A classification reliability driven reject rule for multi-expert systems

In this paper we propose a reject rule applicable to a Multi-Expert System (MES). The rule is adaptive to the given domain and allows the achievement of the best trade-off between reject and error rates as a function of the c osts attributed to errors and rejects in the considered application. The re sults of the method axe particularly effective since the method does not re ly on particular statistical assumptions, as other reject rules. An experim ental analysis carried out on publicly available databases is reported toge ther with a comparison with other methods present in the literature.