DOI QR코드

DOI QR Code

Machine learning application for predicting the strawberry harvesting time

  • Yang, Mi-Hye (Department of Bioresources and Rural Systems Engineering, Hankyong National University) ;
  • Nam, Won-Ho (Department of Bioresources and Rural Systems Engineering, Hankyong National University) ;
  • Kim, Taegon (Institute on the Environment, University of Minnesota) ;
  • Lee, Kwanho (CESeL Primus) ;
  • Kim, Younghwa (Rural Research Institute, Korea Rural Community Corporation)
  • Received : 2019.03.15
  • Accepted : 2019.05.29
  • Published : 2019.06.01

Abstract

A smart farm is a system that combines information and communication technology (ICT), internet of things (IoT), and agricultural technology that enable a farm to operate with minimal labor and to automatically control of a greenhouse environment. Machine learning based on recently data-driven techniques has emerged with big data technologies and high-performance computing to create opportunities to quantify data intensive processes in agricultural operational environments. This paper presents research on the application of machine learning technology to diagnose the growth status of crops and predicting the harvest time of strawberries in a greenhouse according to image processing techniques. To classify the growth stages of the strawberries, we used object inference and detection with machine learning model based on deep learning neural networks and TensorFlow. The classification accuracy was compared based on the training data volume and training epoch. As a result, it was able to classify with an accuracy of over 90% with 200 training images and 8,000 training steps. The detection and classification of the strawberry maturities could be identified with an accuracy of over 90% at the mature and over mature stages of the strawberries. Concurrently, the experimental results are promising, and they show that this approach can be applied to develop a machine learning model for predicting the strawberry harvesting time and can be used to provide key decision support information to both farmers and policy makers about optimal harvest times and harvest planning.

CNNSA3_2019_v46n2_381_f0001.png 이미지

Fig. 1. Comparison of agricultural crop income data between 2005 and 2017 year.

CNNSA3_2019_v46n2_381_f0002.png 이미지

Fig. 2. Classifcation of crop image according to growing steps: (a) Test image of immature strawberry, (b) Test image of mature strawberry, (c) Test image of over mature strawberry.

CNNSA3_2019_v46n2_381_f0003.png 이미지

Fig. 3. Accuracy results based on number of training images and steps for immature strawberry.

CNNSA3_2019_v46n2_381_f0004.png 이미지

Fig. 4. Accuracy results based on number of training images and steps for mature strawberry.

CNNSA3_2019_v46n2_381_f0005.png 이미지

Fig. 5. Accuracy results based on number of training images and steps for over mature strawberry.

CNNSA3_2019_v46n2_381_f0006.png 이미지

Fig. 6. Detection results of immature strawberries according to training steps: (A) Step 100, (B) Step 2,000, (C) Step 20,000, (D) Step 50,000, (E) Step 100,000, (F) Step 150,000, (G) Step 200,000.

CNNSA3_2019_v46n2_381_f0007.png 이미지

Fig. 7. Classifcation loss of training data based on training steps.

CNNSA3_2019_v46n2_381_f0008.png 이미지

Fig. 8. Classifcation loss of validation data based on training steps.

CNNSA3_2019_v46n2_381_f0009.png 이미지

Fig. 9. Localization loss of training data based on training steps.

CNNSA3_2019_v46n2_381_f0010.png 이미지

Fig. 10. Localization loss of validation data based on training steps.

CNNSA3_2019_v46n2_381_f0011.png 이미지

Fig. 11. Detection results of growth stages strawberries: (A, D, G) Detection of immature strawberry images, (B, E, H) Detection of mature strawberry images, (C, F, I) Detection of over mature strawberry images.

Table 1. Accuracy results based on number of training images and steps for immature strawberry.

CNNSA3_2019_v46n2_381_t0001.png 이미지

Table 2. Accuracy results based on number of training images and steps for mature strawberry.

CNNSA3_2019_v46n2_381_t0002.png 이미지

Table 3. Accuracy results based on number of training images and steps for over mature strawberry.

CNNSA3_2019_v46n2_381_t0003.png 이미지

Acknowledgement

Supported by : 농림식품기술기획평가원

References

  1. Lim H, An H, Kim H, Lee J. 2018. Prediction of pollution loads in the Geum River upstream using the recurrent neural network algorithm. Korean Journal of Agricultural Science 46:67-78. [in Korean]
  2. Lee J, Kim S, Lee S, Choi H, Jung J. 2014. A study on the necessity and construction plan of the internet of things platform for smart agriculture. Journal of Korea Multimedia Society 17:1313-1324. [in Korean] https://doi.org/10.9717/kmms.2014.17.11.1313
  3. Lanfley P. 1995. Applications of machine learning and rule induction. Institute for the Study of Learning and Experise, Technical Report 95-1.
  4. Liakos KG, Busato P, Moshou D, Pearson S, Bochtis D. 2018. Machine learning in agriculture: A review. Sensors 18:2674.
  5. Lokers R, Knapen R, Janssen S, van Randen Y, Jansen J. 2016. Analysis of big data technologies for use in agro-environmental science. Environmental Modelling & Software 84:494-504.
  6. MAFRA (Ministry of Agriculture, Food and Rural Affairs). 2018. Major statistics of agricultural and livestock food. MAFRA, Sejong, Korea. [in Korean]
  7. McQueen RJ, Garner SR, Nevill-Manning CG, Witten IH. 1995. Applying machine learning to agricultural data. Computers and Electronics in Agriculture 12:275-293.
  8. Miao Y, Mulla DJ, Robert PC. 2006. Identifying important factors influencing corn yield and grain quality variability using artificial neural networks. Precision Agriculture 7:117-135.
  9. Mohanty SP, Hughes DP, Salathe M. 2016. Using deep learning for image-based plant disease detection. Frontiers in Plant Science 7:1419.
  10. Nam WH, Kim T, Hong EM, Choi JY, Kim JT. 2017. A wireless sensor network (WSN) application for irrigation facilities management based on information and communication technologies (ICTs). Computers and Electronics in Agriculture 143:185-192.
  11. Oquab M, Bottou L, Laptev I, Sivic J. 2014. Learning and transferring mid-level image representations using convolutional neural networks. 2014 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Columbus, USA.
  12. Ray PP. 2017. Internet of things for smart agriculture: Technologies, practices and future direction. Journal of Ambient Intelligence and Smart Environments 9:395-420.
  13. RDA (Rural Development Administration). 2018. 2017 agricultural products income data. RDA, Jeonju, Korea. [in Korean]
  14. Shine P, Murphy MD, Upton J, Scully T. 2018. Machine-learning algorithms for prediction on-farm direct water and electricity consumption on pasture based dairy farms. Computers and Electronics in Agriculture 150:74-87.
  15. Szegedy C, Vanhoucke V, Ioffe S, Shlens J. 2016. Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR):2818-2826.
  16. Walter A, Finger R, Huber R, Buchmann N. 2017. Smart farming is key to developing sustainable agriculture. Proceedings of the National Academy of Sciences of the United States of America 114:6148-6150.
  17. Bae SM, Han SM, Choi JM, Lee JS, Kim HK. 2016. Manufacturing of Korean traditional rice wine, Makgeolli, supplemented with Strawberry and its physicochemical and microbial Properties during Fermentation. The Korean Journal of Mycology 44:307-313. [in Korean]
  18. Balducci F, Impedovo D, Pirlo G. 2018. Machine learning applications on agricultural datasets for smart farm enhancement. Machines 6:38.
  19. Espejo-Garcia B, Martinez-Guanter J, Perez-Ruiz M, Lopez-Pellicer FJ, Zarazaga-Soria FJ. 2018. Machine learning for automatic rule classification of agricultural regulations: A case study in Spain. Computers and Electronics in Agriculture 150:343-352.
  20. Hong EM, Choi JY, Nam WH, Kim JT. 2016. Decision support system for the real-time operation and management of an agricultural water supply. Irrigation and Drainage 65:197-209.
  21. Jayaraman PP, Yavari A, Georgakopoulos D, Morshed A, Zaslavsky A. 2016. Internet of things platform for smart farming: Experiences and lessons learnt. Sensors 16:1884.
  22. Kamienski C, Soininen JP, Taumberger M, Dantas R, Toscano A, Cinotti TS, Maia RF, Neto AT. 2019. Smart water management platform: IoT-based precision irrigation for agriculture. Sensors 19:276.
  23. Kamilaris A, Kartakoullis A, Prenafeta-Boldu FX. 2017. A review on the practice of big data analysis in agriculture. Computers and Electronics in Agriculture 143:23-37.
  24. Kamilaris A, Prenafeta-Boldu FX. 2018. Deep learning in agriculture: A survey. Computers and Electronics in Agriculture 147:70-90.
  25. Kim GM. 2017. A study on the packaging design of agricultural products by Smart Farm agricultural technology development: Focused on strawberry packaging design. Journal of Cultural Product & Design 48:129-138. [in Korean] https://doi.org/10.18555/kicpd.2017.48.11
  26. Kim W, Son CS, Choi CK, So NH, Lee CW, Ha DJ. 2017. Analysis on factors affecting the greenhouse strawberry income. Korea Journal of Agricultural Management and Policy 44:469-487. [in Korean]
  27. KOSIS (Korean Statistical Information Service). 2018. 2017 Report of the agricultural and fishery. KOSIS, Daejeon, Korea. [in Korean]
  28. KREI (Korea Rural Economic Institute). 2018. Korean agriculture in the world by statistics. KREI, Naju, Korea. [in Korean]
  29. KREI (Korea Rural Economic Institute). 2019. Trends in agricultural and rural economy 2018 winter. KREI, Naju, Korea. [in Korean]
  30. Wolfert S, Ge L, Verdouw C, Bogaardt MJ. 2017. Big data in smart farming - A review. Agricultural Systems 153:69-80.
  31. Yu BG. 2016. A study on the smart farming diffusion policies in Gyeongbuk Province. Daegu Gyeongbuk Development Institute, Daegu, Korea. [in Korean]
  32. Zaborowicz M, Boniecki P, Koszela K, Przybylak A, Przybyl J. 2017. Application of neural image analysis in evaluating the quality of greenhouse tomatoes. Scientia Horticulturae 218:222-229.