| 研究実績の概要 |
This study aims to present a method for eliminating the need for trust in sequential pattern mining while preserving privacy and providing secure, precise, and fast sequential data analysis that carefully learns the data distribution.
Secure sequential data analysis of sequential medical data has been extensively studied. In detail, several methods to analyze the sequence variants (SV) from more than one hospital have been designed, such as comparing SVs, identifying factors that led to branches in SVs, etc. The proposed methods were rigorously evaluated using real medical data from more than 20 hospitals focusing on multiple diseases. As shown to be highly effective, the methods can be expected to be applied to other sequential data types.
Then, an appropriate amount of noise is added to the original frequency to ensure privacy when estimating the frequency of the sequences. Based on data distribution, only related data is added to the analysis to speed up the analysis while preserving high utility.
Finally, the sensitive medical data was analyzed securely with careful access control management to enhance privacy.
|
