Application of a method of managing evidential reasoning to decision tree classifier
The possibility and advantage of applying a method of managing evidential reasoning to decision tree classifyer is discussed. Relative algorithms are proposed and some experiments have been conducted. Results are very good.
KeywordsFeature Extraction Internal Node Tree Classifier Error Accumulation Evidential Reasoning
Unable to display preview. Download preview PDF.
- Q.R. Wang and C.Y. Suen, "Analysis and Design of a Decition Tree Based on Entropy Reduction and Its Application to Large Character Set Recognition", IEEE Tr.Vol PAMI-6, pp406–417, 1984Google Scholar
- M. Ben-Bassat and L. Zaidenberg, "Contextual Template Matching: A Distance Measure for Patterns with Hierarchically Dependent Features", IEEE Tr.Vol PAMI-6, pp201–211, 1984Google Scholar
- Q.R. Wang and C.Y. Suen, "Large Tree Classifier with Heuristic Search and Global Training", IEEE Tr.Vol PAMI-9, pp91–103, 1987Google Scholar
- A.V.Kulkarni and L.N.Kanal, "Admissible Search Strategies for Parametric and Nonparametric Hierarchical Classification", in proc. of 4th IJCPR, Japan, Nov. 1978Google Scholar