| Project/Area Number |
16K07972
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Agricultural environmental engineering/Agricultural information engineering
|
|---|
| Research Institution | Kochi University |
|---|
Principal Investigator |
KAWANO Toshio 高知大学, 教育研究部自然科学系農学部門, 教授 (60224812)
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2016: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
|
|---|
| Keywords | 食品の異物検出 / 非金属異物 / 生物系異物 / 近赤外分光法 / 異物検出 / 近赤外 / 検出法 / 食品 / 異物 / 検出 |
|---|
| Outline of Final Research Achievements |
In order to detect the extraneous materials mixed in food with non-destructive ways, a method using near-infrared spectroscopy was proposed. Frozen hamburg patty and croquette samples were taken as a target foods for preventing from mixture of extraneous materials, and 11 kinds of extraneous materials including of non-metal and biological were adopted as the contaminant. Spectra data of 1) food mixed with no extraneous materials, 2) extraneous materials, and 3) food mixed with extraneous materials were measured, and specific wave lengths for discriminating between foods and extraneous materials were selected. Then, a neural network base model was constructed for detecting if extraneous materials are mixed in foods or not. The degree of accuracy of the model was ranged from 82% to 95%.
|
| Academic Significance and Societal Importance of the Research Achievements |
食品への異物混入は国民にとってきわめて不快な事象であり、我が国の食品の安全・安心を揺るがす大きな社会問題である。食品生産の段階での異物検出では、生産機械の欠損によって生じた金属片や硬質プラスチックをＸ線で検出する方法が利用されているが、その他の非金属異物や生物系異物の検出は困難である。そこで本研究では食品に光を照射し、その反射光に含まれる近赤外域の情報から、異物が混入しているかどうかを判定する手法について検討した。AI(人工知能)型の異物混入判定を行うもので、結果的に、その異物混入の推定精度は82%から95%であった。
|
