Mahalanobis distance-based two new feature evaluation criteria

DOI10.1016/0020-0255(92)90012-WzbMath0745.62062MaRDI QIDQ1185872

S. Singh

Publication date: 28 June 1992

Published in: Information Sciences (Search for Journal in Brave)

zbMATH Keywords

feature evaluation; Mahalanobis distance-based criteria; multiclass pattern recognition problem

Mathematics Subject Classification ID

62H30: Classification and discrimination; cluster analysis (statistical aspects)

68T10: Pattern recognition, speech recognition

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Efficient feature-subset selection with probabilistic distance criteria
• An efficient estimator of pattern recognition system error probability
• An interpretation of Mahalanobis distance in the dual space
• Classification, pattern recognition and reduction of dimensionality
• On information and distance measures, error bounds, and feature selection
• Semi-invariants of the interclass Mahalanobis distance
• Moments of the interclass Mahalanobis distance
• Bayes Error Estimation Using Parzen and k-NN Procedures
• k-nearest-neighbor Bayes-risk estimation
• Mathematical methods of feature selection in pattern recognition
• Patterns in pattern recognition: 1968-1974
• Classification Error for a Very Large Number of Classes
• Calculation of Bayes' Recognition Error for Two Multivariate Gaussian Distributions