Grid data mining for outcome prediction in intensive care medicine
This paper introduces a distributed data mining approach suited to grid computing environments based on a supervised learning classifier system. Specific Classifier and Majority Voting methods for Distributed Data Mining (DDM) are explored and compared with the Centralized Data Mining (CDM) approach...
| Autor principal: | |
|---|---|
| Outros Autores: | , |
| Formato: | conferencePaper |
| Idioma: | eng |
| Publicado em: |
2011
|
| Assuntos: | |
| Texto completo: | http://hdl.handle.net/1822/17750 |
| País: | Portugal |
| Oai: | oai:repositorium.sdum.uminho.pt:1822/17750 |
| Resumo: | This paper introduces a distributed data mining approach suited to grid computing environments based on a supervised learning classifier system. Specific Classifier and Majority Voting methods for Distributed Data Mining (DDM) are explored and compared with the Centralized Data Mining (CDM) approach. Experimental tests were conducted considering a real world data set from the intensive care medicine in order to predict the outcome of the patients. The results demonstrate that the performance of the DDM methods are better than the CDM method. |
|---|