Modeling second-order data for classification issues: Data characteristics, algorithms, processing procedures and applications

Abstract

This review outlines some of the challenging aspects of applying second-order data modeling in classification issues analyzing selected examples of current applications. The main analytical platforms used for classification are briefly discussed from the application point of view, and the utilization of the generated data is illustrated. After a critical discussion of the advantages concerning the general features of the available algorithms and their underlying models, one example is presented and discussed in detail with the purpose of illustrating the high potentiality of second-order data modeling in the classification field. In addition, advanced data pre-processing tools, prior to multivariate analysis, are explained, and relevant tools are displayed. Finally, novelty prospects in multi-way classification area are presented.