Incremental clustering algorithm based on representative points and covariance for large data
by Jiayao Li; Qiannan Wu; Li Li; Ruizhi Sun; Huiyu Mu; Kaiyi Zhao
International Journal of Simulation and Process Modelling (IJSPM), Vol. 20, No. 2, 2023

Abstract: As the dynamic data increases, more space is needed to store the data. However, most traditional clustering methods are time-consuming and only suitable for static data. For this problem, incremental clustering methods are increasingly used in dynamic data. The study proposes an incremental clustering algorithm based on representative points and covariance for large data (IDPC_RC). Firstly, the representative points were selected in the initial data. Then, the similarity between new data points and representative points was calculated to find the pre-allocated cluster. Finally, the covariance determinant was used to measure the degree of local imbalance for pre-allocated clusters after new data is added, and the cluster numbers were adjusted adaptively. The performance of the proposed scheme was tested on five benchmark datasets and real consumption data. The experimental results show the scheme achieves excellent clustering performance and low time consumption on all datasets, which is useful for incremental clustering tasks.

Online publication date: Fri, 02-Feb-2024

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Simulation and Process Modelling (IJSPM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com