한국시뮬레이션학회논문지 (Journal of the Korea Society for Simulation)

한국시뮬레이션학회 (The Korea Society for Simulation)
권호 표지
DOI QR코드

DOI QR Code

CNN을 활용한 새싹삼의 품질 예측 모델 개발

A Quality Prediction Model for Ginseng Sprouts based on CNN

  • 투고 : 2021.02.25
  • 심사 : 2021.05.09
  • 발행 : 2021.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

농촌 인구의 감소와 고령화가 지속되면서 농업 생상성 향상의 중요성이 높아지고 있는 가운데, 농작물 품질에 대한 조기 예측은 농업 생산성 및 수익성 향상에 중요한 역할을 할 수 있다. 최근 CNN 기반의 딥러닝 기술 및 전이 학습을 활용하여 농작물의 질병을 분류하거나 수확량을 예측하는 연구가 활발하게 진행되고 있지만, 수확 후 농작물의 품질을 식재단계에서 조기에 예측하는 연구는 찾아보기 힘들다. 본 연구에서는 건강 기능성 식품으로 주목받고 있는 새싹삼을 대상으로, 수확 후 새싹삼의 품질을 식재단계에서 조기에 예측하는 모델을 제안한다. 이를 위하여 묘삼의 이미지를 촬영한 후 수경재배를 통해 새싹삼을 재배하였고, 수확 후 새싹삼의 품질을 분류하여 실험 데이터를 수집하였다. 다수의 CNN 기반의 사전 학습된 모델을 활용하여 새싹삼 조기 품질 예측 모델을 구축하고, 수집된 데이터를 이용하여 각 모델의 학습 및 예측 성능을 비교 분석하였다. 분석 결과 모든 예측 모델에서 80% 이상의 예측 정확도를 보였으며, 특히 ResNet152V2 기반의 예측 모델에서 가장 높은 정확도를 보였다. 본 연구를 통해 인력에 의존하던 기존의 묘삼 선별 작업을 자동화하여 새싹삼의 품질을 높이고 생산량을 증대시켜 농가의 수익창출에 기여할 수 있을 것으로 기대된다.

As the rural population continues to decline and aging, the improvement of agricultural productivity is becoming more important. Early prediction of crop quality can play an important role in improving agricultural productivity and profitability. Although many researches have been conducted recently to classify diseases and predict crop yield using CNN based deep learning and transfer learning technology, there are few studies which predict postharvest crop quality early in the planting stage. In this study, a early quality prediction model is proposed for sprout ginseng, which is drawing attention as a healthy functional foods. For this end, we took pictures of ginseng seedlings in the planting stage and cultivated them through hydroponic cultivation. After harvest, quality data were labeled by classifying the quality of ginseng sprout. With this data, we build early quality prediction models using several pre-trained CNN models through transfer learning technology. And we compare the prediction performance such as learning period and accuracy between each model. The results show more than 80% prediction accuracy in all proposed models, especially ResNet152V2 based model shows the highest accuracy. Through this study, it is expected that it will be able to contribute to production and profitability by automating the existing seedling screening works, which primarily rely on manpower.

키워드

참고문헌

  1. Chang, E. H., Lee, J. H., Choi, J. W., Shin, I. S., and Hong, Y. P., "Effects of Film Packaging and Gas Composition on the Distribution and Quality of Ginseng Sprouts", Korean Journal of Medicinal Crop Science, Vol. 28, NO. 2, pp. 152-166, 2020. https://doi.org/10.7783/KJMCS.2020.28.2.152
  2. Cho, D. H., "Development of Stable Production Technology for Sprout Ginseng", Korea Institute of Agricultural Technology, 2018.
  3. Chollet, F., "Deep Learning with Python", Manning Publications, Inc. USA, 2017.
  4. Jia, D., et al., "ImageNet: A Large-scale Hierarchica Image Database", Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 248-255, 2009.
  5. Ferentinos, K. P., "Deep Learning Models for Plant Disease Detection and Diagnosis", Comput. Electron. Agric. Vol. 145, pp. 311-318, 2018. https://doi.org/10.1016/j.compag.2018.01.009
  6. Jeong, S. B., and Yoon, H. S., "An Efficient Disease Inspection Model for Untrained Crops Using VGG16", J. of the Korea Society for Simulation, Vol. 29, No. 4, pp. 1-7, 2020. https://doi.org/10.9709/JKSS.2020.29.4.001
  7. Jun, S. Y., Kim, T. H., and Hwang, S. H., "The Consumption Status and Preference for Sprouts and Leafy Vegetables", Korean J. Food Preserv, Vol. 19, No. 5, pp. 783-791, 2012. https://doi.org/10.11002/kjfp.2012.19.5.783
  8. Kang, O. J., and Kim, J. S., "Comparison of ginsenoside contents in different parts of Korean ginseng (Panax ginseng C.A. Meyer)", Prev. Nutr. Food Sci, pp. 389-392, 2016.
  9. Khaki, S., Wang, L., and Archontoulis, S. V., "A CNN-RNN Framework for Crop Yield Prediction", Front. in Plant Science, 2020.
  10. Ko, J. H., and Kim, H. C., "PLC Automatic Control for IOT Based Hydroponic Plant Factory", J. of IKEEE, Vol. 23, No. 2, pp. 487-494, 2019. https://doi.org/10.7471/IKEEE.2019.23.2.487
  11. Lee, K. S., and Park, G. S., "Studies in the Consumption and Preference for Sprout Vegetables", J. East Asian Soc Dietary Life, Vol. 24, No. 6, pp. 896-905, 2014.
  12. Lee, J. Y., Yang, H., Lee, T. K., Lee, C. H., Seo, J. W., Kim, J. E., Kim, S. Y., Yoon, J. H., and Lee, K. W., "A short-term, hydroponic-culture of ginseng results in a significant increase in the anti-oxidative activity and bioactive components", Food Sci Biotechnol, Vol. 29, No. 7, pp. 1007-1012, 2020. https://doi.org/10.1007/s10068-020-00735-5
  13. Li, Y., Nie, J., and Chao, X., "Do we really need deep CNN for plant diseases identification?", Computers and Electronics in Agriculture, Vol. 178, 2020.
  14. Liu, J., and Wang, X., "Tomato Diseases and Pests Detection Based on Improved Yolo V3 Convolutional Neural Network", Front. Plant Sci, 2020.
  15. Oh, H. K., Lee, S. O., Chung, H. S., and Cho, B. K., "Study on the Development of Auto-classification Algorithm for Ginseng Seedling using SVM (Support Vector Machine)", J. of Biosystems Eng Vol. 36, No. 1, pp. 40~47, 2011. https://doi.org/10.5307/JBE.2011.36.1.40
  16. Park, H. W., Kim, Y. C., Kim, J. U., Kim, Y. B., Kang, S. W., Cha, S. W., Kim, S. M., and Hyun, D. Y., "The Effect of Chemical Properties of Growing Media on Production of Ginseng Seedling", The Korean Society of Ginseng. pp. 158-158, 2011.
  17. Park, J. S., Kim, S. J., Kim, H. J., Choi, J. M., and Lee, G. I., "Photosynthetic characteristics and growth analysis of Angelica gigas according to different hydroponics methods", CNU Journal of Agricultural Science, Vol. 41, No. 4, pp. 321-326, 2014.
  18. Picon, A., Alvarez-Gila, A., Seitz, M., Ortiz-Barredo, A., Echazarra, J., and Johannes, A., "Deep Convolutional Neural Networks for Mobile Capture Device-based Crop Disease Classification in the Wild", Comput. Electron. Agric. Vol. 138, pp. 200-209, 2018. https://doi.org/10.1016/j.compag.2017.04.013
  19. Seong, J. B., Kim, S. I., Jee, M. G., Lee, H. C., Kwon, A. R., Kim, H. H., Won, J. Y., and Lee, K. S., "Changes in Growth, Active Ingredients, and Rheological Properties of Greenhouse-cultivated Ginseng Sprout during its Growth Period", Korean Journal of Medicinal Crop Science, Vol. 27, No. 2, pp. 126-135, 2019. https://doi.org/10.7783/KJMCS.2019.27.2.126
  20. Sladojevic, S., Arsenovic, M., Anderla, A., Culibrk, D., and Stefanovic, D., "Deep neural networks based recognition of plant diseases by leaf image classification", Computat. Intelligence Neurosci, pp. 1-11, 2016.
  21. Suh, S. J., Yu, J., Jang, I. B., Moon, J. W., and Lee, S. W., "Effects of Storage Temperature and Seed Treatment on Emergence and Growth Properties of Panax ginseng at Spring-sowing", Korean Journal of Medicinal Crop Science, Vol. 26, NO. 5, pp. 401-407, 2018. https://doi.org/10.7783/KJMCS.2018.26.5.401
  22. Sun, J., Di, L., Sun, Z., Shen, Y., and Lai, Z., "County-Level Soybean Yield Prediction Using Deep CNN-LSTM Model", J. Sensors, Vol. 19. No. 20, 2019.
  23. Zhang, H., Xua, S., Piao, C., Zhao, X., Tian, Y., Cui, D., Sun, G., and Wang, Y., "Post-planting performance, yield, and ginsenoside content of Panax ginseng in relation to initial seedling size", Industrial Crops and Products, Vol. 125, pp. 24-32, 2018. https://doi.org/10.1016/j.indcrop.2018.08.091