MULTIDIMENSIONAL SELECTION MODEL FOR CLASSIFICATION

Dymitr Ruta

Abstract

Recent research efforts dedicated to classifier fusion have made it clear that combining performance strongly depends on careful selection of classifiers. Classifier performance depends, in turn, on careful selection of features, which on top of that could be applied to different subsets of the data. On the other hand, there is already a number of classifier fusion techniques available and the choice of the most suitable method relates back to the selection in the classifier, feature and data spaces. Despite this apparent selection multidimensionality, typical classification systems either ignore the selection altogether or perform selection along only single dimension, usually choosing the optimal subset of classifiers. The presented multidimensional selection sketches the general framework for the optimised selection carried out simultaneously on many dimensions of the classification model. The selection process is controlled by the specifically designed genetic algorithm, guided directly by the final recognition rate of the composite classifier. The prototype of the 3-dimensional fusion-classifier-feature selection model is developed and tested on some typical benchmark datasets.

References

  1. Cho, S.-B. (1999). Pattern recognition with neural networks combined by genetic algorithms. Fuzzy Sets and Systems, 103:339-347.
  2. Davis, L. (1991). Handbook of Genetic Algorithms. Van Nostrand Reinhold, New York.
  3. Dietterich, T. and Bakiri, G. (1995). Solving multiclass learning problems via error-correcting output codes. Journal of Artificial Intelligence Research, 2:263- 286.
  4. Giacinto, G. and Roli, F. (1999). Methods for dynamic classifier selection. In Proc. of the 10th Int. Conf. on Image Analysis and Processing, pages 659-664, Venice.
  5. H. Ishibuchi, T. N. and Nii, M. (2001). Instance selection and construction for Data Mining, chapter Genetic-Algorithm-Based Instance and Feature Selection, pages 95-112. Kluwer Academic Publishers.
  6. Holland, J. (1975). Adaptation in natural and artificial systems. The University of Michigan Press, Michigan.
  7. Kuncheva, L. (2004). Combining pattern classifiers. Methods and algorithms. Wiley-Interscience, New York.
  8. Kuncheva, L. and Jain, L. (1999). Nearest neighbor classifier: Simultaneous editing and feature selection. Pattern Recognition Letters, 20(4):1149-1156.
  9. Kuncheva, L. and Jain, L. (2000). Designing classifier fusion systems by genetic algorithms. IEEE Ttansactions on Evolutionary Computation, 4(4):327-336.
  10. Kuncheva, L. and Whitaker, C. (2001). Feature subsets for classifier combination: an enumerative experiment. In Proc. of the 2nd Int. Workshop on Multiple Classifier Systems, pages 228-237, Cambridge, UK.
  11. Roli, F. and Giacinto, G. (2002). Hybrid Methods in Pattern Recognition, chapter Design of multiple classifier systems, pages 199-226. World Scientific Publishing.
  12. Ruta, D. and Gabrys, B. (2001). Application of the evolutionary algorithms for classifier selection in multiple classifier systems with majority voting. In Proc. of the 2nd Int. Workshop on Multiple Classifier Systems, pages 399-408, Cambridge, UK. Springer Verlag.
  13. Ruta, D. and Gabrys, B. (2005). Classifier selection for majority voting. Information Fusion, 6:63-81.
  14. Zenobi, G. and Cunningham, P. (2001). Using diversity in preparing ensembles of classifiers based on different feature subsets to minimise generalisation error. In Proceedings of the 12th European Conference on Machine Learning, pages 576-587.
Download


Paper Citation


in Harvard Style

Ruta D. (2005). MULTIDIMENSIONAL SELECTION MODEL FOR CLASSIFICATION . In Proceedings of the Seventh International Conference on Enterprise Information Systems - Volume 2: ICEIS, ISBN 972-8865-19-8, pages 226-232. DOI: 10.5220/0002547902260232


in Bibtex Style

@conference{iceis05,
author={Dymitr Ruta},
title={MULTIDIMENSIONAL SELECTION MODEL FOR CLASSIFICATION},
booktitle={Proceedings of the Seventh International Conference on Enterprise Information Systems - Volume 2: ICEIS,},
year={2005},
pages={226-232},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002547902260232},
isbn={972-8865-19-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Seventh International Conference on Enterprise Information Systems - Volume 2: ICEIS,
TI - MULTIDIMENSIONAL SELECTION MODEL FOR CLASSIFICATION
SN - 972-8865-19-8
AU - Ruta D.
PY - 2005
SP - 226
EP - 232
DO - 10.5220/0002547902260232