Decision Combination in Multiple Classifier Systems
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Generating classifier outputs of fixed accuracy and diversity
Pattern Recognition Letters
Experiments with Classifier Combining Rules
MCS '00 Proceedings of the First International Workshop on Multiple Classifier Systems
Evaluation of Combination Methods
ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
An Overview and Comparison of Voting Methods for Pattern Recognition
IWFHR '02 Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02)
Design of a new classifier simulator
MCS'05 Proceedings of the 6th international conference on Multiple Classifier Systems
| Hi-index | 0.00 |
The use of artificial outputs generated by a classifiersimulator has recently emerged as a new trend toprovide an underlying evaluation of classifiercombination methods. In this paper, we propose a newmethod for the artificial generation of classifier outputsbased on additional parameters which provide sufficientdiversity to simulate, for a problem of any number ofclasses and any type of output, any classifierperformance. This is achieved through a two-stepalgorithm which first builds a confusion matrixaccording to desired behaviour and secondly generates,from this confusion matrix, outputs of any specifiedtype. We provide the detailed algorithms andconstraints to respect for the construction of the matrixand the generation of outputs. We illustrate on a smallexample the usefulness of the classifier simulator.