Abstract
This paper addresses the problem of GA-based attribute selection. Previous work in this direction has mainly focused on problem representation so that a genetic algorithm could work on it searching for a satisfactory attribute subset. Even though good experimental results were reported, they were usually acquired at the cost of time. This paper presents a novel approach to this problem. In particular, it introduces attribute quality measure during genetic evolution in order to make some promising attributes more likely to appear in a new generation. In this way, the evolution process is faster, and satisfactory results can be achieved in less time. Preliminary experimental results in image interpretation show that this approach is promising.
Preview
Unable to display preview. Download preview PDF.
References
Baim, P.W., 1982. The PROMISE Method for Selecting Most Relevant Attributes for Inductive Learning Systems. Reports of the Intelligent Systems Group, Department of Computer Science, University of Illinois at Urbana-Champaign, ISG 82–5.
Bala, J., Huang, J., Vafaie, H., DeJong, K. and Wechsler, H, 1995. Hybrid Learning Using Genetic Algorithms and Decision Trees for Pattern Classification. Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, August, Motreal, Quebec, Canada.
De Jong, K., 1996. Evolutionary Computation: Theory and Practice. MIT Press.
Forsburg, S., 1976. AQPLUS: An adaptive random search method for selecting a best set of attribute from a large collection of candidates. Internal Report, Department of Computer Science, University of Illinois, Urbana, Illinois.
Imam, I.F., and Vafaie, H., 1994. An Empirical Comparison Between Global and Greedy-like Search for Attribute selection. Proceedings of the Seventh Florida Artificial Intelligence Research Symposium, May, Pensacola Beach, FL., pp. 66–70.
John, G., Kohavi, R., and Pfleger, K., 1994. Irrelevant Features and the Subset Selection Problem. Proceedings of the Eleventh International Conference on Machine Learning, July, Rutgers University in New Brunswick, New Jersey, pp. 121–129.
Koller, D., and Sahami, M., 1996. Toward Optimal Feature Selection. Proceedings of the Thirteenth International Conference on Machine Learning, July, Bari, Italy, pp. 284–292.
Kreithen, D.E., Halversen, S.D. and Owirka, F.J., 1993. Discriminating Targets from Clutter. Journal of MIT Lincoln Lab., pp. 25–52.
Laws, K., 1980. Textured Image Segmentation. Ph.D. Thesis, University of Southern California, Department of Electrical Engineering.
Michalski, R.S., Mozetic, I., Hong, J., and Lavrac, N., 1986. The Multipurpose Incremental Learning System AQ15 and its Testing Application to Three Medical Domains. Proceedings of the Fifth National Conference on Artificial Intelligence, August, Philadelphia, PA., pp. 1041–1045.
Michalski, R.S., Zhang, Q., Maloof, M.A., and Bloedorn, E., 1996. The MIST Methodology and Its Application to Natural Scene Interpretation. Proceedings of Image Understanding Workshop, Palms Spring, CA., pp. 1473–1479.
Vafaie, H. and De Jong, K., 1993. Robust Feature Selection Algorithms. Proceedings of the International Conference on Tools with AI, Boston, MA., pp. 356–364.
Weiss, S.M., & Kulikowski, C.A., 1992. Computer systems that learn: classification and prediction methods from statistics, neural nets, machine learning and expert systems, Morgan Kaufmann, San Mateo, CA.
Wnek, J., Kaufman, K., Bloedom, E., and Michalski, R.S., 1995. Selective Induction and Learning System AQ15c: the Method and User's Guide. Reports of the Machine Learning and Inference Lab., MLI 95-4, Machine Learning and Inference Lab., George Mason University, Fairfax, VA.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, Q. (1997). Speeding GA-based attribute selection for image interpretation. In: RaÅ›, Z.W., Skowron, A. (eds) Foundations of Intelligent Systems. ISMIS 1997. Lecture Notes in Computer Science, vol 1325. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63614-5_23
Download citation
DOI: https://doi.org/10.1007/3-540-63614-5_23
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63614-4
Online ISBN: 978-3-540-69612-4
eBook Packages: Springer Book Archive