点击次数：

论文类型：期刊论文

发表时间：2017-09-20

发表刊物：NEUROCOMPUTING

收录刊物：SCIE、EI、Scopus

卷号：256

期号：,SI

页面范围：82-89

ISSN号：0925-2312

关键字：Nuero-fuzzy c-means; Cloud computing; Heterogeneous data; Internet of Things; BGV

摘要：Currently, massive heterogeneous data is generating from the Internet of Things (IoT). Heterogeneous data processing with the neuro-fuzzy technology has become a hot topic for IoT. In this work, we propose a privacy-preserving high-order neuro-fuzzy c-means algorithm for clustering heterogeneous data (PPHOFCM) on cloud computing. PPHOFCM clusters the heterogeneous data set by representing each heterogeneous data object as a tensor and uses the tensor distance to capture the correlations in the high order tensor space. Furthermore, the cloud computing is employed to improve the clustering efficiency for massive heterogeneous data from IoT. The BGV encryption scheme is used to protect the private data when performing the high-order neuro-fuzzy c-means algorithm on cloud computing. Experiments are conducted on two real IoT datasets to verify the proposed algorithm. (C) 2017 Elsevier B.V. All rights reserved.