Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Multi-segments Naïve Bayes classifier in likelihood space

© The Institution of Engineering and Technology
Received 12/11/2017, Accepted 24/04/2018, Revised 16/03/2018, Published 26/04/2018

Naïve Bayes (NB) classifier has shown amazing performance in many real applications. However, the true probability distributions are usually unknown and tend to be quite complicated with high feature dimensions. Incorrect estimation models will decrease classification performance. In this study, a new method named multi-segment NB classifier is proposed to reduce errors caused by improper estimation models by implementing the classification directly in the likelihood space rather than through calculating posterior probability. The estimation of the conditional probability distribution is treated as a non-linear projection method which maps the original features into the likelihood space. Then, the mapped data is divided into some successive sub-segments and the classifier in each segment is trained by the corresponding sub-dataset, respectively. The discriminant functions are learned through a distance-measure method instead of a probability-based way and the parameters of the former classifier are used in the next training process in order to decrease the searching space. Experimental results on benchmark datasets demonstrate the effectiveness of the proposed method.

Inspec keywords: pattern classification; statistical distributions; Bayes methods

Other keywords: incorrect estimation models; posterior probability; error reduction; discriminant functions; training process; mapped data; multisegments Naïve Bayes classifier; distance-measure method; nonlinear projection method; conditional probability distribution; likelihood space

Subjects: Other topics in statistics; Data handling techniques

References

    1. 1)
      • 18. Zhang, L., Jiang, L., Li, C., et al: ‘Two feature weighting approaches for naive Bayes text classifiers’, Knowl.-Based Syst., 2014, 100, (C), pp. 137–144.
    2. 2)
      • 21. Nunzio, G.M.D.: ‘A new decision to take for cost-sensitive naïve Bayes classifiers’, Inf. Process. Manage., 2014, 50, (5), pp. 653–674.
    3. 3)
      • 24. Soria, D., Garibaldi, J.M., Ambrogi, F., et al: ‘A ‘non-parametric’ version of the naïve Bayes classifier’, Knowl.-Based Syst., 2011, 24, (6), pp. 775–784.
    4. 4)
      • 3. Jones, M., Goldstein, M., Jonathan, P., et al: ‘Bayes linear analysis for Bayesian optimal experimental design’, J. Stat. Plan. Inference, 2016, 171, pp. 115–129.
    5. 5)
      • 10. Hsu, C.C., Huang, Y.P., Chang, K.W.: ‘Extended naïve Bayes classifier for mixed data’, Expert Syst. Appl., 2008, 35, (3), pp. 1080–1083.
    6. 6)
      • 22. Liu, Z.X., Zou, Y.N., Xie, W.X., et al: ‘Multi-target Bayes filter with the target detection’, Signal Process., 2017, 140, pp. 69–76.
    7. 7)
      • 25. Sáez-Atienzar, S., Martínez-Gómez, J., Alonso-Barba, J.I., et al: ‘Automatic quantification of the subcellular localization of chimeric GFP protein supported by a two-level Naive Bayes classifier’, Expert Syst. Appl., 2015, 42, (3), pp. 1531–1537.
    8. 8)
      • 12. Zheng, F., Webb, G.I.: ‘Efficient lazy elimination for averaged one-dependence estimators’. Proc. 23rd int. Conf. on Machine learning, Pittsburgh, USA, June 2006, pp. 1113–1120.
    9. 9)
      • 11. Zheng, Z., Webb, G.I.: ‘Lazy learning of Bayesian rules’, Mach. Learn., 2000, 41, (1), pp. 53–84.
    10. 10)
      • 20. Jiang, L., Li, C., Wang, S.: ‘Cost-sensitive Bayesian network classifiers’, Pattern Recognit. Lett., 2014, 45, (1), pp. 211–216.
    11. 11)
      • 4. Sun, S., Taylor, J.S., Mao, L.: ‘PAC-Bayes analysis of multi-view learning’, Inf. Fusion, 2017, 35, pp. 117–131.
    12. 12)
      • 17. Dai, Q., Li, J., Wang, J., et al: ‘A Bayesian hashing approach and its application to face recognition’, Neurocomputing, 2016, 213, pp. 5–13.
    13. 13)
      • 5. Xie, X., Sun, S.: ‘PAC-Bayes bounds for twin support vector machines’, Neurocomputing, 2017, 234, pp. 137–143.
    14. 14)
      • 19. Wong, T.T., Liu, C.R.: ‘An efficient parameter estimation method for generalized Dirichlet priors in naïve Bayesian classifiers with multinomial models’, Pattern Recognit., 2016, 60, pp. 62–71.
    15. 15)
      • 16. Tütüncü, G.Y., Kayaalp, N.: ‘An aggregated fuzzy Naive Bayes data classifier’, J. Comput. Appl. Math., 2015, 286, pp. 17–27.
    16. 16)
      • 28. Rong, D., Wei, J., Hong, M.: ‘Semi-supervised image classification in likelihood space’. Int. Conf. on Image Processing, Atlanta, USA, October 2006, pp. 957–960.
    17. 17)
      • 1. Escalante, H.J., Morales, E.F., Sucar, L.E.: ‘A naïve Bayes baseline for early gesture recognition’, Pattern Recognit. Lett., 2016, 73, (C), pp. 91–99.
    18. 18)
      • 14. Šuch, O., Barreda, S.: ‘Bayes covariant multi-class classification’, Pattern Recognit. Lett., 2016, 84, pp. 99–106.
    19. 19)
      • 27. Singh, R., Raj, B.: ‘Classification in likelihood spaces’, Technometrics, 2004, 46, (3), pp. 318–329.
    20. 20)
      • 8. Benadit, P.J., Francis, F.S., Muruganantham, U.: ‘Improving the performance of a proxy cache using tree augmented naive Bayes classifier’, Procedia Comput. Sci., 2015, 46, pp. 184–193.
    21. 21)
      • 26. Domingos, P., Pazzani, M.: ‘On the optimality of the simple Bayesian classifier under zero-one loss’, Mach. Learn., 1997, 29, (2–3), pp. 103–130.
    22. 22)
      • 2. Ko, Y.: ‘How to use negative class information for Naive Bayes classification’, Inf. Process. Manage., 2017, 53, pp. 1255–1268.
    23. 23)
      • 13. Li, J., Fang, G., Li, B., et al: ‘A novel naive Bayes classifier model based on differential evolution’. Int. Conf. on Intelligent Computing, Fuzhou, China, August 2015, pp. 558–566.
    24. 24)
      • 23. Zhang, H., Cao, Z.X., Li, M., et al: ‘Novel naïve Bayes classification models for predicting the carcinogenicity of chemicals’, Food Chem. Toxicol., 2016, 97, pp. 141–149.
    25. 25)
      • 15. Borrotti, M., Minervini, G., Lucrezia, D.D., et al: ‘Naïve Bayes ant colony optimization for designing high dimensional experiments’, Appl. Soft Comput., 2016, 49, pp. 259–268.
    26. 26)
      • 6. Birgé, L.: ‘About the non-asymptotic behaviour of Bayes estimators’, J. Stat. Plan. Inference, 2015, 166, pp. 67–77.
    27. 27)
      • 29. Yu, S., Tan, T., Huang, K., et al: ‘A study on gait-based gender classification’, IEEE Trans. Image Process., 2009, 18, (8), pp. 1905–1910.
    28. 28)
      • 30. Yu, S., Tan, D., Tan, T.: ‘A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition’. Int. Conf. on Pattern Recognition, Hong Kong, China, August 2006, pp. 441–444.
    29. 29)
      • 9. Jiang, L., Wang, S., Li, C., et al: ‘Structure extended multinomial naive Bayes’, Inf. Sci., 2016, 329, (C), pp. 346–356.
    30. 30)
      • 7. Mizianty, M.J., Kurgan, L.A., Ogiela, M.R.: ‘Discretization as the enabling technique for the Naive Bayes and semi-Naive Bayes-based classification’, Knowl. Eng. Rev., 2010, 25, (4), pp. 421–449.
    31. 31)
      • 31. Mansouri, N., Mohammed, A.I., Jemaa, Y.B.: ‘Gait features fusion for efficient automatic age classification’, IET Comput. Vis., 2018, 12, (1), pp. 69–75.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2017.0546
Loading

Related content

content/journals/10.1049/iet-cvi.2017.0546
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address