Reinforced Social Ant with Discrete Swarm Optimizer for Sensitive Item and Rule Hiding
P. Tamil Selvan

Dr. P. TamilSelvan, Assistant Professor in Department of Computer Science, Karpagam Academy of Higher Education, Coimbatore.
Manuscript received on 26 June 2019 | Revised Manuscript received on 05 July 2019 | Manuscript published on 30 July 2019 | PP: 902-908 | Volume-8 Issue-9, July 2019 | Retrieval Number: I7816078919/19©BEIESP | DOI: 10.35940/ijitee.I7816.078919

Open Access | Ethics and 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 (

Abstract: In data mining Privacy Preserving Data mining (PPDM) of the important research areas concentrated in recent years which ensures ensuring sensitive information and rule not being revealed. Several methods and techniques were proposed to hide sensitive information and rule in databases. In the past, perturbation-based PPDM was developed to preserve privacy before use and secure mining of association rules were performed in horizontally distributed databases. This paper presents an integrated model for solving the multi-objective factors, data and rule hiding through reinforcement and discrete optimization for data publishing. This is denoted as an integrated Reinforced Social Ant and Discrete Swarm Optimization (RSA-DSO) model. In RSA-DSO model, both Reinforced Social Ant and Discrete Swarm Optimization perform with the same particles. To start with, sensitive data item hiding is performed through Reinforced Social Ant model. Followed by this performance, sensitive rules are identified and further hidden for data publishing using Discrete Swarm Optimization model. In order to evaluate the RSA-DSO model, it was tested on benchmark dataset. The results show that RSA-DSO model is more efficient in improving the privacy preservation accuracy with minimal time for optimal hiding and also optimizing the generation of sensitive rules.
Keywords: Privacy Preserving Data Mining, Perturbation-Based, Data and Rule Hiding, Reinforcement, Discrete Optimization.

Scope of the Article: Data Mining