Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, EpiSciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Abstract : K-means is a classic, the division of the clustering algorithm, apply to the classification of the globular data. According to the initial clustering center, this paper comprehensive consideration the characteristics of various Hierarchical cluster algorithms and choose the appropriate Hierarchical cluster algorithm to improve K-means, and combined with Hainan Green Tangerine Peel cluster analysis of data which is compared experiments. The results indicate that the improved algorithm have increasing the distance between classes with each others, get a stable of cluster results and better implementation data mining. Finally to summary the two algorithms and the further research direction.
https://hal.inria.fr/hal-01342139 Contributor : Hal IfipConnect in order to contact the contributor Submitted on : Tuesday, July 5, 2016 - 2:39:06 PM Last modification on : Wednesday, July 6, 2016 - 10:09:17 AM
ying Luo, Haiyan Fu. Modified K-means Algorithm for Clustering Analysis of Hainan Green Tangerine Peel. 13th Conference on e-Business, e-Services and e-Society (I3E), Nov 2014, Sanya, China. pp.144-150, ⟨10.1007/978-3-662-45526-5_14⟩. ⟨hal-01342139⟩