Abstract
In this paper, we propose a new function for estimating the quality of classification into N classes. This function is invariant to the imbalance of classes to be processed. It is constructed by computing the sine of an angle formed by the errors of each class in an N-dimensional space. A geometrical substantiation of its construction is provided and its properties are investigated. It is shown that this function is an improved version of the balanced accuracy function. In contrast to other functions, the proposed function considers class distribution of errors. Examples of analyzing the confusion matrices in the classification of synthetic and real-world data are provided.
Similar content being viewed by others
REFERENCES
H. Guo, Y.Li, J. Shang, M. Gu., Y. Huang, and B. Gong, “Learning from class-imbalanced data: Review of methods and applications,” Expert Syst. Appl., 73, 220–239 (2017).
V. V. Starovoitov and Yu. I. Golub, “Comparative study of quality estimation of binary classification,” Inf. 17 (1), 87–101 (2020) [in Russian]. https://doi.org/10.37661/1816-0301-2020-17-1-87-101
H. He and Y. Ma (Eds.), Imbalanced Learning: Foundations, Algorithms, and Applications (Wiley, Hoboken, NJ, 2013).
A. Pierleoni, P. L. Martelli, P. Fariselli, and R. Casadio, “BaCelLo: a balanced subcellular localization predictor,” Bioinf. 22 (14), e408–e416 (2006).
P. M. Buscema, G. Massini, and G. Maurelli, “Artificial Adaptive Systems to predict the magnitude of earthquakes,” Boll. Geofis. Teor. Appl. 56 (2), 227–256 (2015).
S. Nurmaini, R. U. Partan, W. Caesarendra, T. Dewi, M. N. Rahmatullah, A. Darmawahyuni, V. Bhayyu, and F. Firdaus, “An automated ECG beat classification system using Deep Neural Networks with an unsupervised feature extraction technique,” Appl. Sci. 9 (14), Article 2921, 1–17 (2019). https://doi.org/10.3390/app9142921
E. Dobos, E. Micheli, M. F. Baumgardner, L. Biehl, and T. Helt, “Use of combined digital elevation model and satellite radiometric data for regional soil mapping,” Geoderma 97 (3–4), 367–391 (2000).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors declare that they do not have a conflict of interest.
Additional information
Starovoitov Valery, Dr. Sci. (Eng.), Professor, laureate of State Prize of the Republic of Belarus, Chief Researcher, the United Institute of Informatics Problems of the National Academy of Sciences of Belarus, Minsk, Belarus.
Golub Yuliya, Cand. Sci. (Eng.), Associate Professor, Senior Research, the United Institute of Informatics Problems of the National Academy of Sciences of Belarus, Minsk, Belarus.
Translated by Yu. Kornienko
Rights and permissions
About this article
Cite this article
Starovoitov, V.V., Golub, Y.I. New Function for Estimating Imbalanced Data Classification Results. Pattern Recognit. Image Anal. 30, 295–302 (2020). https://doi.org/10.1134/S105466182003027X
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S105466182003027X