Cluster-based convolution process on big data in privacy preserving data mining. (28th October 2021)

• Record Type: Journal Article
• Authors: Lalitha, R.; Rameshkumar, K.
• Is Part Of: International journal of business information systems. Volume 38:Number 1(2021)
• Page Start: 17
• Page End: 33
• Publication Date: 2021-10-28
• Subjects: k-means clustering -- MapReduce -- privacy preserving -- K-nearest neighbour -- KNN; Information storage and retrieval systems -- Business -- Periodicals; Business -- Data processing -- Periodicals; Management information systems -- Periodicals; System design -- Periodicals; System analysis -- Periodicals; 651.8
• Languages: English
• ISSNs: 1746-0972

Abstract

The main intension of this paper is to privacy preserving-aware over big data in clouds using KNN and MapReduce framework. This paper consists of three phases such as, MapReduce phase, clustering the map reduced data and evaluation phase. In MapReduce phase, we are splitting the input data after the splitting process we are including a k-means clustering algorithm to cluster the map reduced data. Then, we are performing a convolution process to the dataset and create a new matrix. Once it is over, the privacy-persevering framework over big data in cloud systems is performed based on the evaluation base. In evaluation module, deduplication is performed with the aid of the KNN algorithm. In this phase using the KNN technique to check the duplication of data based on the threshold. Thus the non-duplicated data's are stored in cloud database, which is improving the utility of the privacy data.