Application Of t-Cherry Junction Trees in Pattern Recognition

Tamas Szantai, Edith Kovacs

Abstract


Pattern recognition aims to classify data (patterns) based ei-
ther on a priori knowledge or on statistical information extracted from the data. In this paper we will concentrate on statistical pattern recognition using a new probabilistic approach which makes possible to select the so called 'informative' features. We develop a pattern recognition algorithm which is based on the conditional independence structure underlying the statistical data. Our method was succesfully applied on a real problem of recognizing Parkinson's disease on the basis of voice disorders.

Keywords


pattern recognition, probabilistic modeling, h-uniform hyper- tree, t-cherry junction tree

Full Text:

PDF


(C) 2010-2017 EduSoft