A SURVEY ON PRIVACY PRESERVATIONTECHNIQUES FOR DATA CLUSTERING K-MEANS OVER LARGE-SCALE DATASET

challa srihitha, A Sai Hanuman

Abstract


Cloud computing supports different handling of Big-Data applications in such divisions like human services and Sports and so on. Data sets like electronic well being records is regularly contain protection touchy data, which achieves security concerns possibly if the data is discharged/shared to outsiders in cloud. A functional and broadly received procedure for protection safeguarding is to anonymize information by means of speculation to fulfill a given security demonstrates. In this paper, we propose a viable security safeguarding K-implies grouping plan that can be effectively outsourced to cloud servers. The present work permits cloud servers to perform bunching specifically finished encoded data sets, while achieving comparable computational complexity and accuracy compared with clusters over unencrypted ones. In addition to existing techniques, Map Reduce approach also combined in this paper, which makes this work greatly appropriate for Map Reduce condition. Deferentially security approach ensures the results of questions to a database, which will expand the versatility and time proficiency over existing methodologies.

Keywords


Cloud Computing, Big data, MapReduce, Data Anonymization, K-means algorithm

Full Text:

PDF


DOI: https://doi.org/10.26483/ijarcs.v9i1.5235

Refbacks

  • There are currently no refbacks.




Copyright (c) 2018 International Journal of Advanced Research in Computer Science