Abstract
This paper proposes an idea for determining the inspection order when a new sample is classified by a neural-network-based classification system. In real world classification problems such as medical diagnoses, inspection costs for measuring many inspection items can not be negligible.Therefore, it is useful to classify a new sample by measuring a small number of inspection items. In this paper, first we propose a method for classifying a new sample by partial information on its attribute values in a neural-network-based classification system. The proposed method is based on the interval representation of incomplete (i.e., partial) input values. Next we propose an idea for determining the inspection order of input values for a new sample. Last, we illustrate the proposed approach by computer simulations on a numerical example and the iris data.
