• Shailaja B N

As one essential approach of fuzzy clustering in statistics mining and pattern recognition, the possibilistic c-method set of rules (PCM) has been broadly used in photo evaluation and understanding discovery. However, it is tough for PCM to produce a good result for clustering large records, particularly for heterogenous information, considering that it is first of all designed for best small dependent dataset. To address this trouble, the paper proposes a excessive-order PCM algorithm (HOPCM) for huge records clustering by means of optimizing the goal function within the tensor area. Further, we design a allotted HOPCM approach based on MapReduce for extremely big amounts of heterogeneous statistics. Finally, we devise a privacy-maintaining HOPCM set of rules (PPHOPCM) to protect the non-public statistics on cloud by using making use of the BGV encryption scheme to HOPCM, In PPHOPCM, the capabilities for updating the club matrix and clustering centers are approximated as polynomial capabilities to guide the steady computing of the BGV scheme. Experimental effects suggest that PPHOPCM can efficiently cluster a big quantity of heterogeneous statistics the usage of cloud computing without disclosure of private statistics.

Big Data Clustering, Cloud computing, Privacy preserving, Possibility c-Means, Tensor space

"PPHOPCM:Privacy preserving on high order possibilistic c- Means Algorithm for Bigdata Clustering with Cloud Computing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 8, page no.d151-d154, August-2021, Available :http://www.jetir.org/papers/JETIR2108389.pdf

"PPHOPCM:Privacy preserving on high order possibilistic c- Means Algorithm for Bigdata Clustering with Cloud Computing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 8, page no. ppd151-d154, August-2021, Available at : http://www.jetir.org/papers/JETIR2108389.pdf