Abstract

The collection and effectiveness of sensitive Big Data have grown with Information Technology (IT) development. While using sensitive Big Data to acquire relevant information, it becomes indispensable that irrelevant sensitive data are reduced to safeguard personal information in healthcare sector. Many privacy-preserving strategies have been applied in the recent years using quasi-identifiers (QI) for applications like health services. However, privacy preservation over quasi-identifiers is still challenging in the context of Big Data because most datasets were of huge volume. Existing methods suffer from higher time consumption and lower data utility because of dynamically progressing datasets. In this paper, an efficient Distinctive Context Sensitive and Hellinger Convolutional Learning (DCS-HCL) is introduced to ensure privacy preservation and achieve high data utility for big healthcare datasets. First, Distinctive Impact Context Sensitive Hashing model is designed for the given input Big Dataset where both the distinctive and impact values are identified and applied to Context Sensitive Hashing. With this, similar QI-classes are mapped to evolve the computationally efficient anonymyzed data. Second, Hellinger Convolutional Neural Privacy Preservation model is presented to preserve the privacy of the sensitive unstructured data. This is performed by hashing QI-class values, weight updation and bias in CNN to increase the accuracy and to reduce the information loss. Evaluation results demonstrate that with proposed method with large-volume unstructured datasets improved performance of run time, data utility, information loss and accuracy significantly over existing methods.

Highlights

  • Privacy-preservation issues have made an appearance with the growing magnitudes of data being issued together with sensitive, private information pertaining to individual persons and business establishments

  • In this work, Distinctive Impact Context Sensitive Hashing model is designed that evolves with computationally efficient quasi-identifiers with minimal time and higher data utility

  • The quasi-identifiers is used in big healthcare datasets to ensure the privacy requirements and to achieve high data utility simultaneously with minimum run time and information loss

Read more

Summary

INTRODUCTION

Privacy-preservation issues have made an appearance with the growing magnitudes of data being issued together with sensitive, private information pertaining to individual persons and business establishments. Despite maintaining privacy and reducing the running time with the absence of strong data-anonymization models, data utility was not focused To address this issue, in this work, Distinctive Impact Context Sensitive Hashing model is designed that evolves with computationally efficient quasi-identifiers with minimal time and higher data utility. A sensitive QID using ldiversity and t-closeness was designed It was in novel privacy model, anonymization and reconstruction was possible while maintaining the high quality of data within stipulated time period. Though high data quality within stipulated time period was maintained, the accuracy and information loss was not concentrated To address this issue in this work, Hellinger Convolutional Neural Privacy Preservation model is proposed to protect both the sensitive data by designing a significant privacy preservation model considering both the distance by means of Hellinger and improving the accuracy by updated weight and bias via convolutional neural learning

Contributions
Organization Structure
RELATED WORKS
Research Gap
METHODOLOGY
System Model
Distinctive Impact Context Sensitive Hashing Model
Hellinger Convolutional Neural Privacy Preservation Model
EXPERIMENTAL ANALYSIS
Dataset Description
RESULT
Performance Measure of Run Time
Performance Measure of Accuracy
Performance Measure of Information Loss
Findings
CONCLUSION
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call