Skip to Main content Skip to Navigation
Conference papers

CNN-Based Growth Prediction of Field Crops for Optimizing Food Supply Chain

Abstract : Along with the aging of the Japanese agricultural population in recent years, the nation’s food self-sufficiency rate has declined. The vitality of agriculture has also declined. This study specifically examines the food supply chain to integrate farm production, manufacturing, and sales. For the food supply chain, it is necessary to ascertain the harvest time of field crops for establishing proper sales strategies. A method to predict harvest time from field crop images using convolutional neural networks (CNN) is proposed. Then the effectiveness of the proposed method is verified using computer experiments. Results show that the discrimination rate is high in the early stage of the growth, even if misclassification occurs. Labels close to the correct answer are predicted. However, the discrimination rate is not so high and the deviation from the correct answer becomes greater in later stages of growth.
Document type :
Conference papers
Complete list of metadatas

Cited literature [7 references]  Display  Hide  Download

https://hal.inria.fr/hal-02419248
Contributor : Hal Ifip <>
Submitted on : Thursday, December 19, 2019 - 1:16:55 PM
Last modification on : Thursday, December 19, 2019 - 1:57:15 PM
Long-term archiving on: : Friday, March 20, 2020 - 5:47:45 PM

File

 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2022-01-01

Please log in to resquest access to the document

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Shunsuke Iitsuka, Nobutada Fujii, Daisuke Kokuryo, Toshiya Kaihara, Shinichi Nakano. CNN-Based Growth Prediction of Field Crops for Optimizing Food Supply Chain. IFIP International Conference on Advances in Production Management Systems (APMS), Sep 2019, Austin, TX, United States. pp.148-154, ⟨10.1007/978-3-030-30000-5_20⟩. ⟨hal-02419248⟩

Share

Metrics

Record views

51