2018 Fiscal Year Final Research Report
Study on freshness estimation of fruit and vegetable using general-purpose devices
| Project/Area Number |
17K20034
|
|---|
| Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Applied informatics and related fields
|
|---|
| Research Institution | Ritsumeikan University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
井尻 敬 芝浦工業大学, 工学部, 准教授 (30550347)
|
|---|
| Project Period (FY) |
2017-06-30 – 2019-03-31
|
| Keywords | 食物 / 鮮度 / 汎用センサ / 機械学習 / トマト / リンゴ / みかん |
|---|
| Outline of Final Research Achievements |
The goal of this study is to develop a new technique for estimating conditions of fruits (e.g. firmness and storage time) by using small and common sensors. Key idea is to use sound signal; we hit a linear sweep signal to a target fruit by using a small speaker and capture a reflected signal with a small microphone. We collect reflected signals from fruits in various conditions and use it to perform regression. In this study, we have performed various experiments. For instance, we collected reflected signals of tomatoes, mandarin oranges and apples to estimate their firmness and storage time. We conducted cross validation for the collected dataset and found relatively accurate estimation results. We recently found some results indicating a possibility that conditions of our measurement devices had an influence to the estimation results. We are continuing experiments to clarify this point.
|
| Free Research Field |
信号処理
|
| Academic Significance and Societal Importance of the Research Achievements |
鮮度・硬さ・食べごろといった果物の状態は，農業従事者だけでなく，一般消費者にとっても重要な関心ごとであり，農作物の状態を手軽に計測できるツールの需要は少なくない．本研究課題は，小型スピーカー・小型マイクといった安価な汎用センサのみで，果物の状態を推定できるシステムの実現を目指している．2年の研究期間中に蓄えた実験結果やノウハウに基づき，今後さらに実験を実施する予定である．本研究課題が実現できれば，果物の貯蔵日数や硬さを手軽に推定できるようになり，その社会的な意義は大きい．
|
