- Tytuł:
- Hypertension diagnosis using compound pattern recognition methods
- Autorzy:
-
Krawczyk, B.
Woźniak, M. - Powiązania:
- https://bibliotekanauki.pl/articles/333544.pdf
- Data publikacji:
- 2011
- Wydawca:
- Uniwersytet Śląski. Wydział Informatyki i Nauki o Materiałach. Instytut Informatyki. Zakład Systemów Komputerowych
- Tematy:
-
rozpoznawanie wzorców
metody złożone
zespoły klasyfikatora
uczenie maszynowe
niesymetryczna klasyfikacja
uznanie dwustopniowe
pattern recognition
compound methods
classifier ensembles
machine learning
unbalanced classification
two-stage recognition - Opis:
- 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.
- Źródło:
-
Journal of Medical Informatics & Technologies; 2011, 18; 41-50
1642-6037 - Pojawia się w:
- Journal of Medical Informatics & Technologies
- Dostawca treści:
- Biblioteka Nauki