The Optimal Classification Using a Linear Discriminant for Two Point Classes Having Known Mean and Covariance

Abstract

The current study provides a simple algorithm for finding the optimal ROC curve for a linear discriminant between two point distributions, given only information about the classes' means and covariances. The method makes no assumptions concerning the exact type of distribution and is shown to provide the best possible discrimination for any physically reasonable measure of the classification error. This very general solution is shown to specialise to results obtained in other papers which assumed multi-dimensional Gaussian distributed classes, or minimised the maximum classification error. Some numerical examples are provided which show the improvement in classification of this method over previously used methods.

Efficiently training a better visual detector with sparse eigenvectors

“…As mentioned in [15] that a more general technique for generating discriminating hyperplanes is to define the total within-class covariance matrix as…”

Quantitative Automated Image Analysis System with Automated Debris Filtering for the Detection of Breast Carcinoma Cells

“…7) shows a high degree of separation. Using discriminant analysis, an optimally separating cutoff line can be drawn between the 2 populations [34]. …”

An optimized feature selection and classification method for using electroencephalographic coherence in brain–computer interfaces

“…In the case of I = 2 classes, the discriminating hyperplane is computed through the following normal vector [12]:…”

“…The discriminant defined by (9)- (12) has been proven to offer better performance in comparison to the traditional FLD, specially in cases when the covariances of the two classes are markedly different. More details on this optimized version of the linear discriminant can be found in [12].…”