Privacy Preservation using (L, D) Inference Model Based on Dependency Identification Information Gain
R. Deepika1, V. Divya2, C. Yamini3, P. Sobiyaa4
1R. Deepika, Assistant Professor, Bannari Amman Institute of Technology, (Tamil Nadu), India.
2V. Divya, Assistant Professor, Bannari Amman Institute of Technology, (Tamil Nadu), India.
3C. Yamini, Assistant Professor, Bannari Amman Institute of Technology, (Tamil Nadu), India.
4P. Sobiyaa, Assistant Professor, Bannari Amman Institute of Technology, (Tamil Nadu), India.
Manuscript received on 28 September 2019 | Revised Manuscript received on 10 November 2019 | Manuscript Published on 22 November 2019 | PP: 1170-1173 | Volume-8 Issue-6S3 September 2019 | Retrieval Number: F11960986S319/19©BEIESP | DOI: 10.35940/ijeat.F1196.0986S319
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The improvement of an information processing and Memory capacity, the vast amount of data is collected for various data analyses purposes. Data mining techniques are used to get knowledgeable information. The process of extraction of data by using data mining techniques the data get discovered publically and this leads to breaches of specific privacy data. Privacypreserving data mining is used to provide to protection of sensitive information from unwanted or unsanctioned disclosure. In this paper, we analysis the problem of discovering similarity checks for functional dependencies from a given dataset such that application of algorithm (l, d) inference with generalization can anonymised the micro data without loss in utility. [8] This work has presented Functional dependency based perturbation approach which hides sensitive information from the user, by applying (l, d) inference model on the dependency attributes based on Information Gain. This approach works on both categorical and numerical attributes. The perturbed data set does not affects the original dataset it maintains the same or very comparable patterns as the original data set. Hence the utility of the application is always high, when compared to other data mining techniques. The accuracy of the original and perturbed datasets is compared and analysed using tools, data mining classification algorithm.
Keywords: Anonymization, Classification, Functional Dependency Attributes, Gain Ratio Index, (l,d) Inference Model, Privacy Preservation Data Mining, Perturbation.
Scope of the Article: Information-Centric Networking