Abstract
The paper proposes a hybrid feature selection approach based on Rough sets and Bayesian network classifiers. In the approach, the classification result of a Bayesian network is used as the criterion for the optimal feature subset selection. The Bayesian network classifier used in the paper is a kind of naive Bayesian classifier. It is employed to implement classification by learning the samples consisting of a set of texture features. In order to simplify feature reduction using Rough Sets, a discrete method based on C-means clustering method is also presented. The proposed approach is applied to extract residential areas from panchromatic SPOT5 images. Experiment results show that the proposed method not only improves classification quality but also reduces computational cost.
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
Swiniarski, R.W.: Rough sets as a front end of neural networks texture classifiers. Neurocomputing 85–102 (2001)
Swiniarski, R.W., Skowron, A.: Rough set methods in feature selection and recognition. Pattern Recognition Letters 24, 833–849 (2003)
Yang, J., Honavar, V.: Feature subset selection using a genetic algorithm. Journal of Intelligent Information Systems 16, 215–228 (2001)
Pan, L., Nahavanid, S., Zheng, H.: The Rough set feature selection for tree recognition in color image using genetic algorithm. In: Proceedings of the 2nd International Conference on Computational Intelligence, Robotics and Autonomous Systems, pp. 15–18 (2003)
Vafaie, H., Jong, K.D.: Robust feature selection algorithms. In: Proceedings of International Conference on Tools with AI, Boston, Massachusetts, pp. 356–363 (2001)
Zheng, H., Zhang, J.X., Nahavandi, S.: Learning detect to texture objects by artificial immune approaches. Future Generation Computer Systems 20, 1197–1208 (2002)
Huang, Y., Luck, K., Zhang, C.: Texture classification by multi-model feature integration using Bayesian networks. Pattern Recognition Letters 24, 393–401 (2003)
Aksoy, S., Koperski, K.: Learning Bayesian classifiers for scene classification with a visual grammar. IEEE Trans. Geosci. Remote. Sens. 43, 581–589 (2005)
Paola, J.D., Schowengerdt, R.A.: The effect of neural network structure on a multi-spectral use/land-cover classification. Photogrammetry Engineering and Remote Sensing 63, 535–544 (1997)
Mitra, S.K., Lee, T.W., Goldbaum, M.: A Bayesian network based sequential inference for diagnosis of diseases from retinal images. Pattern Recognition Letters 26, 459–470 (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pan, L., Zheng, H., Li, L. (2008). A Hybrid Feature Selection Approach Based on the Bayesian Network Classifier and Rough Sets. In: Wang, G., Li, T., Grzymala-Busse, J.W., Miao, D., Skowron, A., Yao, Y. (eds) Rough Sets and Knowledge Technology. RSKT 2008. Lecture Notes in Computer Science(), vol 5009. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-79721-0_94
Download citation
DOI: https://doi.org/10.1007/978-3-540-79721-0_94
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-79720-3
Online ISBN: 978-3-540-79721-0
eBook Packages: Computer ScienceComputer Science (R0)