Abstract
Feature learning aims at automatic optimization of features to be used in the classification process. We consider the situation where, given a parameterized algorithm for extracting the features from the data, the optimizer tunes the parameters so that classification accuracy is maximized. The present paper extends our previous study [4] on feature learning problem by including two important mechanisms. First, an improved genetic algorithm (GA) with variable length chromosomes controls the size of the feature set. Second, the GA operates in conjuction with a neural network classifier for maximizing the identification accuracy. The performance of the feature learning algorithm is demonstrated with a problem of automatic identification of plant species from their fluorescence induction curves. The general approach should also be useful in other types of pattern recognition applications where a priori unknown characteristics are inferred from large feature spaces.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bandyopadhyay, S.: Pattern classification using genetic algorithms: Determination of H. Pattern Recognition Letters 19, 1171–1181 (1998)
Blickle, T., Thiele, L.: A comparison of selection schemes used in Evolutionary Algorithms. Evolutionary Computation 4, 361–394 (1996)
Chen, K.-Z., Zhang, X.-W., Ou, Z.-Y., Feng, X.-A.: Recognition of digital curves scanned from paper drawings using genetic algorithms. Pattern Recognition 36, 123–130 (2003)
Codrea, M.C., Aittokallio, T., Keränen, M., Tyystjärvi, E., Nevalainen, O.S.: Feature learning with a genetic algorithm for fluorescence fingerprinting of plant species. Pattern Recognition Letters 24, 2663–2673 (2003)
Dash, M., Liu, H.: Feature Selection for Classification. Intelligent Data Analysis 1, 131–156 (1997)
Fukunaga, K.: Introduction to Statistical Pattern Recognition, 2nd edn. Academic Press, San Diego (1990)
Govindjee: Sixty-three years since Kautsky: Chlorophyll a fluorescence. Australian Journal of Plant Physiology 22, 131–160 (1995)
Ho, S.-Y., Chen, Y.-C.: An efficient evolutionary algorithm for accurate polygonal approximation. Pattern Recognition 34, 2305–2317 (2001)
Keränen, M., Aro, E.-M., Tyystjärvi, E., Nevalainen, O.S.: Automatic plant identification with chlorophyll fluorescence fingerprinting. Precision Agriculture 4, 53–67 (2003)
Kohavi, R., John, G.H.: Wrappers for feature subset selection. Artificial Intelligence 97, 273–324 (1997)
Komosiński, M., Krawiec, K.: Evolutionary weighting of image features for diagnosing of CNS tumors. Artificial Intelligence in Medicine 19, 25–38 (2000)
Lazár, D.: Chlorophyll a fluorescence induction. Biochimica et Biophysica Acta 1412, 1–28 (1999)
Mao, J., Jain, A.K.: Artificial neural networks for feature extraction and multivariate data projection. IEEE Trans. Neural Networks 6, 296–317 (1995)
Maxwell, K., Johnson, G.N.: Chlorophyll fluorescence - a practical guide. Journal of Experimental Botany 51, 659–668 (2000)
Nilsson, N.J.: Artificial Intelligence: A new Synthesis. Morgan Kaufmann Publishers Inc., San Francisco (1998)
Piater, J.H., Piater, J.H., Grupen, R.A.: Feature Learning for Recognition with Bayesian Networks. In: Proceedings of International Conference on Pattern Recognition, pp. 1017–1020 (2000)
Siedlecki, W., Slansky, J.: A note on genetic algorithms for large-scale feature selection. Pattern Recognition Letters 10, 335–347 (1989)
Späth, H.: Cluster analysis algorithms for data reduction and classification of objects. Ellis Horwood Ltd., UK (1980)
Tyystjärvi, E., Koski, A., Keränen, M., Nevalainen, O.S.: The Kautsky curve is a built-in barcode. Biophysical Journal 77, 1159–1167 (1999)
Questier, F., Walczak, B., Massart, D.L., Boucon, C., de Jong, S.: Feature selection for hierarchical clustering. Analytica Chimica Acta 466, 311–324 (2002)
Yao, X.: A review of evolutionary artificial neural networks. International Journal of Intelligent Systems 8, 539–567 (1993)
Yu, S., De Backer, S., Scheunders, P.: Genetic feature selection combined with composite fuzzy nearest neighbor classifiers for hyperspectral satellite imagery. Pattern Recognition Letters 23, 183–190 (2002)
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
Codrea, M.C., Aittokallio, T., Keränen, M., Tyystjärvi, E., Nevalainen, O.S. (2004). Genetic Feature Learning Algorithm for Fluorescence Fingerprinting of Plants. In: Liardet, P., Collet, P., Fonlupt, C., Lutton, E., Schoenauer, M. (eds) Artificial Evolution. EA 2003. Lecture Notes in Computer Science, vol 2936. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24621-3_30
Download citation
DOI: https://doi.org/10.1007/978-3-540-24621-3_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21523-3
Online ISBN: 978-3-540-24621-3
eBook Packages: Springer Book Archive