Accession Number : AD0667570

Title :   COMPOUND DECISION PROCEDURES FOR PATTERN CLASSIFICATION.

Descriptive Note : Final rept. 1 Aug 65-30 Apr 67,

Corporate Author : PHILCO-FORD CORP BLUE BELL PA SYSTEM SCIENCES LAB

Personal Author(s) : Abend,Kenneth

Report Date : DEC 1967

Pagination or Media Count : 108

Abstract : Compound decision theory is shown to be powerful as a general theoretical framework for pattern recognition, leading to nonparametric methods, methods of threshold adjustment, and methods for taking context into account. The finite-sample-size performance of the Fix-Hodges nearest-neighbor nonparametric classification procedure is derived for independent binary patterns. The optimum (Bayes) sequential compound decision procedure, for known distributions and dependent states of nature is derived. When the states of nature form a Markov chain, the procedure is recursive, easily implemented, and immediately applicable to the use of context. A similar procedure, in which a decision depends on previous observations only through the decision about the preceding state of nature, can (when the populations are not well separated) yield results significantly worse than a procedure that does not depend on previous observations at all. When the populations are well separated, however, an improvement almost equal to that of the optimum sequential rule is achieved. (Author)

Descriptors :   (*PATTERN RECOGNITION, *DECISION THEORY), PROBABILITY, POPULATION(MATHEMATICS), ANALYSIS OF VARIANCE, RANDOM VARIABLES, CLASSIFICATION, CHARACTER RECOGNITION, SAMPLING

Subject Categories : Operations Research
      Bionics

Distribution Statement : APPROVED FOR PUBLIC RELEASE