The University of Dublin | Trinity College -- Ollscoil Átha Cliath | Coláiste na Tríonóide
Trinity's Access to Research Archive
Home :: Log In :: Submit :: Alerts ::

School of Computer Science and Statistics >
Computer Science >
Computer Science Technical Reports >

Please use this identifier to cite or link to this item:

Title: Dynamic Integration of Classifiers for Tracking Concept Drift in Antibiotic Resistance Data
Author: Tsymbal, Alexey
Cunningham, Pádraig
Keywords: Computer Science
Issue Date: 17-Feb-2005
Publisher: Trinity College Dublin, Department of Computer Science
Citation: Tsymbal, Alexey; Cunningham, Pádraig. 'Dynamic Integration of Classifiers for Tracking Concept Drift in Antibiotic Resistance Data'. - Dublin, Trinity College Dublin, Department of Computer Science, TCD-CS-2005-26, 2005, pp11
Series/Report no.: Computer Science Technical Report
Abstract: In the real world concepts are often not stable but change with time. A typical example of this in the medical context is antibiotic resistance, where pathogen sensitivity may change over time as new pathogen strains develop resistance to antibiotics which were previously effective. This problem, known as concept drift, complicates the task of learning a model from medical data and requires special approaches, different from commonly used techniques, which treat arriving instances as equally important contributors to the final concept. The underlying data distribution may change as well, making previously built models useless, which is known as virtual concept drift. These changes make regular updates of the model necessary. Among the most popular and effective approaches to handle concept drift is ensemble learning, where a set of models built over different time periods is maintained and the best model is selected or the predictions of models are combined according to their expertise level regarding the current concept. In this paper we propose a new ensemble integration technique that helps to better track concept drift at the instance level. Our experiments with the antibiotic resistance data show that dynamic integration of classifiers built over small time intervals can be more effective than the best single learning algorithm applied in combination with feature selection, which gives the best known accuracy for the considered problem domain. Besides, dynamic integration is significantly better than weighted voting which is currently the most commonly used integration approach for tracking concept drift with ensembles.
Appears in Collections:Computer Science Technical Reports

Files in This Item:

File Description SizeFormat
TCD-CS-2005-26.pdf74.04 kBAdobe PDFView/Open

This item is protected by original copyright

Please note: There is a known bug in some browsers that causes an error when a user tries to view large pdf file within the browser window. If you receive the message "The file is damaged and could not be repaired", please try one of the solutions linked below based on the browser you are using.

Items in TARA are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback