Classification with Nearest Disjoint Centroids

TL;DR

This paper introduces a novel classification method called the nearest disjoint centroid classifier, which uses feature-disjoint centroids and a normalized distance measure, demonstrating improved accuracy and feature efficiency over existing methods.

Contribution

The paper proposes a new classification approach with disjoint feature centroids and a normalized distance, along with an algorithm for feature subset selection and theoretical analysis.

Findings

Outperforms other classifiers in misclassification rates

Uses fewer features while maintaining accuracy

Effective on both simulated and real gene expression data

Abstract

In this paper, we develop a new classification method based on nearest centroid, and it is called the nearest disjoint centroid classifier. Our method differs from the nearest centroid classifier in the following two aspects: (1) the centroids are defined based on disjoint subsets of features instead of all the features, and (2) the distance is induced by the dimensionality-normalized norm instead of the Euclidean norm. We provide a few theoretical results regarding our method. In addition, we propose a simple algorithm based on adapted k-means clustering that can find the disjoint subsets of features used in our method, and extend the algorithm to perform feature selection. We evaluate and compare the performance of our method to other classification methods on both simulated data and real-world gene expression datasets. The results demonstrate that our method is able to outperform other competing classifiers by having smaller misclassification rates and/or using fewer features in various settings and situations.