شناسایی ویژگی‌های مؤثر بر هزینه سامانه‌های آبیاری قطره‌ای با استفاده از روش‌های انتخاب ویژگی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری گروه مهندسی آبیاری و آبادانی، دانشکدگان کشاورزی و منابع طبیعی، دانشگاه تهران، کرج، ایران.

2 استادیار گروه احیاء مناطق خشک و کوهستانی، دانشکدگان کشاورزی و منابع طبیعی، دانشگاه تهران، کرج، ایران

3 استاد گروه مهندسی آبیاری و آبادانی، دانشکدگان کشاورزی و منابع طبیعی، دانشگاه تهران، کرج، ایران.

چکیده

این پژوهش با هدف انتخاب ویژگی­های مهم برای مدل‌سازی هزینه سامانه‌های آبیاری تحت‌فشار با استفاده از داده‌های 515 پروژه آبیاری قطره­ای در چهار بخش شامل هزینه ایستگاه پمپاژ و سامانه کنترل مرکزی (TCP)، هزینه لوازم داخل مزرعه (TCF)، هزینه نصب و اجرای داخل مزرعه و ایستگاه پمپاژ (TCI) و هزینه کل (TCT) انجام شد. در مرحله اول بانک اطلاعاتی شامل 39 متغیر تأثیرگذار در هزینه بخش­های یادشده، تهیه و قیمت تمام پروژه‌ها (1385 تا 1398) برای سال پایه 1400 به‌روزرسانی شد. سپس انتخاب ویژگی با الگوریتم­های مختلف در محیط MATLAB و در دو بخش شامل (1) کل ویژگی‌ها (ویژگی­های قبل از طراحی و ویژگی­های بعد از آن شامل 39 ویژگی) و (2) ویژگی‌های قبل از مرحله طراحی (شامل 18 ویژگی) انجام شد. نتایج انتخاب ویژگی نشان داد که مقادیر RMSE و R2 برای بخش کل ویژگی‌ها به‌ترتیب برابر با 0/007 و 0/92 و برای بخش ویژگی­های قبل از طرحی به‌ترتیب برابر 0/003 و 0/89 است. از بین الگوریتم­های مختلف برای انتخاب ویژگی، ماشین بردار پشتیبان (SVM) و الگوریتم‌های بهینه‌سازی (Wrapper) به‌ترتیب عنوان بهترین یادگیرنده و روش انتخاب ویژگی شناسایی شدند. نتایج معیارهای ارزیابی نشان داد که دو الگوریتم LCA و FOA برآورد مناسبی را به دست دادند و معیار خطای آن در بخش کل ویژگی‌ها به‌ترتیب 0/0020و 0/0018 و همبستگی آن 0/94 و 0/94 به دست آمد. در بخش ویژگی‌های قبل از طراحی نیز این معیارها به‌ترتیب 0/0006 و 0/95 برای هر دو الگوریتم بود. در نهایت در بخش کل ویژگی‌ها، 10 مورد از 39 ویژگی و در بخش ویژگی‌های قبل از طراحی، 8 مورد از 18 ویژگی به‌عنوان مؤثرترین ویژگی­ها انتخاب شد. نتایج انتخاب مؤثرترین ویژگی‌ها که بر هزینه بخش‌های مختلف سامانه آبیاری قطره‌ای اثرگذارند، می­تواند مدل‌سازی هزینه سامانه‌ها را ساده­تر و سریع‌تر کرده و ضمن کاربرد در کارهای پژوهشی، در عمل نیز برآورد و مدیریت هزینه‌ها را قبل از طراحی و اجرای این طرح­ها ممکن کند.

کلیدواژه‌ها

عنوان مقاله [English]

Identifying the Features Affecting the Cost of Drip Irrigation Systems Using Feature Selection Methods

نویسندگان [English]

  • Masoud Pourgholam-Amiji 1
  • Khaled Ahmadaali 2
  • Abdolmajid Liaghat 3
1 Ph.D. Candidate, Department of Irrigation and Reclamation Engineering, College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran.
2 Assistant Professor, Department of Arid and Mountainous Regions Reclamation, College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran.
3 Professor, Department of Irrigation and Reclamation Engineering, College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran
چکیده [English]

This research aimed to select essential features for modeling the cost of pressurized irrigation systems using the data of 515 drip irrigation projects in four parts, including the cost of pumping station and central control system (TCP), cost of on-farm equipment (TCF), cost of installation and operation on-farm and pumping station (TCI), and total cost (TCT). In the first stage, a database including 39 features influencing the cost of the mentioned sectors was prepared and the price of all projects (2006 to 2019) was updated for the base year of 2021. Then, feature selection was done with different algorithms in MATLAB environment and in two parts including (1) all features (39 features before and after the design stage) and (2) 18 features before the design phase (BD). The results showed that the amounts of RMSE and R2 for all the features were equal to 0.007 and 0.92, respectively, and for the BD section, they were equal to 0.003 and 0.89, respectively. Among the different algorithms for feature selection, support vector machine (SVM) and optimization algorithms (Wrapper) were identified as the best learner and feature selection method, respectively. The results of the evaluation criteria showed that the two LCA and FOA algorithms achieved the best estimation, and their error criterion in all the features were 0.0020 and 0.0018, respectively, while their correlations were 0.94 and 0.94. In the BD features, these criteria were 0.0006 and 0.95 for both algorithms, respectively. Finally, in the all features section, 10 out of 39 features and for BD section, 8 out of 18 were selected as the most effective features. The results of choosing the most effective features that affect the cost of different parts of the drip irrigation system can make the cost modeling of the systems simpler and faster and, while being useful for research works, it facilitates estimation and management of costs before implementation of each project.

کلیدواژه‌ها [English]

  • Economic modeling
  • Modern irrigation systems
  • Sensitivity analysis
  • Pattern recognition
  • Meta-heuristic algorithms

مراجع

  1. Ahiaga-Dagbui, D. D., and Smith, S. D. 2012. Neural networks for modelling the final target cost of water projects.
  2. Ahmadaali, K., Liaghat, A., Heydari, N., and Bozorg-Haddad, O. 2013. Application of artificial neural network and adaptive neural-based fuzzy inference system techniques in estimating of virtual water. International Journal of Computer Application, 76: 12-19.
  3. Alshahethi, A. A. A., and Radhika, K. L. 2018. Estimating the Final Cost of Construction Project Using Neural Networks: A Case of Yemen Construction Projects. International Journal for Research in Applied Science & Engineering Technology, 6(11): 2141-2151.
  4. Altarabichi, M. G., Nowaczyk, S., Pashami, S., and Mashhadi, P. S. 2023. Fast Genetic Algorithm for feature selection—A qualitative approximation approach. Expert Systems with Applications, 211: 118528.
  5. Alweshah, M. 2021. Solving feature selection problems by combining mutation and crossover operations with the monarch butterfly optimization algorithm. Applied Intelligence, 51(6): 4058-4081.
  6. Arora, S., and Mishra, N. 2017. Software cost estimation using single layer artificial neural network. International Journal of Advanced Engineering Research and Science, 4(9): 237250.
  7. Arora, S., and Mishra, N. 2018. Software cost estimation using artificial neural network. In Soft Computing: Theories and Applications (pp. 51-58). Springer, Singapore.
  8. Awad, M., and Khanna, R. 2015. Support vector regression. In efficient learning machines (pp. 67-80). Apress, Berkeley, CA.
  9. Babaei, M., Rashidi-baqhi, A., and Rashidi, M. 2022. Estimating Project Cost under Uncertainty Using Universal Generating Function Method. Journal of Construction Engineering and Management, 148(2): 04021194.
  10. Chandanshive, V., and Kambekar, A. R. 2019. Estimation of building construction cost using artificial neural networks. Journal of Soft Computing in Civil Engineering, 3(1): 91-107.
  11. Chandrashekar, G., and Sahin, F. 2014. A survey on feature selection methods. Computers & Electrical Engineering, 40(1): 16-28.
  12. Cheng, M. Y., Tsai, H. C., and Sudjono, E. 2010. Conceptual cost estimates using evolutionary fuzzy hybrid neural network for projects in construction industry. Expert Systems with Applications, 37(6): 4224-4231.
  13. Cortes, C., and Vapnik, V. 1995. Support-vector networks. Machine learning, 20(3): 273-297.
  14. Drenthe, N. T., Zandbergen, B. T. C., Curran, R., and Van Pelt, M. O. 2019. Cost estimating of commercial smallsat launch vehicles. Acta Astronautica, 155: 160-169.
  15. Elfaki, A. O., Alatawi, S., and Abushandi, E. 2014. Using intelligent techniques in construction project cost estimation: 10-year survey. Advances in Civil Engineering, 2014: 1-11.
  16. Elhag, T. M. S., and Boussabaine, A. H. 1998. An artificial neural system for cost estimation of construction projects. In 14th Annual ARCOM Conference (Vol. 1, pp. 219-226). University of Reading: Association of Researchers in Construction Management.
  17. Ghaddar, B., and Naoum-Sawaya, J. 2018. High dimensional data classification and feature selection using support vector machines. European Journal of Operational Research, 265(3): 993-1004.
  18. Ghaemi, M., and Feizi-Derakhshi, M. R. 2016. Feature selection using forest optimization algorithm. Pattern Recognition, 60: 121-129.
  19. Gransberg, D. D., and Rueda, J. A. 2020. Construction equipment management for engineers, estimators, and owners. CRC Press.
  20. Kashan, A. H. 2014. League Championship Algorithm (LCA): An algorithm for global optimization inspired by sport championships. Applied Soft Computing, 16: 171-200.
  21. Kiani, A., and Shaker, M. 2022. Evaluating the Effectiveness of Pressurized Irrigation Systems in Iran. Water Management in Agriculture, 8(2): 167-182. (In Persian)
  22. Kim, G. H., Shin, J. M., Kim, S., and Shin, Y. 2013. Comparison of school building construction costs estimation methods using regression analysis, neural network, and support vector machine. Journal of Building Construction and Planning Research, 1(1): 1-7.
  23. Lester, E. I. A. 2017. Estimating. In: Project management, planning and control. The Netherlands: Elsevier, 61–65.
  24. Liu, J., Lin, Y., Lin, M., Wu, S., and Zhang, J. 2017. Feature selection based on quality of information. Neurocomputing, 225: 11-22.
  25. Masoudi-Sobhanzadeh, Y., and Motieghader, H. 2016. World Competitive Contests (WCC) algorithm: A novel intelligent optimization algorithm for biological and non-biological problems. Informatics in Medicine Unlocked, 3: 15-28.
  26. Masoudi-Sobhanzadeh, Y., Motieghader, H., & Masoudi-Nejad, A. 2019. FeatureSelect: a software for feature selection based on machine learning approaches. BMC Bioinformatics, 20(1): 1-17.
  27. Matel, E., Vahdatikhaki, F., Hosseinyalamdary, S., Evers, T., and Voordijk, H. 2022. An artificial neural network approach for cost estimation of engineering services. International Journal of Construction Management, 22(7): 1274-1287.
  28. Metin, S. K. 2018. Feature selection in multiword expression recognition. Expert Systems with Applications, 92: 106-123.
  29. Mevellec, P. 2021. Cost systems: A new approach. Academia Letters, 2.
  30. Miao, J., and Niu, L. 2016. A survey on feature selection. Procedia Computer Science, 91: 919-926.
  31. Nalbandan, R. B., Delavar, M., Abbasi, H., and Zaghiyan, M. R. 2023. Model-based water footprint accounting framework to evaluate new water management policies. Journal of Cleaner Production, 382: 135220.
  32. Norvig, P. R., and Intelligence, S. A. 2002. A modern approach. Prentice Hall Upper Saddle River, NJ, USA: Rani, M., Nayak, R., & Vyas, OP (2015). An ontology-based adaptive personalized e-learning system, assisted by software agents on cloud storage. Knowledge-Based Systems, 90: 33-48.
  33. Omotayo, T., Bankole, A., and Olubunmi Olanipekun, A. 2020. An artificial neural network approach to predicting most applicable post-contract cost controlling techniques in construction projects. Applied Sciences, 10(15): 5171-5195.
  34. Panday, D., de Amorim, R. C., and Lane, P. 2018. Feature weighting as a tool for unsupervised feature selection. Information processing letters, 129: 44-52.
  35. Pazoki, M., Yadav, A., and Abdelaziz, A. Y. 2020. Pattern-recognition methods for decision-making in protection of transmission lines. In Decision making applications in modern power systems (pp. 441-472). Academic Press.
  36. Pourgholam-Amiji, M., Ahmadaali, K., and Liaghat, A. 2021a. Sensitivity Analysis of Parameters Affecting the Early Cost of Drip Irrigation Systems Using Meta-Heuristic Algorithms. Iranian Journal of Irrigation & Drainage, 15(4): 737-756. (In Persian)
  37. Pourgholam-Amiji, M., Liaghat, A., and Ahmadaali, K. 2021b. Early Stage Cost Modeling of Drip Irrigation Systems. Irrigation and Drainage Structures Engineering Research, 22(82): 1-22. (In Persian)
  38. Rahmaninia, M., and Moradi, P. 2018. OSFSMI: online stream feature selection method based on mutual information. Applied Soft Computing, 68: 733-746.
  39. Rastegar, R., Rahmati, M., and Meybodi, M. R. 2005. A clustering algorithm using cellular learning automata based evolutionary algorithm. In Adaptive and Natural Computing Algorithms (pp. 144-150). Springer, Vienna.
  40. Roxas, C. L. C., and Ongpeng, J. M. C. 2014. An artificial neural network approach to structural cost estimation of building projects in the Philippines. DLSU Res. Congr.
  41. Schubert, A. L., Hagemann, D., Voss, A., and Bergmann, K. 2017. Evaluating the model fit of diffusion models with the root mean square error of approximation. Journal of Mathematical Psychology, 77: 29-45.
  42. Sharma, A., Jain, A., Gupta, P., and Chowdary, V. 2020. Machine learning applications for precision agriculture: A comprehensive review. IEEE Access, 9: 4843-4873.
  43. Sheikhpour, R., Sarram, M. A., Gharaghani, S., and Chahooki, M. A. Z. 2017. A survey on semi-supervised feature selection methods. Pattern Recognition, 64: 141-158.
  44. Solorio-Fernández, S., Carrasco-Ochoa, J. A., and Martínez-Trinidad, J. F. (2020): A review of unsupervised feature selection methods. Artificial Intelligence Review, 53(2): 907-948.
  45. Talukdar, S., Naikoo, M. W., Mallick, J., Praveen, B., Sharma, P., Islam, A. R. M. T. ... and Rahman, A. 2022. Coupling geographic information system integrated fuzzy logic-analytical hierarchy process with global and machine learning based sensitivity analysis for agricultural suitability mapping. Agricultural Systems, 196: 103343.
  46. Teksin, S., Azginoglu, N., and Akansu, S. O. 2022. Structure estimation of vertical axis wind turbine using artificial neural network. Alexandria Engineering Journal, 61(1): 305-314.
  47. Thakkar, A., and Lohiya, R. 2023. Fusion of statistical importance for feature selection in Deep Neural Network-based Intrusion Detection System. Information Fusion, 90: 353-363.
  48. Venkatachalam, A. R. 1993. Software cost estimation using artificial neural networks. In Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan) (Vol. 1, pp. 987-990). IEEE.
  49. Waliulu, Y. E. P. R., and Adi, T. J. W. 2022. A system dynamic thinking for modeling infrastructure project duration acceleration. Procedia Computer Science, 197: 420-427.
  50. Winston, P. H. 1992. Artificial intelligence. Addison-Wesley Longman Publishing Co., Inc.
  51. Yadav, R., Vyas, M., Vyas, V., and Agrawal, S. 2016. Cost estimation model (CEM) for residential building using artificial neural network. International Journal of Engineering Research & Technology (IJERT), 5(1): 430-432.
پژوهش آب در کشاورزی
دوره 36، شماره 4
اسفند 1401
صفحه 421-440

فایل ها

هم رسانی

ارجاع به این مقاله

آمار