Improved Hierarchical K-means Clustering Algorithm without Iteration Based on Distance Measurement - Intelligent Information Processing VII (IIP 2014) Access content directly
Conference Papers Year : 2014

Improved Hierarchical K-means Clustering Algorithm without Iteration Based on Distance Measurement

Abstract

Hierarchical K-means has got rapid development and wide application because of combining the advantage of high accuracy of hierarchical algorithm and fast convergence of K-means in recent years. Traditional HK clustering algorithm first determines to the initial cluster centers and the number of clusters by agglomerative algorithm, but agglomerative algorithm merges two data objects of minimum distance in dataset every time. Hence, its time complexity can not be acceptable for analyzing huge dataset. In view of the above problem of the traditional HK, this paper proposes a new clustering algorithm iHK. Its basic idea is that the each layer of the N data objects constructs $\lceil{{N}\over{2}} \rceil $ clusters by running K-means algorithm, and the mean vector of each cluster is used as the input of the next layer. iHK algorithm is tested on many different types of dataset and excellent experimental results are got.
Fichier principal
Vignette du fichier
978-3-662-44980-6_5_Chapter.pdf (99.7 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01383315 , version 1 (18-10-2016)

Licence

Attribution

Identifiers

Cite

Wenhua Liu, Yongquan Liang, Jiancong Fan, Zheng Feng, Yuhao Cai. Improved Hierarchical K-means Clustering Algorithm without Iteration Based on Distance Measurement. 8th International Conference on Intelligent Information Processing (IIP), Oct 2014, Hangzhou, China. pp.38-46, ⟨10.1007/978-3-662-44980-6_5⟩. ⟨hal-01383315⟩
273 View
664 Download

Altmetric

Share

Gmail Facebook X LinkedIn More