Distributed threshold k-means clustering for privacy preserving data mining
Vadlana Baby, N. Subhash Chandra · 2016
Privacy preserving is important in wherein data mining turns into a cooperative assignment among members. In data mining, a standout amongst the most capable and often utilized systems is k-means clustering. In this paper, we propose an efficient distributed threshold privacy-preserving k-means clustering algorithm that use the code based threshold secret sharing as a privacy-preserving mechanism. Construction involves code based approach which allows the data to be divided into multiple shares and processed separately at different servers. Our protocol takes less number of iterations compare with existing protocols and it do not require any trust among the servers or users. We also provide experiment results with comparison and security analysis of the proposed scheme.