ROCML 2005 ACCEPTED PAPERS

Research Papers

• Bagging Evolutionary ROC-based Hypotheses Application to Terminology Extraction.
  Jérôme Azé, Mathieu Roche, and Michèle Sebag.
• The Expected Performance Curve.
  Samy Bengio, Johnny Mariéthoz, and Mikaela Keller.
• Maximizing the Area under the ROC Curve using Incremental Reduced Error Pruning.
  Henrik Boström.
• Modifying ROC Curves to Incorporate Predicted Probabilities.
  Cèsar Ferri, Peter Flach, José Hernández-Orallo, and Athmane Senad.
• Formulation and comparison of multi-class ROC surfaces.
  Jonathan E. Fieldsend and Richard M. Everson.
• Pointwise ROC Confidence Bounds: An Empirical Evaluation.
  Sofus A. Macskassy, Foster Provost and Saharon Rosset
• Optimal Linear Combination of Dichotomizers via AUC.
  • Extended Version: "Exploiting AUC for Optimal Linear Combination of Dichotomizers", Pattern Recognition Letters, 27(8), 2006. preview, doi
  Claudio Marrocco, Mario Molinara and Francesco Tortorella.
• Improving Classificaiton Performance by Exploring the Role of Cost Matrices in Partioning the Estimated Class Probability Space.
  Deirdre B. O'Brien and Robert M. Gray.
• Boosting for Regression Using Regression Error Characteristic Curves.
  Aloìsio Carlos de Pina and Gerson Zaverucha.
• A data-dependent generalisation error bound for the AUC.
  Nicolas Usunier, Massih-Reza Amini, and Patrick Gallinari.
• A Scored Metric for Classifier Evaluation and Selection.
  Shaomin Wu and Peter Flach.

Position Papers

• AUC Maximizing Support Vector Learning.
  Ulf Brefeld and Tobias Scheffer.
• Visualisation of multi-class ROC surfaces.
  Jonathan E. Fieldsend and Richard M. Everson.
• ROC Confidence Bands: An Empirical Evaluation.
  Sofus A. Macskassy, Foster Provost and Saharon Rosset