Open AccessPrivacy Preservation Using (L, D) Inference Model Based On Dependency Identification Information Gain
Author(s) -
R. Deepika,
V. Divya,
C Yamini,
P. Sobiyaa
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.f1196.0986s319
Subject(s) - computer science , data mining , inference , dependency (uml) , generalization , categorical variable , information extraction , information loss , functional dependency , personally identifiable information , identification (biology) , data set , set (abstract data type) , information sensitivity , machine learning , information retrieval , artificial intelligence , relational database , mathematics , mathematical analysis , botany , computer security , biology , programming language
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.