Right-Protected Data Publishing With Provable Distance-Based Mining: A Survey |
Author(s): |
S. Mythili , GOBI ARTS AND SCIENCE COLLEGE; Dr. V. Thiagarasu, GOBI ARTS AND SCIENCE COLLEGE |
Keywords: |
Data Publishing, Right-protection, Watermarking techniques, NN (Nearest Neighbors) – preserving |
Abstract |
Data exchange and data publishing are becoming an essential part of business and academic practices and data owners need to maintain the principal rights over the concern datasets that they share. This survey reviews the right-protection mechanism that can provide detectable evidence for the legal ownership of a shared dataset, without compromising its usability under wide range of machine learning, mining and search operations. The watermarking preservation algorithms protect important properties of the dataset which are essential for mining operations and so guarantee both right protection and utility preservation. It proves fundamental lower and upper bounds on the distance between objects. In particular, it establishes a restricted isometric property, i.e., tight bounds on the expansion of original distances. The review of various methods is discussed to assess the quality and reliability of right-protection mechanisms. From the survey it is observed that the right-protection mechanism based on watermarking technique has good efficiency and better capability for upgrading the best approach and helps to overcome the problems by analyzing and focusing the components of watermarking preservation algorithms. This analysis used to design fast algorithms for NN (Nearest Neighbors)-preserving watermarking that drastically prunes the vast search space. Then the performances of various existing watermarking algorithms are discussed and also the limitations of object distance validation are discussed. |
Other Details |
Paper ID: IJSRDV3I60431 Published in: Volume : 3, Issue : 6 Publication Date: 01/09/2015 Page(s): 1099-1103 |
Article Preview |
|
|