Class-Separability Weighting and Bootstrapping in Error Correcting Output Code Ensembles
Smith, RS and Windeatt, T (2010) Class-Separability Weighting and Bootstrapping in Error Correcting Output Code Ensembles In: 9th International Workshop on Multiple Classifier Systems, 2010-04-07 - 2010-04-09, Cairo, EGYPT.
|PDF - Accepted Version |
Available under License : See the attached licence file.
|Plain Text (licence)|
A method for applying weighted decoding to error-correcting output code ensembles of binary classifiers is presented. This method is sensitive to the target class in that a separate weight is computed for each base classifier and target class combination. Experiments on 11 UCI datasets show that the method tends to improve classification accuracy when using neural network or support vector machine base classifiers. It is further shown that weighted decoding combines well with the technique of bootstrapping to improve classification accuracy still further.
|Item Type:||Conference or Workshop Item (Paper)|
|Divisions:||Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing|
|Deposited By:||Symplectic Elements|
|Deposited On:||21 Sep 2011 15:31|
|Last Modified:||08 Jun 2013 16:02|
Repository Staff Only: item control page