A Novel Method for Elimination of Inconsistencies in Ordinal Classification with Monotonicity Constraints

摘要: In order to handle inconsistencies in ordinal and monotonic information systems, several relaxed versions of the Dominance-based Rough Set Approach DRSA have been proposed, e.g., VC-DRSA. These use special consistency measures admit some inconsistent objects lower approximations. The minimal level that has be attained by included approximations is defined using a prior knowledge or trial-and-error procedure. avoid dependence on knowledge, an alternative way handling iteratively eliminate most according measure until system becomes consistent. This idea base new method presented this paper called TIPStoC. TIPStoC algorithm illustrated example from area telecommunication efficiency proved computational experiment.