The The Use of Distance Blocks Representative to Avoid Empty Groups Due to Non-unique Medoids
Keywords:clustering, identical objects, accuracy
The existence of identical objects in a data set is a necessity. This paper proposes a new indicator and procedure to obtain the initial medoids. The new algorithm guarantees no empty groups and identical objects in the same group, either in the initial or final groups. We use six real data sets to evaluate the proposed method and compare the results of other methods in terms of adjusted Rand index and clustering accuracy. The experiment results show that the performance of the proposed method is comparable with other methods
Copyright (c) 2022 Kariyam Kariyam, Abdurakhman Abdurakhman, Adhitya Ronnie Effendie
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.