Research on Parameter Estimation of Hidden Markov Model with Differential Privacy
Nut Sornchumni (1251210)
Privacy is one of the main concerns in database query processing and data mining. In this research, I investigated about the adaptation of differential privacy framework, which is newly proposed privacy definition and privacy preserving mechanism, to the vastly used stateful data mining method, hidden Markov model(abbreviate as HMM).
First, the differential privacy framework will be briefly introduced.
Follows by the introduction of the method used to build the HMM that satisfied differential privacy framework.
Finally, the experimental evaluation of the proposed method's performance will be shown.