A Comparative Analysis of the Study of Optimization Schemes for K-Means Algorithm Clustering Centers in High-Dimensional Data

DOI

10.2991/assehr.k.220701.028How to use a DOI?

Keywords

Clustering algorithms; K-means algorithm; initial clustering centres; centre optimization; high-dimensional data

Abstract

As an important concept of artificial intelligence in the field of information mining and in the broader field of deep learning, clustering analysis has attracted a large number of researchers to think about and improve its research methods, application areas and disadvantage optimization to different degrees. The traditional K-means clustering algorithm suffers from the fact that the number of clusters required needs to be determined artificially, and therefore the clustering results can be influenced by the different initial cluster centers, and the computational complexity of the clustering iteration process. Especially when processing multi-dimensional or high-dimensional data, the number of iterations, the computational complexity and the long running time can affect the effectiveness and accuracy of the algorithm. Different researchers have proposed optimization solutions for this drawback based on different priorities. This paper provides a comparative analysis of these schemes to explore their feasibility and advantages and disadvantages.

Copyright

© 2022 The Authors. Published by Atlantis Press SARL.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license.

Download article (PDF)

TY  - CONF
AU  - Jinglu Tian
PY  - 2022
DA  - 2022/07/04
TI  - A Comparative Analysis of the Study of Optimization Schemes for K-Means Algorithm Clustering Centers in High-Dimensional Data
BT  - Proceedings of the 2022 International Conference on Science and Technology Ethics and Human Future (STEHF 2022)
PB  - Atlantis Press
SP  - 138
EP  - 142
SN  - 2352-5398
UR  - https://doi.org/10.2991/assehr.k.220701.028
DO  - 10.2991/assehr.k.220701.028
ID  - Tian2022
ER  -