Bayesian and Decision Tree Approaches for Pattern Recognition Including Feature Measurement Costs
Galigekere R. Dattatreya, V. V. S. Sarma · IEEE Transactions on Pattern Analysis and Machine Intelligence · 1981
The minimum cost classifier when general cost functions are associated with the tasks of feature measurement and classification is formulated as a decision graph which does not reject class labels at intermediate stages. Noting its complexities, a heuristic procedure to simplify this scheme to a binary decision tree is presented. The optimization of the binary tree in this context is carried out using dynamic programming. This technique is applied to the voiced-unvoiced-silence classification in speech processing.