Genetic Fuzzy Rule-Based Classifiers for Land Cover Classification from Multispectral Images
This chapter presents a Boosted Genetic Fuzzy Classifier (BGFC), for land cover classification from multispectral images. The model comprises a set of fuzzy classification rules, which resemble the reasoning employed by humans. BGFC's learning algorithm is divided into two stages. During the first stage, a number of fuzzy rules are generated in an iterative fashion, incrementally covering subspaces of the feature space, as directed by a boosting algorithm. Each rule is able to select the required features, further improving the interpretability of the obtained model. The rule base generation stage is followed by a genetic tuning stage, aiming at improving the cooperation among the fuzzy rules and, subsequently, increasing the classification performance attained after the former stage. The BGFC is tested using an IKONOS multispectral VHR image, in a lake-wetland ecosystem of international importance. For effective classification, we consider advanced feature sets, containing spectral and textural feature types. The results indicate that the proposed system is able to handle multi-dimensional feature spaces, effectively exploiting information from different feature sources.
KeywordsLand Cover Fuzzy Rule Rule Base Multispectral Image Learn Vector Quantization
Unable to display preview. Download preview PDF.
- 7.N.E. Mitrakis, C.A. Topaloglou, T.K. Alexandridis, J.B. Theocharis and G.C. Zalidis, Decision fusion of GA self-organizing neuro-fuzzy multilayered classifiers for land cover classification using textural and spectral features, IEEE Trans. Geosci. Remote Sensing 46(7), 2137–2152, 2008.CrossRefGoogle Scholar
- 21.P. Thrift, Fuzzy logic synthesis with genetic algorithms, in Proc. Fourth Int. Conf. on Genetic Algorithms (ICGA′91), San Diego, USA, Morgan Kaufmann, Los Altos, CA, pp. 509–513, 1991.Google Scholar
- 22.J. Casillas, P. Martínez and A.D. Benítez, Learning consistent, complete and compact sets of fuzzy rules in conjunctive normal form for regression problems, Soft Comput., in press, 2008.Google Scholar
- 25.M. Valenzuela-Rendón, The fuzzy classifier system: A classifier system for continuously varying variables, in Proc. 4th Int. Conf. Genetic Algorithms, University of California, San Diego, July 13–16, pp. 346–353, 1991.Google Scholar
- 26.A. Parodi and P. Bonelli, A new approach to fuzzy classifier systems, in Proc. 5th Int. Conf. Genetic Algorithms, University of Illinois, Urbana-Champaign, July 17–21, pp. 223–230, 1993.Google Scholar
- 32.Y. Freund and R. Schapire, Experiments with a new boosting algorithm, in Proc. 13th Int. Conf. Machine Learning, pp. 148–156, 196.Google Scholar
- 33.C.T. Lin, Neural Fuzzy Control Systems with Structure and Parameter Learning. World Scientific, Singapore, 1994.Google Scholar
- 35.J. H. Horne, A tasseled cap transformation for IKONOS images, in Proc. ASPRS Annu. Conf., Anchorage, Alaska, 2003.Google Scholar
- 36.R.M. Haralick and L.G. Shapiro, Robot and Computer Vision, Vol. 1, Addison-Wesley, Reading, MA, 1992.Google Scholar
- 39.J.R. Quinlan, C4.5: Programs for Machine Learning, Morgan Kauffman, 1993.Google Scholar
- 41.J. Alcalá-Fdez, L. Sánchez, S. García, M.J. del Jesus, S. Ventura, J.M. Garrell, J. Otero, C. Romero, J. Bacardit, V.M. Rivas, J.C. Fernández and F. Herrera, KEEL: A software tool to assess evolutionary algorithms to data mining problems, Soft Comput. 13(3), 307–318, 2009. Software available online: http://www.keel.esCrossRefGoogle Scholar