Abstract
In this paper we study some of the most common global measures employed to measure the classifier performance on the multi-class imbalanced problems. The aim of this work consists of showing the relationship between global classifier performance (measure by global measures) and partial classifier performance, i.e., to determine if the results of global metrics match with the improved classifier performance over the minority classes. We have used five strategies to deal with the class imbalance problem over five real multi-class datasets on neural networks context.
This work has been partially supported under grants of: Projects 3072/2011 from the UAEM, PROMEP/103.5/12/4783 from the Mexican SEP and SDMAIA-010 of the TESJO.
Chapter PDF
Similar content being viewed by others
References
Tsoumakas, G., Katakis, I.: Multi-label classification: An overview. Int. J. Data Warehousing and Mining, 1–13 (2007)
Ou, G., Murphey, Y.L.: Multi-class pattern classification using neural networks. Pattern Recognition 40(1), 4–18 (2007)
Wang, S., Yao, X.: Multi-class imbalance problems: Analysis and potential solutions. IEEE Transactions on IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics (99), 1–12 (2012)
Zhou, Z.H., Liu, X.Y.: Training cost-sensitive neural networks with methods addressing the class imbalance problem. IEEE Transactions on Knowledge and Data Engineering 18, 63–77 (2006)
Pérez-Godoy, M.D., Fernández, A., Rivera, A.J., del Jesus, M.J.: Analysis of an evolutionary rbfn design algorithm, co2rbfn, for imbalanced data sets. Pattern Recogn. Lett. 31(15), 2375–2388 (2010)
He, H., Garcia, E.: Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering 21(9), 1263–1284 (2009)
García, V., Mollineda, R.A., Sánchez, J.S.: Theoretical analysis of a performance measure for imbalanced data. In: ICPR, pp. 617–620 (2010)
Ferri, C., Hernández-Orallo, J., Modroiu, R.: An experimental comparison of performance measures for classification. Pattern Recognition Letter 30(1), 27–38 (2009)
Fawcett, T.: An introduction to roc analysis. Pattern Recogn. Lett. 27, 861–874 (2006)
Bruzzone, L., Serpico, S.: Classification of imbalanced remote-sensing data by neural networks. Pattern Recognition Letters 18, 1323–1328 (1997)
A. Asuncion, D.N.: UCI machine learning repository (2007)
Kohavi, R., John, G.H.: Wrappers for feature subset selection. Artif. Intell. 97(1-2), 273–324 (1997)
Weiss, G.M., Provost, F.J.: Learning when training data are costly: The effect of class distribution on tree induction. J. Artif. Intell. Res. (JAIR) 19, 315–354 (2003)
Wilson, D.: Asymptotic properties of nearest neighbor rules using edited data. IEEE Transactions on Systems, Man and Cybernetics 2(4), 408–420 (1972)
Sánchez, J.S., Pla, F., Ferri, F.J.: Prototype selection for the nearest neighbour rule through proximity graphs. Pattern Recognition Letters 18(6), 507–513 (1997)
Alejo, R., Valdovinos, R., García, V., Pacheco-Sanchez, J.: A hybrid method to face class overlap and class imbalance on neural networks and multi-class scenarios. Pattern Recognition Letters 34(4), 380–388 (2012)
García, S., Herrera, F.: Evolutionary undersampling for classification with imbalanced datasets: Proposals and taxonomy. Evolutionary Computation 17, 275–306 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Alejo, R., Antonio, J.A., Valdovinos, R.M., Pacheco-Sánchez, J.H. (2013). Assessments Metrics for Multi-class Imbalance Learning: A Preliminary Study. In: Carrasco-Ochoa, J.A., Martínez-Trinidad, J.F., Rodríguez, J.S., di Baja, G.S. (eds) Pattern Recognition. MCPR 2013. Lecture Notes in Computer Science, vol 7914. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38989-4_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-38989-4_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38988-7
Online ISBN: 978-3-642-38989-4
eBook Packages: Computer ScienceComputer Science (R0)