Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Journal of Medical Informatics & Technologies

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: zespoły klasyfikatora

Sortuj według:

Ogranicz wyniki do:

Medical diagnosis support system based on the ensemble of single-parameter classifiers

Orczyk T., Porwik P., Bernaś M.

Journal of Medical Informatics & Technologies

2014

Vol. 23

173--179

This paper presents a medical diagnosis support system based on an ensemble of single parameter k–NN classifiers [1]. System was verified on a database containing real blood test results of diagnosed patients with a liver fibrosis. This dataset contains problems typical to a real medical data – especially missing values. Paper also describes the process of selecting a subset of parameters used for further evaluation (feature selection/elimination algorithm). Complete database contains many parameters, but not all are important for diagnosis, thus eliminating them is an important step. A comparison of proposed method of classification and feature selection with methods known from literature has also been presented.

Hypertension diagnosis using compound pattern recognition methods

Krawczyk B., Woźniak M.

Journal of Medical Informatics & Technologies

2011

Vol. 18

41--50

The paper presents a hypertension type classification task where the decisions should be made only on the basis of blood pressure, general information and basis biochemical data. This problem has a great importance to the medical decision support systems, yet results achieved so far are not satisfactory. When the canonical approaches tend to fail we should look for the compound pattern recognition systems, such as multiple classifiers systems. This article presents the results of an experimental investigation of the pool of compound classifiers which have their origin in classifiers ensembles, random forest, and random subspace. Presented methods returned good, satisfactory results, outperforming canonical approaches for this problem.