Automatic Fuzzy Classification System for Metabolic Types Detection

Abstract

Patients suffering from obesity have different demands for medical treatment regarding the causes of their metabolic disorders. To propose new medical solutions to weight reduction, it is desirable to group patients exhibiting similar characteristics. This contribution describes an automatic fuzzy classification system capable of dividing obese patients into groups of diverse metabolic types. Metabolic data were acquired through energometry tests and bioimpedance measurements. Methods considered in this paper are particularly Principal Component Analysis used for data set's reduction and fuzzy clustering method dividing patients into groups called clusters. Newly tested patients are then classified into designed clusters. A set of statistical hypothesis testing methods is eventually applied to verify the performed classification. The designed classification system could be applied in hospitals to help the doctors with design of an individual treatment for obese patients' groups.

A Fuzzy Evaluation of Quality for Color Vision Disorders Diagnostic

“…In the future, the software for testing color vision will be extended to be able to diagnose the particular color blindness, using neural networks [13,14].…”