Please use this identifier to cite or link to this item: http://hdl.handle.net/1880/46403
Title: EVALUATING CLASSIFIER COMBINATION USING SIMULATED CLASSIFIERS
Authors: Parker, James
Keywords: Computer Science
Issue Date: 25-Oct-2000
Abstract: The use of standard data sets with known properties is standard practice for the evaluation of composite classifiers. However, because the properties of the original test data cannot be specified in advance, it is difficult to conduct controlled tests on classifier combination methods. In these cases it is common to use simulated data, but a standard means for doing this has not evolved. Confusion matrices can also be used to create simulated classifiers having similar properties to the original and, by generating specific confusion matrices and basing a set of simulated classifiers on these, test suites can be designed that have pre-determined properties. This simulation allows controlled testing of classifier combination techniques. Such a scheme is described and evaluated using known combination methods and standard data sets, both to confirm the simulation and to demonstrate its flexibility.
URI: http://hdl.handle.net/1880/46403
Appears in Collections:Parker, James

Files in This Item:
File Description SizeFormat 
2000-659-11.pdf25.65 kBAdobe PDFView/Open
2000-659-11.ps152.03 kBPostscriptView/Open


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