papers AI Learner
The Github is limit! Click to go to the new site.

TiK-means: $K$-means clustering for skewed groups

2019-04-21
Nicholas S. Berry, Ranjan Maitra

Abstract

The $K$-means algorithm is extended to allow for partitioning of skewed groups. Our algorithm is called TiK-Means and contributes a $K$-means type algorithm that assigns observations to groups while estimating their skewness-transformation parameters. The resulting groups and transformation reveal general-structured clusters that can be explained by inverting the estimated transformation. Further, a modification of the jump statistic chooses the number of groups. Our algorithm is evaluated on simulated and real-life datasets and then applied to a long-standing astronomical dispute regarding the distinct kinds of gamma ray bursts.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.09609

PDF

http://arxiv.org/pdf/1904.09609


Similar Posts

Comments