Skip to main content
Top
Published in: Soft Computing 13/2019

31-07-2018 | Foundations

Evidential joint calibration of binary SVM classifiers

Authors: Pauline Minary, Frédéric Pichon, David Mercier, Eric Lefevre, Benjamin Droit

Published in: Soft Computing | Issue 13/2019

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

In order to improve overall performance with respect to a classification problem, a path of research consists in using several classifiers and to fuse their outputs. To perform this fusion, some approaches merge the classifier outputs using a rule of combination. This requires that the outputs be made comparable beforehand, which is usually done thanks to a probabilistic calibration of each classifier. The fusion can also be performed by concatenating the classifier outputs into a vector and applying a joint probabilistic calibration to this vector. Recently, extensions of probabilistic calibration techniques of an individual classifier have been proposed using evidence theory, in order to better represent the uncertainties inherent to the calibration process. In this paper, we adapt this latter idea to joint probabilistic calibration techniques, leading to evidential versions of joint calibration techniques. In addition, our proposal was tested on generated and real datasets and the results showed that it either outperforms or is comparable to state-of-the-art approaches.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Footnotes
1
We used the software for the evidential \(\kappa \)NN classifier with parameter optimization available at: https://​www.​hds.​utc.​fr/​~tdenoeux/​dokuwiki/​en/​software/​k-nn
 
Literature
go back to reference Bagley SC, White H, Golomb BA (2001) Logistic regression in the medical literature: standards for use and reporting, with particular attention to one medical domain. J Clin Epidemiol 54(10):979–985CrossRef Bagley SC, White H, Golomb BA (2001) Logistic regression in the medical literature: standards for use and reporting, with particular attention to one medical domain. J Clin Epidemiol 54(10):979–985CrossRef
go back to reference Denœux T (1995) A k-nearest neighbor classification rule based on dempster-shafer theory. IEEE Trans Syst Man Cybern 25(5):804–813CrossRef Denœux T (1995) A k-nearest neighbor classification rule based on dempster-shafer theory. IEEE Trans Syst Man Cybern 25(5):804–813CrossRef
go back to reference Denœux T (1997) Analysis of evidence-theoretic decision rules for pattern classification. Pattern Recognit 30(7):1095–1107CrossRef Denœux T (1997) Analysis of evidence-theoretic decision rules for pattern classification. Pattern Recognit 30(7):1095–1107CrossRef
go back to reference Denœux T (2014) Likelihood-based belief function: justification and some extensions to low-quality data. Int J Approx Reason 55(7):1535–1547MathSciNetCrossRefMATH Denœux T (2014) Likelihood-based belief function: justification and some extensions to low-quality data. Int J Approx Reason 55(7):1535–1547MathSciNetCrossRefMATH
go back to reference Denœux T, Smets P (2006) Classification using belief functions: relationship between case-based and model-based approaches. IEEE Trans Syst Man Cybern B 36(6):1395–1406CrossRef Denœux T, Smets P (2006) Classification using belief functions: relationship between case-based and model-based approaches. IEEE Trans Syst Man Cybern B 36(6):1395–1406CrossRef
go back to reference Duin RPW (2002) The combining classifier: to train or not to train? In: Proceedings of the 16th International Conference on Pattern Recognition, Quebec City, Quebec, Canada, August, 2002, IEEE, vol 2, pp 765–770 Duin RPW (2002) The combining classifier: to train or not to train? In: Proceedings of the 16th International Conference on Pattern Recognition, Quebec City, Quebec, Canada, August, 2002, IEEE, vol 2, pp 765–770
go back to reference Hosmer DW, Lemeshow S, Sturdivant RX (2013) Applied logistic regression, vol 398. Wiley, HobokenCrossRefMATH Hosmer DW, Lemeshow S, Sturdivant RX (2013) Applied logistic regression, vol 398. Wiley, HobokenCrossRefMATH
go back to reference Kanjanatarakul O, Sriboonchitta S, Denœux T (2014) Forecasting using belief functions: an application to marketing econometrics. Int J Approx Reason 55(5):1113–1128MathSciNetCrossRefMATH Kanjanatarakul O, Sriboonchitta S, Denœux T (2014) Forecasting using belief functions: an application to marketing econometrics. Int J Approx Reason 55(5):1113–1128MathSciNetCrossRefMATH
go back to reference Kanjanatarakul O, Denœux T, Sriboonchitta S (2016) Prediction of future observations using belief functions: a likelihood-based approach. Int J Approx Reason 72:71–94MathSciNetCrossRefMATH Kanjanatarakul O, Denœux T, Sriboonchitta S (2016) Prediction of future observations using belief functions: a likelihood-based approach. Int J Approx Reason 72:71–94MathSciNetCrossRefMATH
go back to reference Minary P, Pichon F, Mercier D, Lefevre E, Droit B (2016) An evidential pixel-based face blurring approach. In: Vejnarov J, Kratochvil V (eds) Proceedings of the 4th International Conference on Belief Functions, Prague, Czech Republic, September 21–23, Springer, Lecture Notes in Computer Science, vol 9861, pp 222–230 Minary P, Pichon F, Mercier D, Lefevre E, Droit B (2016) An evidential pixel-based face blurring approach. In: Vejnarov J, Kratochvil V (eds) Proceedings of the 4th International Conference on Belief Functions, Prague, Czech Republic, September 21–23, Springer, Lecture Notes in Computer Science, vol 9861, pp 222–230
go back to reference Minary P, Pichon F, Mercier D, Lefevre E, Droit B (2017) Evidential joint calibration of binary svm classifiers using logistic regression. In: Proceedings of the 11th international conference on scalable uncertainty management, Granada, Spain, October 4–6, 2017, Lecture Notes in Artificial Intelligence, Springer, p 7 Minary P, Pichon F, Mercier D, Lefevre E, Droit B (2017) Evidential joint calibration of binary svm classifiers using logistic regression. In: Proceedings of the 11th international conference on scalable uncertainty management, Granada, Spain, October 4–6, 2017, Lecture Notes in Artificial Intelligence, Springer, p 7
go back to reference Minka TP (2003) Algorithms for maximum-likelihood logistic regression. Technical Report 758, Carnegie Mellon University Minka TP (2003) Algorithms for maximum-likelihood logistic regression. Technical Report 758, Carnegie Mellon University
go back to reference Platt JC (1999) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv Large Margin Classif 10(3):61–74 Platt JC (1999) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv Large Margin Classif 10(3):61–74
go back to reference Shafer G (1976) A mathematical theory of evidence, vol 1. Princeton University Press, PrincetonMATH Shafer G (1976) A mathematical theory of evidence, vol 1. Princeton University Press, PrincetonMATH
go back to reference Smets P (1993) Belief functions: the disjunctive rule of combination and the generalized Bayesian theorem. Int J Approx Reason 9(1):1–35MathSciNetCrossRefMATH Smets P (1993) Belief functions: the disjunctive rule of combination and the generalized Bayesian theorem. Int J Approx Reason 9(1):1–35MathSciNetCrossRefMATH
go back to reference Tulyakov S, Jaeger S, Govindaraju V, Doermann D (2008) Review of classifier combination methods. In: Marinai S, Fujisawa H (eds) Machine learning in document analysis and recognition. Springer, Berlin, pp 361–386CrossRef Tulyakov S, Jaeger S, Govindaraju V, Doermann D (2008) Review of classifier combination methods. In: Marinai S, Fujisawa H (eds) Machine learning in document analysis and recognition. Springer, Berlin, pp 361–386CrossRef
go back to reference Xu P, Davoine F, Denœux T (2015) Evidential multinomial logistic regression for multiclass classifier calibration. In: Proceedings of the 18th international conference on information fusion, Washington, DC, USA, July 6–9, 2015, IEEE, pp 1106–1112 Xu P, Davoine F, Denœux T (2015) Evidential multinomial logistic regression for multiclass classifier calibration. In: Proceedings of the 18th international conference on information fusion, Washington, DC, USA, July 6–9, 2015, IEEE, pp 1106–1112
go back to reference Zadrozny B, Elkan C (2001) Obtaining calibrated probability estimates from decision trees and naive bayesian classifiers. In: Proceedings of the 18th international conference on machine learning, Morgan Kaufmann, pp 609–616 Zadrozny B, Elkan C (2001) Obtaining calibrated probability estimates from decision trees and naive bayesian classifiers. In: Proceedings of the 18th international conference on machine learning, Morgan Kaufmann, pp 609–616
go back to reference Zadrozny B, Elkan C (2002) Transforming classifier scores into accurate multiclass probability estimates. In: Proceedings of the 8th international conference on knowledge discovery and data mining, New York, NY, USA, 2002, ACM, pp 694–699 Zadrozny B, Elkan C (2002) Transforming classifier scores into accurate multiclass probability estimates. In: Proceedings of the 8th international conference on knowledge discovery and data mining, New York, NY, USA, 2002, ACM, pp 694–699
go back to reference Zhong W, Kwok JT (2013) Accurate probability calibration for multiple classifiers. In: Proceedings of the 23rd international joint conference on artificial intelligence, Beijing, China, August, 2013, pp 1939–1945 Zhong W, Kwok JT (2013) Accurate probability calibration for multiple classifiers. In: Proceedings of the 23rd international joint conference on artificial intelligence, Beijing, China, August, 2013, pp 1939–1945
go back to reference Zouhal LM, Denœux T (1998) An evidence-theoretic k-nn rule with parameter optimization. IEEE Trans Syst Man Cybern C 28(2):263–271CrossRef Zouhal LM, Denœux T (1998) An evidence-theoretic k-nn rule with parameter optimization. IEEE Trans Syst Man Cybern C 28(2):263–271CrossRef
Metadata
Title
Evidential joint calibration of binary SVM classifiers
Authors
Pauline Minary
Frédéric Pichon
David Mercier
Eric Lefevre
Benjamin Droit
Publication date
31-07-2018
Publisher
Springer Berlin Heidelberg
Published in
Soft Computing / Issue 13/2019
Print ISSN: 1432-7643
Electronic ISSN: 1433-7479
DOI
https://doi.org/10.1007/s00500-018-3429-x

Other articles of this Issue 13/2019

Soft Computing 13/2019 Go to the issue

Premium Partner