Predicting food quality using artificial intelligence

2020 Fiscal Year Final Research Report

• Project/Area Number: 18K14421
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 38050:Food sciences-related
• Research Institution: Kyoto University
• Principal Investigator: Ogawa Takenobu 京都大学, 農学研究科, 助教 (10793359)
• Project Period (FY): 2018-04-01 – 2021-03-31
• Keywords: ＡＩ / 品質 / 食感 / イメージング / 構造

Outline of Final Research Achievements

The purpose of this study was to establish an academic method for freely controlling the quality of processed foods, including the feeling of eating and physiological functionality, by logically determining the food material, processing method and conditions according to the processed food. The particularly remarkable results obtained in this study can be summarized in the following three points: 1) Established a novel technology to measure the internal structure of food that changes according to processing with high accuracy and high speed. 2) Made it possible to predict quality such as texture using artificial intelligence based on the structure measured using the developed technology. 3) Elucidated a part of the mechanism by which structure controls quality by back-analyzing artificial intelligence.

Free Research Field

食品工学

Academic Significance and Societal Importance of the Research Achievements

食品の内部構造と五感での受感などの関係は、これまで推論の域を出なかったが、人工知能を用いることで直接的に解明できることを実証した点に本研究の学術的な意義がある。これまでの工業的な食品製造では、限られたデータと経験的な知見を基に試行錯誤的に加工方法や条件を決めてきたが、これが論理的に決定できるようになることは重要である。より美味しく、かつ一層の健康の維持が可能な加工食品を開発・製造していくことはあくなき人類の欲望であるが、本研究の遂行により、食を通した人生の楽しみを失うことなく、健康の維持・改善が将来的に可能になる点に社会的な意義がある。