A New Method for the Design of k-Class Bayes Classifiers
Roghayeh Doost, Mohammad Mahdi Rahmati, A. Sayyadian, Hossein Shamsi · 2007
In this paper a new method for the design of K -class bayes classifier is proposed. As a benefit, the proposed method has less complexity rather than its conventional counterparts, OVA and OVO. Simulation results show that the classification error of the proposed method is approximately identical to the classification error of conventional approaches, OVO and OVA.