A note on the separability index

TL;DR

This paper discusses the limitations of the existing separability index (SI) used to measure class separability in classification tasks and proposes a modified measure that combines SI with another separability metric.

Contribution

It introduces a slight variation to the separability index by integrating it with an additional measure to better capture class separability.

Findings

Identified limitations of the original separability index

Proposed a combined separability measure with improved interpretability

Enhanced the measure's ability to quantify class separability

Abstract

In discriminating between objects from different classes, the more separable these classes are the less computationally expensive and complex a classifier can be used. One thus seeks a measure that can quickly capture this separability concept between classes whilst having an intuitive interpretation on what it is quantifying. A previously proposed separability measure, the separability index (SI) has been shown to intuitively capture the class separability property very well. This short note highlights the limitations of this measure and proposes a slight variation to it by combining it with another form of separability measure that captures a quantity not covered by the Separability Index.