The K-means algorithm is commonly used with the Euclidean metric. While the use of Mahalanobis distances seems to be a straightforward extension of the algorithm, the initial estimation of covariance matrices can be complicated. We propose a novel approach for initializing covariance matrices.
Bibliographical noteFunding Information:
This research was supported in part by the Seed Grant of the Corporate Fund “ Fund of Social Development ” of Nazarbayev University.
Copyright 2020 Elsevier B.V., All rights reserved.
- K-means algorithm
- Mahalanobis distance