Abstract
A method of fast bandwidth selection in a nonparametric algorithm of pattern recognition corresponding to the maximum a posteriori probability criterion is proposed. The algorithm is based on the results of studying the asymptotic properties of the nonparametric estimate of the separation surface equation and probability densities in solving a two-alternative problem of pattern recognition. The proposed method is compared with the traditional approach based on minimizing the classification error probability estimate.
Similar content being viewed by others
References
E. V. Dmitriev, V. V. Kozoderov, A. O. Dementyev, and A. N. Safonova, “Combining Classifiers in the Problem of Thematic Processing of Hyperspectral Aerospace Images,” Avtometriya 54(3), 3–13 (2018) [Optoelectron., Instrum. Data Process. 54 (3), 213–221 (2018)].
A. V. Lapko and V. A. Lapko, “Nonparametric Algorithms for Estimating the States of Natural Objects,” Avtometriya 54(5), 33–39 (2018) [Optoelectron., Instrum. Data Process. 54 (5), 451–456 (2018)].
M. I. Borrajo, W. González-Manteiga, and M. D. Martínez-Miranda, “Bandwidth Selection for Kernel Density Estimation with Length-Biased Data,” J. Nonparametr. Statist. 29(3), 636–668 (2017). DOI: https://doi.org/10.1080/10485252.2017.1339309.
S. Chen, “Optimal Bandwidth Selection for Kernel Density Functionals Estimation,” J. Probability Statist. 242683 (2015). DOI: https://doi.org/10.1155/2015/242683.
D. W. Scott, Multivariate Density Estimation: Theory, Practice, and Visualization (John Wiley and Sons, New Jersey, 2015).
S. J. Sheather, “Density Estimation,” Statist. Sci. 19(4), 588–597 (2004). DOI: https://doi.org/10.1214/088342304000000297.
B. W. Silverman, Density Estimation for Statistics and Data Analysis (Chapman and Hall, London, 1986).
A. V. Lapko and V. A. Lapko, “Fast Algorithm for Choosing the Fuzziness Coefficients of the Kernel Functions in the Nonparametric Estimate of the Probability Density,” Izmer. Tekhnika, No. 6, 16–20 (2018). DOI: https://doi.org/10.32446/0368-1025it-2018-6-16-20.
A. V. Lapko and V. A. Lapko, “Fast Algorithm for Choosing the Fuzziness Coefficients in Multi-Dimensional Kernel Estimates of the Probability Density,” Izmer. Tekhnika, No. 10, 19–23 (2018).
A. V. Lapko and V. A. Lapko, Multilevel Nonparametric Systems of Information Processing (SibGAU, Krasnoyarsk, 2013) [in Russian].
E. Parzen, “On Estimation of a Probability Density Function and Mode,” Ann. Math. Statist. 33(3), 1065–1076 (1962).
V. A. Epanechnikov, “Nonparametric Estimate of the Multidimensional Probability Density,” Teor. Veroyatn. Primen. 14(1), 156–161 (1969).
A. V. Lapko and V. A. Lapko, “Asymptotic Properties of the Nonparametric Estimate of the Separation Surface Equation in the Pattern Recognition Algorithm Corresponding to the Criterion of the Maximum a Posteriori Probability,” Sit. Upravl. Inform. Tekhnol. 42(4), 58–61 (2010).
V. E. Gmurman, Probability Theory and Mathematical Statistics (Vysshaya Shkola, Moscow, 1999) [in Russian].
A. S. Sharakshane, I. G. Zheleznov, and V. A. Ivnitskii, Complex Systems (Vysshaya Shkola, Moscow, 1977) [in Russian].
Author information
Authors and Affiliations
Corresponding author
Additional information
Russian Text © The Author(s), 2019, published in Avtometriya, 2019, Vol. 55, No. 6, pp. 76–86.
About this article
Cite this article
Lapko, A.V., Lapko, V.A. Method of Fast Bandwidth Selection in a Nonparametric Classifier Corresponding to the a Posteriori Probability Maximum Criterion. Optoelectron.Instrument.Proc. 55, 597–605 (2019). https://doi.org/10.3103/S8756699019060104
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S8756699019060104