Answers are grounded in this paper and cite their sources.
Abstract. A new hybrid classifier is proposed which utilizes the advantages of the maximum likelihood classifier and the parallelepiped classifier. The new hybrid classifier reduces the processing time more substantially than the conventional one by introducing a lower boundary for each class. The rate of misclassification is comparable to that of maximum likelihood classifier. Performance of the conventional and the new method are compared by an example.
No takes yet. Share an insight, caveat, or question.
Koo et al. (1986) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: