Secure, Precise and Fast Sequential Pattern Mining with Learning Data Distribution

2023 Fiscal Year Final Research Report

• Project/Area Number: 21K17746
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 60080:Database-related
• Research Institution: Ochanomizu University (2023); Tokyo Institute of Technology (2021-2022)
• Principal Investigator: Le Hieu Hanh お茶の水女子大学, 文理融合 AI・データサイエンスセンター, 准教授 (60813996)
• Project Period (FY): 2021-04-01 – 2024-03-31
• Keywords: シーケンス解析 / 電子カルテ / データ保護

Outline of Final Research Achievements

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 hospital medical data on multiple diseases.
Then, an appropriate amount of noise is added to the original frequency to ensure privacy when estimating the frequency of the sequences. Only related data is added to the analysis based on data distribution and medical meaningfulness. Finally, a secure experimental environment using the cloud in which the data access control is carefully managed has been suggested for a secure data analysis.

Free Research Field

データ工学

Academic Significance and Societal Importance of the Research Achievements

この研究は、セキュアなシーケンシャルデータ解析に大きな波及効果をもたらす。これにより、医療や小売業など多くのビジネスにおいて、安全にカスタマイズ可能なツールやサービスを提供するアプリケーションの範囲が拡大できる。顧客向けのサービスや製品を安全にカスタマイズするだけでなく、産業企業内のサプライチェーン管理を効率的に最適化する可能性を見せることができる。