Abstract
In cross bucket generalization, divide micro-data into equivalence teams and buckets. First, it provides separate protection for identity and sensitive values, and therefore the level of protection may be flexibly adjusted supported actual demands. Second, the sizes of equivalence teams and buckets are reduced as way as potential by solely satisfying the protection needs, that avoid the over shielding for identity and cut back data loss. Most duplicates are detected by progressive duplicate detection. Rather than reducing the general time required to end the whole method, progressive approaches try and scale back the typical time when that a replica is found. To discover the duplicity with less time of execution and additionally while not perturbing the dataset quality, strategies like concurrent Progressive blocking and concurrent Progressive Neighborhood are used. Progressive sorted neighborhood technique conjointly known as CC-PSNM is employed during this model for locating or sleuthing the duplicate during a parallel approach.
Keywords
Data mining
Data bucketization
Concurrent Progressive Blocking
Concurrent sorted neighborhood
Privacy Data
Generalization
Cross Bucket.
Authors
How to Cite this Article
S. Menaka, M.M. Kavitha (2019).
"EFFICIENT PRIVACY PRESERVATION FOR MICRO-DATA APPLICATION USING CROSS-BUCKET WITH PROGRESSIVE DUPLICATE DETECTION MODEL".
International Journal of Contemporary Research in Computer Science and Technology,
5(3), pp. 19-24.
