Bayes-Extension Discriminant Method of Two Populations Based on Multivariate Kernel Density Estimation | Zendy

Jilei Shi | Zendy; Shuhai Zhu | Zendy; Yingying Zhou | Zendy; Rihua Li | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Bayes-Extension Discriminant Method of Two Populations Based on Multivariate Kernel Density Estimation

Author(s) -

Jilei Shi,

Shuhai Zhu,

Yingying Zhou,

Rihua Li

Publication year - 2017

Publication title -

procedia computer science

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.334

H-Index - 76

ISSN - 1877-0509

DOI - 10.1016/j.procs.2017.11.437

Subject(s) - variable kernel density estimation , bayes' theorem , kernel density estimation , kernel (algebra) , multivariate kernel density estimation , computer science , extension (predicate logic) , density estimation , mathematics , kernel fisher discriminant analysis , statistics , pattern recognition (psychology) , naive bayes classifier , linear discriminant analysis , artificial intelligence , kernel method , bayesian probability , support vector machine , combinatorics , estimator , programming language

Introducing the correlation function of Extension into the Bayes discrimination based on kernel density estimation. This paper have obtained a new Bayes-Extension discrimination based on kernel density estimation, which combines the advantages of the former two methods. This new method eliminates the discriminant variables with this constraint for obeying normal distribution and taking into account the correlation degree of each index matter element and the overall sample matter element, applying optimal bandwidth adjustment algorithm in this paper, adjust the back substitution error rate to zero. It shows that the method of Bayes-Extension discrimination based on kernel density estimation has better effect through case analysis.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research