Study for IoT and Big-data in smart agriculture to predict future harvest
Project/Area Number |
15K00164
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Multimedia database
|
Research Institution | Numazu National College of Technology |
Principal Investigator |
Yamazaki Satoshi 沼津工業高等専門学校, 制御情報工学科, 准教授 (80635889)
|
Co-Investigator(Kenkyū-buntansha) |
切岩 祥和 静岡大学, 農学部, 教授 (50303540)
|
Project Period (FY) |
2015-04-01 – 2019-03-31
|
Project Status |
Completed (Fiscal Year 2018)
|
Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2018: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2016: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
Keywords | IoTネットワーク / 施設栽培イチゴ / 収穫量推定 / ノンパラメトリック回帰 / 差分値 / 収穫量推定精度 / 収穫モデル / 収穫量推定・予測 / 積算値 / IoT / BigData / センサネットワーク / イチゴ / 回帰分析 / センサ計測 / データ解析 |
Outline of Final Research Achievements |
In this study, first, in order to construct a robust harvest model for the environment, we design and manufacture a sensor terminal composed of general-purpose electronic components. As a result, we establish means for easily acquiring information (data) in physical space, that is, construct an IoT network. Next, we proposed a model that the harvest volume is affected by long and short-term environmental influence for crops harvested multiple times during a season. We show the effectiveness of proposed model by evaluating the yield estimation accuracy based on nonparametric GAM (Generalized Additive Model) regression using actual yield data and environmental data obtained from the IoT network built in the house facility of the regional strawberry farmer.
|
Academic Significance and Societal Importance of the Research Achievements |
近年のイチゴ栽培では軽労化に向け高設化が進み,従来の土耕と比べ植物体周辺の環境条件に大きな変化があり,環境情報が収穫・生育に与える影響を明らかにすることは意義がある.汎用品のみで設計・製作したセンサ端末は工場など農業以外の分野でも利用可能であり適用範囲が広い.さらに,提案する収穫量推定モデルは他の作物でも適用可能で汎用性が高い.これらを活用することでIoTやそのデータ解析技術の更なる進展が期待される.
|
Report
(5 results)
Research Products
(24 results)