C. Marrocco, M. Molinara, F. Tortorella
In this paper, we propose a method for the linear combination of several dichotomizers aimed at maximizing the area under the receiver operating characteristic (ROC) curve of the resulting classification system. This is particularly suited for real applications where it is difficult to exactly determine the key parameters such as costs and priors. In such cases, the accuracy is not adequate in measuring the quality of a classification system, while the ROC analysis provides the right tools for an appropriate assessment of the classification performance. The proposed approach revealed to be particularly effective with respect to other widespread combination rules both on artificial and real applications.
A file of this publication is available for download , for
personal use only . Click on the download button and enter your
email address in the box . You will receive an email with
instructions to proceed to download