APPLICATION OFt-CHERRY JUNCTION TREES IN PATTERN RECOGNITION

Pattern recognition aims to classify data (patterns) based ei-ther on a priori knowledge or on statistical information extracted from thedata. In this paper we will concentrate on statistical pattern recognition usinga new probabilistic approach which makes possible to select the so called ʹin-formativeʹ features. We develop a pattern recognition algorithm which is basedon the conditional independence structure underlying the statistical data. Ourmethod was succesfully applied on a real problem of recognizing Parkinsonʹsdisease on the basis of voice disorders