به کارگیری مدل‌های هیبریدی مبتنی بر یادگیری عمیق ماشین در کشاورزی هوشمند (مطالعه موردی: پیش‌بینی قیمت آتی پسته)

مجله اقتصاد و توسعه کشاورزی

مقاله 4، دوره 37، شماره 3 - شماره پیاپی 60، مهر 1402، صفحه 289-307   

نوع مقاله: مقالات پژوهشی

شناسه دیجیتال (DOI): 10.22067/jead.2023.79545.1165

نویسندگان

سید محمد رضا حاج سیدجوادی؛ رضا حیدری^*

مؤسسه پژوهش‏های برنامه‌ریزی، اقتصاد کشاورزی و توسعه روستایی، تهران، ایران

چکیده

امروزه بسیاری از کشاورزان و فعالان بخش کشاورزی از تغییرات قیمت‌های بازار و آخرین پیشرفت‌های فناوری در حوزه قیمت محصولات کشاورزی آگاهی‌های لازم را ندارند؛ بنابراین بهره‌گیری از مدل‌های هوشمند برای پیش‌بینی دقیق قیمت کالاهای کشاورزی در حوزه کشاورزی هوشمند برای آنها اهمیت حیاتی دارد. لذا هدف از این مطالعه، ارائه یک مدل هوشمند بر پایه داده‌کاوی از نوع هیبریدی غیر خطی برای پیش‌بینی دقیق قیمت آتی پسته به منظور رفع محدودیت‌های موجود شامل ماهیت چندبعدی داده‌ها، عدم قطعیت در داده‌های پیش‌بینی شده و نهایتاً ارائه و ساخت مدل پایه قابل انتشار در زمینه ‌به کارگیری الگوریتم‌های یادگیری ماشین عمیق برای پیش‌بینی قیمت محصولات کشاورزی است. نتایج حاصل از این مطالعه نشان داد که 1) با بکارگیری تئوری موجک برای نوفه‌زدایی داده‌ها، میزان خطای داده‌های قیمت کاهش یافته و داده‌ها از یک روند باثبات برخوردار ‌شدند، 2) نتایج حاصل از اجرای شبکه کدکننده خودکار منتج به انتخاب وقفه بهینه یک، به عنوان متغیر ورودی برای پیش‌بینی قیمت آتی پسته تشخیص داده شد، 3) نتایج حاصل از بکارگیری شبیه‌سازی مونت کارلو-زنجیره مارکف و نیز پیش‌بینی خارج از نمونه با مجموعه داده‌های جدید، بیانگر این است که محتمل‌ترین و خوشبینانه‌ترین قیمت قابل وقوع برای قیمت آتی پسته در بورس کالای ایران، در سقف قیمتی 213 هزار تومان قرار دارد و قیمت پیش‌بینی شده با قیمت واقعی دارای اختلاف اندکی است (میزان خطا 0/7 درصد است). بر اساس نتایج حاصل شده، استفاده از مدل هیبریدی پیشنهاد شده و بکارگیری اجزای بکار برده شده در آن یعنی تابع تبدیل موجک، شبکه کدکننده خودکار، شبکه عصبی یادگیری عمیق، شبیه‌سازی مونت کارلو و استنتاج قیمت‌های جدید به عنوان کامل‌ترین زنجیره ارزش دو بخشی تحت یک مدل مرجع و پایه قابل انتشار برای پیش‌بینی و آزمون سایر محصولات کشاورزی با امکان به کارگیری تواترهای زمانی مختلف پیشنهاد می‌شود.

کلیدواژه‌ها

پیش‌بینی قیمت آتی پسته؛ تئوری موجک و شبیه‌سازی مونت کارلو-زنجیره مارکف؛ داده‌کاوی؛ یادگیری شبکه عصبی عمیق

مراجع

1. 1. Akhbari, M. (2018). Project time and cost forecasting using Monte Carlo simulation and artificial neural networks. International Journal of Industrial Engineering and Production Research, 29(2), 231-239.
   2. Anjoy, P., & Paul, R.K. (2017). Wavelet based hybrid approach for forecasting volatile potato price. Journal of the Indian Society of Agricultural Statistics, 71(1), 7-14.
   3. Aworka, R., Cedric, L.S., Hamilton Adoni, W.Y., Zoueu, J.T., Mutombo, F.K., Mberi Kimpolo, Ch. L., Nahhal, T., & Krichen, M. (2022). Agricultural decision system based on advanced machine learning models for yield prediction: Case of East African countries. Journal of Smart Agricultural Technology, 2 100048, 1-9. http://doi.org/10.1016/j.atech.2022.100048
   4. Cemgil, A.T. (2014). A tutorial introduction to Monte Carlo methods, Markov Chain Monte Carlo and particle filtering. Academic press library in signal processing, 1: 1065-1114, ISBN: 978-0-12- 396502-8. http://doi.org/10.1016/B978-0-12-396502-8.00019-X
   5. David, A., & Spade, D.A. (2020). Markov chain Monte Carlo methods: theory and practice. Handbook of Statistics, 43. http://doi.org/10.1016/bs.host.2019.06.001
   6. Ebrahimi, M., Talebnia, Gh., Vakilifard, H.R., & Nikuomaram, H. (2017). Application of Monte Carlo simulation - Markov chain in explaining working capital management strategy. Iranian Journal Quarterly Financial Accounting, 9(33), 1-22. (In Persian with English abstract)
   7. Gao, R., Du, L., Duru, O., & Yuen, K.F. (2021). Time series forecasting based on echo state network and empirical wavelet transformation. Journal of Applied Soft Computing, 102, 107111. http://doi.org/10.1016/j.asoc.2021.107111
   8. Ghaderzadeh, H., Ahmadzadeh, Kh., & Ganji, S. (2019). Determine the appropriate model to predict the price of Agricultural crops: A case of wheat, Alfa-Alfa and Potato crops. Iranian Journal of Agricultural Economics Research, 11(3), 23-40. (In Persian with English abstract)
   9. Ghahremanzadeh, M., & Rashid Ghalam, M. (2015). Seasonal forecasting of meat prices in Iran: Application of periodic autoregressive model. Iranian Journal of Agricultural Economics and Development Research, 46(3), 469-480. https://doi.org/10.22059/ijaedr.2015.55520
   10. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. https://www.amazon.com/
   11. Greff, K., Srivastava, R.K., & Koutnik, J., Steunebrink, B.R., & Schmidhuber, J. (2017). LSTM: A Search Space Odyssey. IEEE Transactions on Neural Networks and Learning Systems, 28(10): 2222-2232. http://doi.org/10.48550/arXiv.1503.04069
   12. Guo, L., & Wozniak, M. (2021). An image super-resolution reconstruction method with single frame character based on wavelet neural network in internet of things. Journal of Mobile Networks and Applications, 26, 390-403. http://doi.org/10.1007/s11036-020-01681-6.
   13. Haj Seyed Javady, M.R., & Heydari, R. (2022). Designing the most suitable hybrid model for forecasting the future price of saffron in the agricultural commodity bourse. Iranian Journal of Agricultural Economics and Development Research, 53-2(4), 1023-1041. http://doi.org/10.22059/IJAEDR.2022.336850.669122
   14. Haviluddin, S., Khosyi, T., & et (2021). A backpropagation neural network algorithm in agricultural product prices prediction. 3rd East Indonesia Conference on Computer and Information Technology (EIConCIT), ISTTS Surabaya, Indonesia.
   15. Hegde, J., Hulipalled, V.R., & Simha, J.B. (2021). Price prediction of agriculture commodities using machine learning and NLP. Second International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE 2021),
   16. Heydari, R., & Haj Seyed Javady, M.R. (2022). The application of hybrid data mining model (genetic algorithm-wavelet-deep neural network-Monte Carlo method) for the price forecasting of agricultural products (Case study: future price of saffron in agricultural commodity exchange). Iranian Journal of Agricultural economics and Development, 30(120), 73-105. http://doi.org/10.30490/AEAD.2023.357440.1412
   17. Hirapara, J., & Vanjara, D. (2022). A comparative study of data mining techniques for agriculture crop price prediction. 7^th International conference for Convergence in Technology (I2CT), Pune, India. Apr 2022, 1-6.
   18. Hogg, D.W., & Foreman-Mackey, D. (2018). Data analysis recipes: using Markov chain Monte Carlo. The Astrophysical Journal Supplement Series, 236(1), 1-54. http://doi.org/10.3847/1538-4365/aab76e
   19. Hoseini, S.M., Mazandarani zadeh, , & Nazari, B. (2021). Simultaneously management of surface and groundwater resources and increasing farmers' resilience to water scarcity by predicting the price of agricultural products and using GA (case study of irrigation and drainage network of Qazvin plain). Iranian Journal of Soil and Water Research, 52(2), 563-576. https://doi.org/10.22059/ijswr.2021.313809.668805
   20. Joshi, A.M., & Patel, S. (2022). A CNN-Bidirectional LSTM approach for price forecasting of agriculture commodities in Gujarat. The International Conference on Applied Artificial Intelligence and Computing (ICAAIC 2022), 266-272. http://doi.org/10.1109/ICAAIC53929.2022.9793154
   21. Kamilaris, A., Francesc, X., & Boldu, P. (2018). Deep learning in agriculture: A survey. Journal of Computers and Electronics in Agriculture, 147, 70-90. http://doi.org/10.1016/j.compag.2018.02.016
   22. Karakoyun, E.S., & Cibikdiken, A.O. (2018). Comparison of ARIMA time series model and lstm deep learning algorithm for bitcoin price forecasting. The 13^th Multidisciplinary Academic conference in Prague (the 13^th MAC 2018).
   23. Li, J., & Wang, J. (2020). Stochastic recurrent wavelet neural network with EEMD method on energy price prediction. Journal of Soft Computing, 24, 17133-17151. https://doi.org/10.1007/s00500-020-05007-2
   24. Li, P., Hua, P., Gui, D., Niu, J., Pei, P., Zhang, J., & Krebs, P. (2020). A comparative analysis of artificial neural networks and wavelet hybrid approaches to long-term toxic heavy metal prediction. Journal of Scientific Reports, 10, 13439. http://doi.org/10.1038/s41598-020-70438-8
   25. Liu, J.; Xu, L., Cao, X., Zhang, K., Zhang, Q., & Cai, Y. (2020). Review on the architectures and applications of deep learning in agriculture. 7^th International Conference on Information Science and Control Engineering (ICISCE), 1234-1240. http://doi.org/10.1109/ICISCE50968.2020.00250
   26. Liu, X., Liu, H., Guo, Q., & Zhang, C. (2020). Adaptive wavelet transform model for time series data prediction. Journal of Soft Computing, 24, 5877-5884. http://doi.org/10.1007/s00500-019-04400-w
   27. Maiti, S., & Tiwari, R.K. (2009). A hybrid Monte Carlo method based artificial neural networks approach for rock boundaries identification: a case study from the KTB Bore Hole. Journal of Pure and Applied Geophysics, 166, 2059-2090. http://doi.org/ 10.1007/s00024-009-0533-y
   28. Mehtab, S., Sen, J., & Dutta, A. (2021). Stock price prediction using machine learning and LSTM-based deep learning models. Machine Learning and Metaheuristics Algorithms, and Applications, 88-106. Springer, http://doi.org/10.1007/978-981-16-0419-5_8
   29. Mitra, D., & Paul, R.K. (2020). Forecasting of price of rice in India using long-memory time series model. Springer: National Academy Science Letters, 44, 289-293. http://doi.org/10.1007/s40009-020-01002-1
   30. Moghadasi, R., & Jaleh Rajabi, M. (2013). Comparison of combined and conventional models in forecasting prices of wheat, corn and sugar. Iranian Journal of Agricultural Economics Research, 5(2), 1-22. (In Persian with English abstract)
   31. Nassar, L., Okwuchi, I.E., Saad, M., Karray, F., & Ponnambalam, K. (2020). Deep learning based approach for fresh produce market price prediction. In 2020 International Joint Conference on Neural Networks (IJCNN) (pp. 1-7). IEEE. http://doi.org/10.1109/IJCNN48605.2020.9207537
   32. North, M. (2012). Data Mining for the Masses. https://www. Amazon.com. https://docs.rapidminer.com.
   33. Pablo, B. J., Hilda, C., & et al. (2016). Artificial neural network and Monte Carlo simulation in a hybrid method for time Series forecasting with generation of L-scenarios. 2016 Intl IEEE Conferences on Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable… (UIC/ATC/ScalCom/CBDCom/IoP/SmartWorld). http://doi.org/10.1109/UIC-ATC-ScalCom-CBDCom-IoP-SmartWorld.2016.0110
   34. Paul, R.K., Paul, A.K., & Bhar, L.M. (2020). Wavelet-based combination approach for modeling sub-divisional rainfall in India. Journal of Theoretical and Applied Climatology, 139(3-4), 949-963. http://doi.org/10.1007/s00704-019-03026-0
   35. Paul, R.K. (2015). ARIMAX-GARCH-WAVELET model for forecasting volatile data. Journal of Model Assisted Statistics and Applications, 10(3), 243–252. http://doi.org/10.3233/MAS-150328
   36. Paul, R.K., & Garai, S. (2021). Performance comparison of wavelets-based machine learning technique for forecasting agricultural commodity prices. Journal of Soft Computing, 25, 12857 12873. http://doi.org/10.1007/s00500-021-06087-4
   37. Pourreza Bilondi, M., & Khashei Siuki, A. (2015). Uncertainty analysis of artificial neural networks in simulation of saturated hydraulic conductivity using Monte-Carlo simulation. Iranian Journal of Irrigation and Drainage, 4(9), 655-664. (In Persian with English abstract)
   38. Raflesia, S.P., Taufiqurrahman, T., Iriyani, S., & Lestarini, D. (2021). Agricultural commodity price forecasting using PSO-RBF neural network for farmers exchange rate improvement in Indonesia. Indonesian Journal of Electrical Engineering and Informatics, 9(3), 784-792. http://doi.org/10.52549/ijeei.v9i3.2723
   39. RapidMiner Manual. (2021). Deployments. https://docs.rapidminer.com.
   40. Rasheed, A., Younis, S., Ahmad, F., Qadir, J., & Kashif, M. (2022). District wise price forecasting of wheat in Pakistan using deep learning. Journal of arXiv-CS-Artificial Intelligence. http://doi.org/arxiv-2103.04781
   41. Roondiwala, M., Patel, H., & Varma, Sh. (2017). Predicting stock prices using LSTM. International Journal of Science and Research, 6(4): 1753-1756.
   42. Sabu, K.M., & Kumar, T.M. (2020). Predictive analytics in agriculture: forecasting prices of Arecanuts in Kerala. Journal of Procedia Computer Science, 171, 699-708. http://doi.org/1016/j.procs.2020.04.076
   43. Samek, W., Wiegand, T., & Muller, K. R. (2017). Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models. arXiv preprint arXiv:1708.08296. http://doi.org/10.48550/arXiv.1708.08296
   44. Shabri, A., & Samsudin, R. (2014). Daily crude oil price forecasting using hybridizing wavelet and artificial neural network model. Hindawi Publishing Corporation Mathematical Problems Engineering, Volume 2014, Article ID 201402, 10 pages. http://doi.org/10.1155/2014/201402
   45. Sharma, A.K., & Rajawat, A.S. (2022). Crop yield prediction using hybrid deep learning algorithm for smart agriculture. The Second International Conference on Artificial Intelligence and Smart Energy (ICAIS-2022), http://doi.org/10.1109/ICAIS53314.2022.9743001
   46. Siami Namini, S., & Siami Namin, K. (2018). Forecasting economics and financial time series: ARIMA vs. LSTM. arXiv preprint arXiv:1803.06386. http://doi.org/10.48550/arXiv.1803.06386
   47. Speagle, J. (2020). A conceptual introduction to Markov chain Monte Carlo methods. arXiv:1909.12313. http://doi.org/10.48550/arXiv.1909.12313
   48. Tohidi, A. (2015). Evaluation of artificial neural network-panel data hybrid model in predicting Iran’s dried fruits export prices. Quarterly Journal of Economics Quarterly, 12(3), 95-116. (In Persian with English abstract)
   49. Vohra, A., Pandey, N., & Khatri, S.K. (2019). Decision making support system for prediction of Prices in agricultural commodity. International Conference on Artificial Intelligence (AICAI 2019), Dubai (United Arab Emirates), 345-348. http://doi.org/10.1109/AICAI.2019.8701273
   50. Wang, J., & Li, X. (2018). A combined neural network model for commodity price forecasting with SSA. Journal of Soft Computing, 22, 5323-5333.
   51. Wang, J., et al. (2018). Gaussian Process Kernels for Noisy Time Series: Application to Housing Price Prediction. International Conference on Neural Information Processing. Springer, Cham. http://doi.org/10.1007/978-3-030-04224-0_8
   52. Wen, Y., Lin, P., & Nie. X. (2020). Research of stock price prediction based on PCA-LSTM model. IOP Conf. Series: Materials Science and Engineering 790 (2020) 012109. http://doi.org/10.1088/1757-899X/790/1/012109.
   53. Weston, J., Elisseeff, A., & Scholkopf, B. (2003). Use of zero-norm with linear models and kernel methods. Journal of Machine Learning Research, 3(5), 1439-1461.
   54. Wojtas, M.A., & Chen, K. (2020). Feature importance ranking for deep learning. 34^th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada, 5105–5114. http://doi.org/10.5555/3495724.3496153
   55. Wu, D., Wang, X., & Wu, S. (2021). A hybrid method based on extreme learning machine and wavelet transform de-noising for stock prediction. Journal of Entropy, 23(4), 440. http://doi.org/10.3390/e23040440.
   56. Iran Mercantile Exchange. (2022). https://www.ime.co.ir.