Classification of Ordinal Data

Abstract

Classification of ordinal data is one of the most important tasks of relation learning. In this thesis a novel framework for ordered classes is proposed. The technique reduces the problem of classifying ordered classes to the standard two-class problem. The introduced method is then mapped into support vector machines and neural networks. Compared with a well-known approach using pairwise objects as training samples, the new algorithm has a reduced complexity and training time. A second novel model, the unimodal model, is also introduced and a parametric version is mapped into neural networks. Several case studies are presented to assert the validity of the proposed models.