| 研究課題/領域番号 |
21K17746
|
|---|
| 研究機関 | 東京工業大学 |
|---|
研究代表者 |
Le Hieu・Hanh 東京工業大学, 情報理工学院, 助教 (60813996)
|
|---|
| 研究期間 (年度) |
2021-04-01 – 2024-03-31
|
| キーワード | privacy / data mining / differential privacy / recommendation |
|---|
| 研究実績の概要 |
This study aims to present a method for eliminating the need for trust in sequential pattern mining (SPM) while preserving privacy and providing secure, precise, and fast sequential data analysis which carefully learns the data distribution.
The fundamental algorithms of sequential data analysis on sequential medical data without privacy-preserving have been studied this year. In detail, utilizing SPM with clustering, the research extracts and compares the clinical pathways from multiple hospitals and discovers the association rules used for specimen inspection recommendations.
These algorithms will be used as base methods for evaluating the effectiveness of the privacy-preserving SPM in the following years.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
3: やや遅れている
理由
Due to the spread of COVID19 and the shortage of semiconductors, the preparation of medical data from multiple hospitals and the delivery of the server were delayed. Therefore, the evaluation of the proposed privacy-preserving analysis algorithm could not be performed on time.
|
| 今後の研究の推進方策 |
In the following year, as the experimental environment and the fundamental analyzing methods were already constructed, the privacy-preserving analysis will be evaluated. At the same time, a method to further reduce the mining time will be proposed and evaluated.
|
| 次年度使用額が生じた理由 |
Due to the spread of the COVID19 infection, it was not possible to make oeversea and domestic business trips. Therefore, the expenses for travel and conference participation fees were carried over to the next year.
|
