Genetic BDD-oriented Pattern Classifiers
In this study, we introduce a BDD — based pattern classifier. The essence of the proposed approach lies in a binarization of continuous data representoin of an original classification data in the form of a binary decision diagram (BDD). The resulting BDD helps compress the data, reveal the most essential binary features and complete classification. It is shown that such BDDs can serve as a digital blueprint of the underlying classifiers.
Keywordsdecision rules Binary Decision Diagrams Genetic Algorithms discretization granulation classifier
Unable to display preview. Download preview PDF.
- Akers B., “Binary decision digrams”, IEEE Trans. Comput., C-27(6), pp.509–16, 1978.Google Scholar
- Siebert J.P., “Vehicle recognition using rule-based methods”, Turing Institute Research Memorandum, TIRM-87-017 (March 1987).Google Scholar
- Ishiura N., Sawada H., and Yajima S., “Minimization of binary decision diagrams based on exchanges of variables”, In Proceedings of the International Conference on Computer-Aided Design, pp. 472–475, Santa Clara, CA, November 1991.Google Scholar
- Rudell R., Dynamic variable ordering for ordered binary decision diagrams, In Proceedings of the International Conference on Computer-Aided Design, pp. 42–47, Santa Clara, CA, November 1993.Google Scholar