Please use this identifier to cite or link to this item:
Title: Predicting Receiver Operating Characteristic Curve, Area Under Curve, and Arithmetic Means of Accuracies based on the Distribution of Data Samples
Authors: Timotius, Ivanna Kristianti
Keywords: classifier performance measurement;receiver operating characteristic curve;area under curve;arithmetic means of accuracies;data sample distribution
Issue Date: Jun-2013
Publisher: IEEE Joint CSS/RAS Indonesia Chapter
Abstract: Measuring the performance of a classifier is an essential step in building a classification method for a two class classification problem. The Receiver Operating Characteristic ROC) Curve, Area Under ROC Curve (AUC), and Arithmetic Means of Accuracies (Ameans) are several classifier performance measurements that are typically calculated by conducting an experiment. This paper presents predicting methods of these classifier performance measurements based on the data sample distributions. The experiment shows that the predicting methods results are similar with the empirical results using the testing data set. Therefore the methods are applicable in predicting the classifier performance without conducting an experiment. The predicted performance measurements might be useful in evaluating the discriminability of a feature sample
Description: Proceedings of 2nd 2013 IEEE Conference On Control, Systems & Industrial Informatics (2013 : Bandung, p. 60 - 64
ISBN: 9781467358170
Appears in Collections:Published Research Reports

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