Abstract—Cluster analysis of heterogeneous data has a wide
range of applications, which is an important basic method of
big data mining, and is also a hot research topic in the field of
information sharing. In order to improve the Cluster analysis
effect of massive heterogeneous data, two pretreatment steps,
data preparation and dimensionality reduction, are adopted in
this paper. Firstly, irrelevant elements are eliminated to reduce
the computation of Cluster analysis of heterogeneous data
resources. Then, FCM Cluster analysis concept is introduced to
cluster analysis based on membership matrix of Euclidean
distance. Finally, the grey prediction model is used to predict
and analyze the data. Cluster analysis efficiency of massive
heterogeneous data has important reference value for massive
data mining in the era of big data.
Index Terms—Heterogeneous data, FCM, cluster analysis.
Xiaotao Xu is with Institute of Information and Communication, Wuhan,
China (e-mail: superxxt@163.com).
[PDF]
Cite:Xiaotao Xu, "Research on Cluster Analysis Method of Heterogeneous Data Resources Based on FCM," International Journal of Information and Electronics Engineering vol. 9, no. 2, pp. 54-58, 2019.