Abstract
Classifiers fusion is considered as an effective way to promote the accuracy of pattern recognition. In practice, its performance is mainly limited by potentials and reliabilities of base classifiers, which are learned from different attribute spaces. In order to overcome the above problems, we present a new approach of classifiers fusion based on hierarchical modifications in the framework of belief function theory. At first, an intra-attribute modification is proposed to taking into account the potentials and reliabilities of base classifiers. Instead of discounting a classifier with a weight only, we employ a piece of evidence derived from the nearest labeled neighbor to modify the weighted output of one base classifier in its individual attribute space. Then, the modified output is combined with other modified results from their own attribute spaces and this procedure could be seen as an inter-attribute modification. Both modifications aim to make the classification result as close to the truth as possible, so we take them into account to construct a new objective function for optimizing the weights. Finally, some real data sets are used in experimental applications to demonstrate that the proposed method is superior to other related belief based fusion methods.
Similar content being viewed by others
References
Kuncheva LI (2004) Combining pattern classifiers: Methods and algorithms. Wiley, Hoboken
Yu ZW, Li L, Liu JM, Han GQ (2015) Hybrid adaptive classifier ensemble. IEEE Trans Cybern 45(2):177–190
Ruta D, Gabrys B (2000) An overview of classifier fusion methods. Comput Inf Syst 7:1–10
Kuncheva LI (2002) A theoretical study on six classifier fusion strategies. IEEE Trans Pattern Anal Mach Intell 24(2):281–286
Liu ZG, Zhang XX, Niu JW, Dezert J (2021) Combination of classifiers with different frames of discernment based on belief functions. IEEE Trans Fuzzy Syst 29(7):1764–1774
Moreno-Seco F, Inesta JM, Ponce de Leon PJ, Mico L (2006) Comparison of classifier fusion methods for classification in pattern recognition tasks, Joint Iapr International Conference on Structural. Springer, pp 705–713
Ruta D, Gabrys G (2005) Classifier selection for majority voting. Inf Fusion 6(1):63–81
Pizzi NJ, Pedrycz W (2010) Aggregating multiple classification results using fuzzy integration and stochastic feature selection. Int J Approx Reason 51:883–894
Song YF, Wang XD, Zhu JW, Lei L (2018) Sensor dynamic reliability evaluation based on evidence theory and intuitionistic fuzzy sets. Appl Intell 48:3950–3962
Yang JB, Xu DL (2013) Evidential reasoning rule for evidence combinations. Artif Intell 205:1–29
Liu ZG, Dezert J, Pan Q, Mercier G (2011) Combination of sources of evidence with different discounting factors based on a new dissimilarity measure. Decis Support Syst 52(1):133–141
Deng Y (2015) Generalized evidence theory. Appl Intell 43(3):530–543
Liu ZG, Liu Y, Dezert J, Cuzzolin F (2020) Evidence combination based on credal belief redistribution for pattern classification. IEEE Trans Fuzzy Syst 28(4):618–631
Liu ZG, Qiu GH, Mercier G, Pan Q (2021) A transfer classification method for heterogeneous data based on evidence theory. IEEE Trans Syst Man Cybern: Syst 51(8):5129–5141
Bi YX, Guan JW, Bell D (2008) The combination of multiple classifiers using an evidential reasoning approach. Artif Intell 172:1731–1751
Xiao FY (2020) Generalization of Dempster-Shafer theory: A complex mass function. Appl Intell 50(10):3266–3275
Quost B, Masson M-H, Denoeux T (2011) Classifier fusion in the Dempster-Shafer framework using optimized t-norm based combination rules. Int J Approx Reason 52(3):353–374
Liu ZG, Huang LQ, Zhou K, Denoeux T (2021) Combination of transferable classification with multisource domain adaptation based on evidential reasoning. IEEE Trans Neural Netw Learn Syst 32 (5):2015–2029
Mercier D, Quost B, Denoeux T (2008) Refined modeling of sensor reliability in the belief function framework using contextual discounting. Inf Fusion 9(2):246–258
Kuncheva LI, Bezdek J, Duin R (2001) Decision templates for multiple classifier fusion: an experimental comparison. Pattern Recognit 34(2):299–314
Elouedi Z, Mellouli K, Smets P (2004) Assessing sensor reliability for multisensor data fusion within the transferable belief model. IEEE Trans Syst Man Cybern Part B: Cybern 34(1):782–787
Liu ZG, Pan Q, Dezert J, Martin A (2018) Combination of classifiers with optimal weight based on evidential reasoning. IEEE Trans Fuzzy Syst 26(3):1217–1230
Liu ZG, Zhang ZW, Liu Y, Dezert J, Pan Q (2019) A new pattern classification improvement method with local quality matrix based on k-NN. Knowl Based Syst 164:336–347
Sun YX, Song L, Liu ZG (2019) Belief-based system for fusing multiple classification results with local weights. Opt Eng 58(4):041604.1-041604.9
Liu ZG, Pan Q, Dezert J, Han JW, He Y (2018) Classifier fusion with contextual reliability evaluation. IEEE Trans Cybern 48(5):1605–1618
Denoeux T (1995) A k-nearest neighbor classification rule based on Dempster-Shafer theory. IEEE Trans Syst Man Cybern 25(5):804–813
Su ZG, Denoeux T, Hao YS, Zhao M, Evidential K -N N (2018) Classification with enhanced performance via optimizing a class of parametric conjunctive trules. Knowl Based Syst 142:7–16
Denoeux T, Kanjanatarakul O, Sriboonchitta S (2015) EK-NNClus: a clustering procedure based on the evidential K-nearest neighbor rule. Knowl Based Syst 88:57–69
Ani AA, Deriche M (2002) A new technique for combining multiple classifiers using the Dempster-Shafer theory of evidence. J Artif Intell Res 17:333–361
Shafer G (1976) A mathematical theory of evidence. Princeton University Press, Princeton
Alcala-fdez J, Fernandez A, Luengo J, Derrac J, Garcia S, Sanchez L, Herrera F (2011) KEEL Data-mining software tool: data set repository, integration of algorithms and experimental analysis framework. J Multiple-Valued Log Soft Comput 17(2-3):255–287
Moreno-Torres JG, Saez JA, Herrera F (2012) Study on the impact of partition-induced dataset shift on k-fold cross-validation. IEEE Trans Neural Netw Learn Syst 23(8):1304–1313
Yu K, Zhang T (2009) High dimensional nonlinear learning using local coordinate coding. Statistics. arXiv:0906.5190
Rish I (2001) An empirical study of the naive bayes classifier. IJCAI Worksh Empir Methods Artif Intell 3(22):41–46
Denoeux T (2000) A neural network classifier based on Dempster-Shafer theory. IEEE Trans Syst Man Cybern Part A: Syst Hum 30(2):131–150
Acknowledgements
This work has been partially supported by Key Research and Development Project of Shaanxi Province (No. 2020SF-367) and Soft Science Project in Shaanxi innovation Pillar Program(No. 2020KRM079).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Song, L., Sun, Yx. An approach of classifiers fusion based on hierarchical modifications. Appl Intell 52, 6464–6476 (2022). https://doi.org/10.1007/s10489-021-02777-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02777-6