Evidential Reasoning combine with Mass- based Similarity for Imbalanced Classification
Abstract
This paper introduces an integrated approach to address imbalanced classification problems using the Dempster-Shafer theory of evidence and mass-based dissim- ilarity measurement. Traditional distance-based and density- based classifiers often struggle with skewed datasets, lead- ing to two key challenges: (1) misclassification bias, where conventional classifiers treat all instances equally despite the dominance of majority-class samples, and (2) variability in instance densities, which affects similarity assessments. To overcome these limitations, we introduce EMass, a novel classifier that replaces distance- and density-based similarity calculations with mass-based measures. Each neighbor of a considering instance is treated as an independent source of prior knowledge, represented through a basic probability assignment (BPA). We then apply Dempster’s rule of combi- nation to aggregate multiple sources of information, produc- ing a comprehensive probability estimate for classification. Experimental evaluations are conducted on 60 imbalanced data sets, comparing 12 algorithms using key performance metrics, including the F1 score, the Brier score, and the area under the curve (AUC). The results show the effectiveness of the proposed EMass classifier in improving the classification performance for imbalanced data sets.
References
R. Rastogi and K. Shim, “Public: A decision tree classifier that integrates building and pruning,” Data Mining and Knowledge Discovery, vol. 4, pp. 315–344, 2000.
J. Hatwell, M. M. Gaber, and R. M. A. Azad, “Ada-WHIPS: explaining AdaBoost classification with applications in the health sciences,” BMC Medical Informatics and Decision Making, vol. 20, no. 1, pp. 1–25, 2020.
F. Thabtah, P. Cowling, and Y. Peng, “Mcar: multi-class classification based on association rule,” in The 3rd AC- S/IEEE International Conference on Computer Systems and Applications. IEEE, 2005, p. 33.
Z. Hao, X. Wang, L. Yao, and Y. Zhang, “Improved classifi- cation based on predictive association rules,” in 2009 IEEE International Conference on Systems, Man and Cybernetics. IEEE, 2009, pp. 1165–1170.
D. Heckerman, D. Geiger, and D. M. Chickering, “Learning bayesian networks: The combination of knowledge and statistical data,” arXiv preprint arXiv:1302.6815, 2013.
S. Zhang, X. Li, M. Zong, X. Zhu, and D. Cheng, “Learning $ for $-NN classification,” ACM Transactions on Intelligent Systems and Technology (TIST), vol. 8, no. 3, pp. 1–19, 2017.
H. Cheng, X. Yan, J. Han, and S. Y. Philip, “Direct discrim- inative pattern mining for effective classification,” in 2008 IEEE 24th International Conference on Data Engineering. IEEE, 2008, pp. 169–178.
A. Paul, D. P. Mukherjee, P. Das, A. Gangopadhyay, A. R. Chintha, and S. Kundu, “Improved random forest for classi- fication,” IEEE Transactions on Image Processing, vol. 27, no. 8, pp. 4012–4024, 2018.
J. Gehrke, R. Ramakrishnan, and V. Ganti, “Rainforest—a framework for fast decision tree construction of large datasets,” Data Mining and Knowledge Discovery, vol. 4, pp. 127–162, 2000.
C. Wang, C. Deng, and S. Wang, “Imbalance-XGBoost: leveraging weighted and focal losses for binary label- imbalanced classification with XGBoost,” Pattern Recogni- tion Letters, vol. 136, pp. 190–197, 2020.
M. Ring and B. M. Eskofier, “An approximation of the Gaussian RBF kernel for efficient classification with SVMs,” Pattern Recognition Letters, vol. 84, pp. 107–113, 2016.
H. Yu, J. Yang, and J. Han, “Classifying large data sets using svms with hierarchical clusters,” in Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Dis- covery and Data Mining, 2003, pp. 306–315.
W. M. Wang, J. Wang, Z. Li, Z. Tian, and E. Tsui, “Multiple affective attribute classification of online customer product reviews: A heuristic deep learning method for supporting kansei engineering,” Engineering Applications of Artificial Intelligence, vol. 85, pp. 33–45, 2019.
Y. Villuendas-Rey, C. F. Rey-Bengur´ıa, A´ . Ferreira-Santiago, O. Camacho-Nieto, and C. Ya´n˜ez-Ma´rquez, “The na¨ıve associative classifier (nac): a novel, simple, transparent, and accurate classification model evaluated on financial data,” Neurocomputing, vol. 265, pp. 105–115, 2017.
Y. Villuendas-Rey, M. D. Alanis-Tamez, C. F. R. Bengur´ıa, C. Ya´n˜ez-Ma´rquez, and O. Camacho-Nieto, “Medical diag- nosis of chronic diseases based on a novel computational intelligence algorithm,” Journal of Universal Computer Sci- ence, pp. 775–796, 2018.
A. Orriols-Puig and E. Bernado´-Mansilla, “Evolutionary rule-based systems for imbalanced data sets,” Soft Comput- ing, vol. 13, pp. 213–225, 2009.
Y. SUN, A. K. C. WONG, and M. S. KAMEL, “Classifi- cation of imbalanced data: A review,” International Journal of Pattern Recognition and Artificial Intelligence, vol. 23, no. 04, pp. 687–719, 2009.
A. G. de Sa´, A. C. Pereira, and G. L. Pappa, “A customized classification algorithm for credit card fraud detection,” Engineering Applications of Artificial Intelligence, vol. 72, pp. 21–29, 2018.
P. Tapkan, L. O¨ zbakır, S. Kulluk, and A. Baykasog˘lu, “A cost-sensitive classification algorithm: BEE-Miner,” Knowledge-Based Systems, vol. 95, pp. 99–113, 2016.
D. Gan, J. Shen, B. An, M. Xu, and N. Liu, “Integrating TANBN with cost sensitive classification algorithm for im- balanced data in medical diagnosis,” Computers & Industrial Engineering, vol. 140, p. 106266, 2020.
C. Zhang, J. Bi, S. Xu, E. Ramentol, G. Fan, B. Qiao, and H. Fujita, “Multi-imbalance: An open-source software for multi-class imbalance learning,” Knowledge-Based Systems, vol. 174, pp. 137–143, 2019.
Y. Pan, L. Zhang, X. Wu, and M. J. Skibniewski, “Multi- classifier information fusion in risk analysis,” Information Fusion, vol. 60, pp. 121–136, 2020.
C. Zhu, B. Qin, F. Xiao, Z. Cao, and H. M. Pandey, “A fuzzy preference-based Dempster-Shafer evidence theory for decision fusion,” Information Sciences, vol. 570, pp. 306– 322, 2021.
X. Xu, D. Zhang, Y. Bai, L. Chang, and J. Li, “Evidence rea- soning rule-based classifier with uncertainty quantification,” Information Sciences, vol. 516, pp. 192–204, 2020.
K. M. Ting, Y. Zhu, M. Carman, Y. Zhu, and Z.-H. Zhou, “Overcoming key weaknesses of distance-based neighbour- hood methods using a data dependent dissimilarity measure,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Singapore: Springer, 2016, pp. 1205–1214.
A. Tversky, “Features of similarity.” Psychological Review, vol. 84, no. 4, p. 327, 1977.
C. L. Krumhansl, “Concerning the applicability of geometric models to similarity data: The interrelationship between similarity and spatial density,” American Psychologist, vol. 5, pp. 445–463, 1978.
A. Hoang, T. N. Mau, D.-V. Vo, and V.-N. Huynh, “A mass- based approach for local outlier detection,” IEEE Access, vol. 9, pp. 16 448–16 466, 2021.
A. P. Dempster, “Upper and lower probabilities induced by a multivalued mapping,” in “Classic Works of the Dempster- Shafer Theory of Belief Functions”. Berlin Heidelberg: Springer, 2008, pp. 57–72.
G. Shafer, A Mathematical Theory of Evidence. New Jersey: Princeton University Press, 1976.
T. N. Mau, Q. Le, D.-V. Vo, D. Doan, and V.-N. Huynh, “Integrating machine learning and evidential reasoning for user profiling and recommendation,” Journal of Systems Science and Systems Engineering, vol. 32, pp. 393–412, 2023.
P. Smets, “Decision making in the TBM: the necessity of the pignistic transformation,” International Journal of Approximate Reasoning, vol. 38, no. 2, pp. 133–147, 2005.
E. Ramasso and R. Gouriveau, “Prognostics in switching systems: Evidential markovian classification of real-time neuro-fuzzy predictions,” in 2010 Prognostics and System Health Management Conference. IEEE, 2010, pp. 1–10.
Z. Su, T. Denoeux, Y. Hao, and M. Zhao, “Evidential $-NN classification with enhanced performance via optimizing a class of parametric conjunctive --rules,” Knowledge-Based Systems, vol. 142, pp. 7–16, 2018.
M. Lichman et al., “UCI Machine Learning Repository,” 2013.
I. Triguero, S. Gonza´lez, J. M. Moyano, S. Garc´ıa, J. Alcala´- Fdez, J. Luengo, A. Ferna´ndez, M. J. del Jesu´s, L. Sa´nchez, and F. Herrera, “Keel 3.0: An open source software for multi-stage analysis in data mining,” International Journal of Computational Intelligence Systems, vol. 10, no. 1, pp. 1238–1249, 2017.
J. P. Siebert, “Vehicle recognition using rule based meth- ods,” Turing Institute Research Memorandum TIRM-87-0.18, 1987.
K. Nakai and M. Kanehisa, “Expert system for predicting protein localization sites in gram-negative bacteria,” Pro- teins: Structure, Function, and Bioinformatics, vol. 11, no. 2, pp. 95–110, 1991.
F. Wilcoxon, “Individual comparisons by ranking methods,” in Breakthroughs in Statistics. New York: Springer, 1992, pp. 196–202.
