PRIVACY PRESERVING USING ENSEMBLE CLASSIFICATION FOR HEART DISEASE DATA SETS

SHANMUGAPRIYA G

Abstract


In this modern era of thriving technology, the data being gathered through way of private in addition to public businesses is increasing each day. But in recent times people are more worried about their data and privateness being preserved at the same time as use of their data in other analysis purpose. Thus Privacy-Preserving Data Mining (PPDM) method has been proposed to permit the extraction of understanding from data at the same time as keeping the privateness of people. The primary purpose of our project is on preserving privacy for healthcare records as privateness lacks in Medical data. Privacy-Preserving Data Mining (PPDM) offers with shielding the privacy of individual’s data or sensitive data without the utility of data. Therefore the strategies like anonymization, randomization are used to attain the intention. However, unfortunately anonymization results in certain level of information loss while preserving privacy. In order to overcome this problem, perturbation technique is carried out. Our challenge initiates with cleaning and preprocessing followed by ensemble classification and proceeded with perturbation to attain the goal. This method focuses on preserving privacy by perturbing the sensitive attributes in the Medical data without causing loss to the information in the process

Keywords


Data mining, adaboost, perturbation technique, noise generation.

Full Text:

PDF

References


Mehmet Emre Gursoy, Ali Inan, Mehmet Ercan Nergiz, and Yucel Saygin , ” Privacy-Preserving learning analytics: challenges and techniques” , IEEE transactions on learning technologies, vol. 10, no. 1, january-march 2017 , pp 68-81

Jasmina D. Novakovic, Alempije Veljovic, “AdaBoost as Classifier Ensemble in Classification Problems”, INFOTEH-JAHORINA Vol. 13, March 2014, pp616-620.

Arshveer Kaur, “A Hybrid Approach of Privacy Preserving Data Mining using Suppression and Perturbation Techniques”, International Conference on Innovative Mechanisms for Industry Applications (ICIMIA 2017), pp306-311

Hamirpur, Hamirpur,” International Journal of Computing, Communications and Networking” volume 4 No.1,January-march 2015

R.Kalaivani ,S.Chidambaram, “additive gaussian noise based data perturbation in multi-level trust privacy preserving data mining”, International Journal of Data Mining & Knowledge Management Process (IJDKP) Vol.4, No.3, May 2014

Hillol Kargupta,Souptik Datta1,Qi Wang, Krishnamoorthy Sivakumar , “Random-data perturbation techniques and privacy-preserving data mining” , Springer-Verlag London Ltd.  2004 Knowledge and Information Systems (2005) 7: 387–414 , pp 318-414

Roman I. Batygin, Olga K. Alsova , ” Software System for Different Types of Data Classification Based on the Ensemble Algorithms” , 2016 13th International Scientific-Technical Conference APEIE – 39281 , pp 506-509

K. Usha Rani,” Analysis of heart diseases dataset using neural network approach”, International Journal of Data Mining & Knowledge Management Process (IJDKP) Vol.1, No.5, September 2011




DOI: https://doi.org/10.26483/ijarcs.v9i2.5777

Refbacks

  • There are currently no refbacks.




Copyright (c) 2018 International Journal of Advanced Research in Computer Science