editors, ICGA91, San Mateo, CA, 1991. Morgan Kaufmann.
Ethem Alpaydim. GAL: Networks that grow when they learn and shrink when they forget. Technical Report TR-91-032, International Computer Science Institute, May 1991.
Enrique Monte, D. Hidalgo, J. Mariño, and I. Hernáez. A vector quantization algorithm based on genetic algorithms and Lvq. In NATO-ASI Bubión, page 231 ff., 1993.
Juan Carlos Pérez and Enrique Vida. Constructive design of LVQ and dsm classifiers. In J. Mira, J. Cabestany, and A. Prieto, editors, New Trends in Neural Computation, pages 334–339, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Merelo, J.J., Prieto, A., Morán, F., Marabini, R., Carazo, J.M. (1997). A GA-optimized neural network for classification of biological particles from electron-microscopy images. In: Mira, J., Moreno-Díaz, R., Cabestany, J. (eds) Biological and Artificial Computation: From Neuroscience to Technology. IWANN 1997. Lecture Notes in Computer Science, vol 1240. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0032577
Download citation
DOI: https://doi.org/10.1007/BFb0032577
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63047-0
Online ISBN: 978-3-540-69074-0
eBook Packages: Springer Book Archive