Predicting food quality using artificial intelligence
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 |
|
Project Period (FY) |
2018-04-01 – 2021-03-31
|
Project Status |
Completed (Fiscal Year 2020)
|
Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2020: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2018: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
Keywords | AI / 品質 / 食感 / イメージング / 構造 / 透明化 / グルテン / 可視化 / 人工知能 / 微細構造 / 麺 / 品質の予測 / 画像処理 / 品質推定 / 生理機能性 |
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.
|
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。
|
Report
(4 results)
Research Products
(6 results)