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...

Full description

Bibliographic Details
Main Author: Santos, Manuel Filipe (author)
Other Authors: Wesley, Mathew (author), Portela, Filipe (author)
Format: conferencePaper
Language:eng
Published: 2011
Subjects:
Intensive care medicine
Outcome prediction
Grid data mining
Distributed data mining
Centralized data mining
Science & Technology
Online Access:http://hdl.handle.net/1822/17750
Country:Portugal
Oai:oai:repositorium.sdum.uminho.pt:1822/17750
Description
Summary: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.

Similar Items