Effect of dimensionality and estimation on the performance of Gaussian classifiers

DOI10.1016/0031-3203(80)90035-7zbMath0444.62072OpenAlexW1995603776MaRDI QIDQ1144876

A. G. Wacker, T. S. El-Sheikh

Publication date: 1980

Published in: Pattern Recognition (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0031-3203(80)90035-7

zbMATH Keywords

maximum likelihood estimationpattern classificationcorrelation coefficientMahalanobis distanceBayes classification rulemultivariate Gaussian distributionpeaking phenomenonaverage probability of correct classificationeffect of dimensionalityoptimum number of measurements

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Bayesian inference (62F15) Probabilistic methods, stochastic differential equations (65C99)

Related Items (3)

Sufficiency of variables in discrete discriminant analysis ⋮ Determination of the optimal number of features for quadratic discriminant analysis via the normal approximation to the discriminant distribution ⋮ Average classification accuracy over collections of Gaussian problems - common covariance matrix case

Cites Work

• Unnamed Item
• Unnamed Item
• On the optimal number of features in the classification of multivariate Gaussian data
• Errors in Discrimination
• Independence, Measurement Complexity, and Classification Performance
• On the Effects of Dimension in Discriminant Analysis
• "Independence, Measurement Complexity, and Classification Performance": An Emendation
• Dimensionality and Classification Performance with Independent Coordinates
• On the Peaking of the Hughes Mean Recognition Accuracy: The Resolution of an Apparent Paradox
• On the monotonicity of the performance of Bayesian classifiers (Corresp.)
• Quantization Complexity and Independent Measurements
• Error Probability in Decision Functions for Character Recognition
• Error analysis of a statistical decision method

This page was built for publication: Effect of dimensionality and estimation on the performance of Gaussian classifiers