Fuzzy Decision Tree Based Classification of Psychometric Data
Krzysztof Pancerz, Vitaly Levashenko, Elena Zaitseva, Jerzy Gomula
DOI: http://dx.doi.org/10.15439/2014F487
Citation: Position Papers of the 2014 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, Vol. 3, pages 37–41 (2014)
Abstract. For five years, the Copernicus system - a tool for computer-aided diagnosis of mental disorders based on data coming from psychometric tests - is developed. This tool uses a variety of classification ways for differential interprofile diagnosis. In the current version of the tool, psychometric data come from the Minnesota Multiphasic Personality Inventory (MMPI) test. In this paper, we describe another machine learning approach, based on fuzzy decision trees, for classification of psychometric data. The algorithm for generation of fuzzy decision trees used by us is based on cumulative information estimations of initial data. Due to the promising results of classification of MMPI data, the presented approach will be implemented in the Copernicus system.