Risk immunizing informatics for learning and preventing fatal injury situations in daily environments

2021 Fiscal Year Final Research Report

• Project/Area Number: 20K21052
• Research Category: Grant-in-Aid for Challenging Research (Exploratory)
• Allocation Type: Multi-year Fund
• Review Section: Medium-sized Section 25:Social systems engineering, safety engineering, disaster prevention engineering, and related fields
• Research Institution: Tokyo Institute of Technology
• Principal Investigator: Yoshifumi Nishida 東京工業大学, 工学院, 教授 (60357712)
• Project Period (FY): 2020-07-30 – 2022-03-31
• Keywords: 免疫学 / 機械学習 / 安全工学 / 小児安全 / 傷害予防 / 状況認識 / 行動モデル / 疫学

Outline of Final Research Achievements

The biological immune systems of organisms respond to new sources of risk that arise in everyday life. This study proposes the concept of a societal immunization system in which the effective function of an immune system providing protection from pathogens is applied to protection from the risk of fatal accident in the living environment. To confirm the feasibility of the concept, we focus on problems of child fatalities. This study developed a prototype system of a societal immunization system for living safety. The developed system consists of knowledge graphs for explaining dangerous situations, an online video capturing part, and a situation recognition part. the feasibility and effectiveness of the system was evaluated through tests among parents and kindergarten carers. The system allows the lecturer to conduct in situ suggestion on specific preventive measures adapted to the home environment via online learning.

Free Research Field

人間情報学、安全工学、機械工学、人工知能

Academic Significance and Societal Importance of the Research Achievements

事故という現実問題解決を行う上での技術的課題は、因果データ取得困難性、状況多様性を扱うことの困難性、ポアソン分布的挙動による限界の３つの困難性があり、従来のリスクマネジメントでは対応できない問題に対する、人と人工知能との協調時代に適合した新たな動的分散制御の方法論が求められている。これに対し、本研究では、免疫の持つ仕組みを、事故予防の分野に適用し、数理的・目的指向的に再現することで、３つの問題を解決した新しいアプローチ「リスク免疫情報学」確立を本研究の長期的な狙いとして、ビッグデータ保有機関との連携によるデータサイエンスの検証、保育所との連携による基本検証を進めた。