پیش‌بینی تقاضا در سیستم‌های رزرواسیون دانشگاهی با هدف کاهش ضایعات مواد غذایی به‌کمک شبکه‌های عصبی با تابع خطای موزون

نوع مقاله : مقاله علمی پژوهشی

نویسندگان

1 دانشجوی دکتری، گروه مدیریت، دانشکده علوم اداری و اقتصادی، دانشگاه فردوسی مشهد، مشهد، ایران.

2 استاد، گروه مدیریت، دانشکده علوم اداری و اقتصادی، دانشگاه فردوسی مشهد، مشهد، ایران.

3 استادیار، گروه یادگیری، تحلیل داده و فناوری، دانشگاه توئنته، انسخده، هلند.

چکیده

هدف: یکی از دغدغه‌های مهم در رزرواسیون غذای دانشگاهی، مراجعه‌نکردن بسیاری از دانشجویان است که با توجه به دریافت یارانه دولتی و قیمت ارزان غذا، انبوهی از مواد غذایی هدر رفته و به ضایعات تبدیل می‌شود. هدف اصلی این پژوهش، جلوگیری از تولید ضایعات مواد غذایی در دانشگاه‌ها، به‌کمک پیش‌بینی تقاضای واقعی است.
روش: برای مدل‌سازی و حل مسئله، از شبکه عصبی مصنوعی با تابع خطای موزونی که به‌کمک جست‌وجوی الگوی تعمیم‌یافته جهت‌دهی می‌شود، استفاده شد. شاخص‌های مجموع رزرو، روز هفته، سطح قیمت وعده، مجموع تعداد رزرو، تعداد رزرو به‌تفکیک مقطع تحصیلی، تعداد رزرو به‌تفکیک وضعیت اسکان و غذای مجاور به‌عنوان متغیرهای ورودی و تعداد تقاضای واقعی غذا نیز شاخص خروجی در نظر گرفته شد.
یافته‌ها: داده‌های هفت سال اخیر سامانه رزرواسیون سلف مرکزی یکی از دانشگاه‌های بزرگ کشور که سالانه به‌طور متوسط پتانسیل تولید ۵۶ هزار پرس غذای مازاد (بیش از ۲۳ هزار تن مواد غذایی) را دارد، بررسی شد. با آموزش یک شبکه عصبی مصنوعی توأم با بهینه‌سازی GPS، الگوریتم ترکیبی با تابع خطای موزون متناسبی به‌دست آمد که قادر است تولید روزانه غذای مازاد را بیش از ۸۰درصد کاهش دهد.
نتیجه‌گیری: با استفاده از مدل ارائه شده، می‌توان تقاضای واقعی را به‌طور دقیق‌تر تخمین زد. مدل پیشنهادی، ضمن معرفی شاخص‌های مؤثر بر تخمین تقاضا، قادر است که در سطوح ریسک مختلف مورد انتظار دانشگاه، تقاضاهای واقعی را برآورد کند. این رویکرد پیشگیرانه، وعده‌های غذایی کنترل شده را فقط به اندازه احتیاج تولید و توزیع خواهد کرد تا از ضایعات مواد غذایی یا اتلاف بودجه عمومی کشور جلوگیری شود.

کلیدواژه‌ها


عنوان مقاله [English]

Demand Prediction in University Booking Systems to Reduce Food Waste Using Neural Networks Including Weighted Error Function

نویسندگان [English]

  • Mohammadali Faezirad 1
  • Alireza Pooya 2
  • Zahra Naji-Azimi 2
  • Maryam Amir Haeri 3
1 Ph.D. Candidate, Department of Management, Faculty of Economics and Administrative Science, Ferdowsi University of Mashhad, Mashhad, Iran.
2 Prof., Department of Management, Faculty of Economics and Administrative Science, Ferdowsi University of Mashhad, Mashhad, Iran.
3 Assistant Prof., Department of Learning, Data-Analytics and Technology, University of Twente, Enschede, Netherlands.
چکیده [English]

Objective: A significant challenge in the university meal booking is the high No-Show rate that leads to considerable food waste in consequence of facing low price of nutrition system and government subsidizing. This study aims to prevent food waste in university dining halls via predicting actual demand.
Methods: To model and solve the problem, an Artificial Neural Network has been used that was performed by weighting the error function with Generalized Pattern Search (GPS). Date, the day of the week, the price level of Food, total number of reservations, total number of reservations by undergraduate students, Masters' students, PhD students and dormitory students and the parallel food have been considered as inputs of the model. The output is the actual demands based on Show's number.
Results: The seven-year data of the meal booking system of a large university in Iran has been examined. This data demonstrated that the food waste rate is close to 10% of the total food reservations. An artificial neural network including weighted error function under GPS optimization was obtained to predict actual demand. Finally, the results of training indicated over 80% waste reduction in surplus daily food production.
Conclusion: The proposed model has the potential to provide an estimation of actual demand. Although adding indicators that influence demand estimation, the proposed model is able to change the actual demand prediction at various levels of risk expected by the university. To avoid food waste and prevent the loss of government subsidies, this precautionary approach can control overproduction.

کلیدواژه‌ها [English]

  • Meal Booking
  • food waste
  • Artificial Neural Networks
  • Weighted Error Function
  • Pattern Search Algorithm
امین ‌ناصری، محمدرضا؛ بهنام، فرنام (۱۳۹۱). پیش بینی تقاضای سفر ریلی در مسیر تهران-مشهد. پژوهشنامه حمل و نقل، ۹(۱)، ۱۵-۲۸.
سیفی، زهرا (۱۳۹۹). نرخ مصوب قیمت غذای دانشجویی به دانشگاه‌ها ابلاغ شد. خبرگزاری مهر. ۲۶ شهریور. دسترسی در آدرس: https://www.mehrnews.com/news/5024681
قانون برنامه پنج‌ساله ششم توسعه اقتصادی، اجتماعی و فرهنگی جمهوری اسلامی ایران (۱۳۹۶). دسترسی در آدرس: https://rc.majlis.ir/fa/law/show/1014547
کاظمی، مصطفی؛ فائضی راد، محمدعلی (1397). پیش‌بینی کارایی به کمک تأثیرپذیری غیرخطی از تأخیرهای زمانی در تحلیل پوششی داده‌ها با شبکه‌های عصبی مصنوعی. مدیریت صنعتی، 10(1)، 17-34.
مردانه، الهام؛ اکبری جوکار، محمدرضا (۱۳۸۵). توسعه و به‌کارگیری تکنیک مدیریت درآمد در سیستم‌های تولید انبارشی. مهندسی صنایع و مدیریت، ۲۲(۳۴)، 87-96.
هزینه ناهار و شام دانشجویی هزار میلیارد تومان! (۱۳۹۸، ۱ مرداد). روزنامه شهروند، ص ۱۲.
 
References
Abdelaal, A. H., McKay, G., & Mackey, H. R. (2019). Food waste from a university campus in the Middle East: Drivers, composition, and resource recovery potential. Waste Management, 98, 14-20.
Ali, A. Y., Hassen, J. M., & Wendem, G. G. (2019). Forecasting as a framework for reducing food waste in Ethiopian university canteens. Journal of Applied Research on Industrial Engineering, 6(4), 374-380.
Alooh, A. O. (2015). Quantifying food plate waste: case study of a university dining facility Doctoral dissertation, Stellenbosch: Stellenbosch University.
Amin-Naseri, M. & Behnam, F. (2012) Forecastin the Travel Demand for Tehran-Mashhad Rail Route. Journal of Transportation Research, 9(1), 15-28. (in Persian)
Arabani, S. P., & Komleh, H. E. (2019). The improvement of forecasting ATMS cash demand of Iran banking network using convolutional neural network. Arabian Journal for Science and Engineering, 44(4), 3733-3743.
Audet, C., & Dennis, Jr., J. E. (2000). Pattern search algorithms for mixed variable programming. SIAM Journal on Optimization, 11(3), 573–594.
Azadeh, S. S., Marcotte, P., & Savard, G. (2014). A taxonomy of demand uncensoring methods in revenue management. Journal of Revenue and Pricing Management, 13(6), 440-456.
Azadeh, S. S., Marcotte, P., & Savard, G. (2015). A non-parametric approach to demand forecasting in revenue management. Computers & Operations Research, 63, 23-31.
Bagheri, A., Nazari, A., & Sanjayan, J. (2019). The use of machine learning in boron-based geopolymers: Function approximation of compressive strength by ANN and GP. Measurement, 141, 241-249.
Blecher, L., & Yeh, R. J. (2008). Forecasting meal participation in university residential dining facilities. Journal of Foodservice Business Research, 11(4), 352-362.
Bogani, C., Gasparo, M. G. & Papini, A. (2009). Generalized Pattern Search methods for a class of nonsmooth optimization problems with structure. Journal of Computational and Applied Mathematics, 229(1), 283-293.
Çetinkaya, Z., & Erdal, E. (2019, September). Daily Food Demand Forecast with Artificial Neural Networks: Kırıkkale University Case. In 2019 4th International Conference on Computer Science and Engineering (UBMK) (pp. 1-6). IEEE.
Gallardo, A., Edo-Alcón, N., Carlos, M., & Renau, M. (2016). The determination of waste generation and composition as an essential tool to improve the waste management plan of a university. Waste management, 53, 3-11.
Gao, A., Tian, Z., Wang, Z., Wennersten, R., & Sun, Q. (2017). Comparison between the technologies for food waste treatment. Energy Procedia, 105, 3915-3921.
Gregorash, B. J. (2016). Restaurant revenue management: apply reservation management. Information Technology & Tourism, 16(4), 331-346.
Hillier, F. S. & Lieberman, G. J. (2015). Introduction to Operations Research. 10th Edition. New York: McGraw-Hill Education.
Hine, J., & Grieco, M. (2003). Scatters and clusters in time and space: implications for delivering integrated and inclusive transport. Transport Policy, 10(4), 299-306.
Ihme, M., Marsden, A. L. & Pitsch, H. (2008). Generation of Optimal Artificial Neural Networks Using a Pattern Search Algorithm: Application to Approximation of Chemical Systems. Neural Computation, 20, 573–601.
Jung, S., & Kwon, S. D. (2013). Weighted error functions in artificial neural networks for improved wind energy potential estimation. Applied energy, 111, 778-790.
Kazemi, A., Shakouri, H. G., Menhaj, M. B., Mehregan, M. R., & Neshat, N. (2010). A hierarchical artificial neural network for transport energy demand forecast: Iran case study. Neural Network World, 20(6), 761-772.
Kazemi, M. & Faezirad, M. (2018). Efficiency Estimation using Nonlinear Influences of Time Lags in DEA Using Artificial Neural Networks. Industrial Management Journal, 10(1), 17-34.
Ke, J., Zheng, H., Yang, H., & Chen, X. (2017). Short-term forecasting of passenger demand under on-demand ride services: A spatio-temporal deep learning approach. Transportation Research Part C: Emerging Technologies, 85, 591-608.
Kılıç, G. (2015). Yapay Sinir Ağlari ile Yemekhane Günlük Talep Tahmini. Master's thesis, Pamukkale Üniversitesi Fen Bilimleri Enstitüsü.
Kochenderfer, M. J., & Wheeler, T. A. (2019). Algorithms for optimization. Cambridge, MA: The MIT Press.
Law, R., Li, G., Fong, D. K. C., & Han, X. (2019). Tourism demand forecasting: A deep learning approach. Annals of Tourism Research, 75, 410-423.
Lazell, J. (2016). Consumer food waste behaviour in universities: Sharing as a means of prevention. Journal of Consumer Behaviour, 15(5), 430-439.
Lemke, C., Riedel, S., & Gabrys, B. (2013). Evolving forecast combination structures for airline revenue management. Journal of Revenue and Pricing Management, 12(3), 221-234.
Liu, W., Yang, H., & Yin, Y. (2015). Efficiency of a highway use reservation system for morning commute. Transportation Research Part C: Emerging Technologies, 56, 293-308.
Lolli, F., Gamberini, R., Regattieri, A., Balugani, E., Gatos, T., & Gucci, S. (2017). Single-hidden layer neural networks for forecasting intermittent demand. International Journal Of Production Economics, 183, 116-128.
Lowe, D. (2013). Integrating Reservations and Queuing in Remote Laboratory Scheduling. IEEE Transactions on Learning Technologies, 6(1), 73-84.
MacDonald, L., Rotteveel, L., Selim-Omar, J., Brown, N., Qin, S., & Allen, S. (2017). Food wasting attitudes and behaviours among residence meal hall users at Dalhousie University, Halifax, Nova Scotia.
Managing food waste in the NHS. (2005). Nutrition & Food Science, 35(5). https://doi.org/10.1108/nfs.2005.01735eab.010.
Marais, M. L., Smit, Y., Koen, N., & Lötze, E. (2017). Are the attitudes and practices of foodservice managers, catering personnel and students contributing to excessive food wastage at Stellenbosch University? South African Journal of Clinical Nutrition, 30(3).
Mardane, A., Akbari Jokar, M. (2006). Revenue Management in Make to Stock Manufacturing Systems. Sharif Journal of Industrial Engineering & Management, 22(34), 87-96.
(in Persian)
Miriyala, S. S., Subramanian, V., & Mitra, K. (2018). TRANSFORM-ANN for online optimization of complex industrial processes: Casting process as case study. European Journal of Operational Research, 264(1), 294-309.
MIT University. (2020, July 07). Further decisions about the fall semester. Retrieved from https://president.mit.edu/speeches-writing/further-decisions-about-fall-semester.
Mu, D., Horowitz, N., Casey, M., & Jones, K. (2017). Environmental and economic analysis of an in-vessel food waste composting system at Kean University in the US. Waste management, 59, 476-486.
Muralitharan, K., Sakthivel, R., & Vishnuvarthan, R. (2018). Neural network based optimization approach for energy demand prediction in smart grid. Neurocomputing, 273, 199-208.
Ozcicek-Dolekoglu, C., & Var, I. (2019). Analysis of food waste in university dining halls: A case study from turkey. Fresenius Environ. Bull, 28, 156-166.
Painter, K., Thondhlana, G., & Kua, H. W. (2016). Food waste generation and potential interventions at Rhodes University, South Africa. Waste Management, 56, 491-497.
Panesar, K. (2020). Implementation of Full-Scale Anaerobic Digestion of Food Waste at the University of South Florida (Doctoral dissertation, University of South Florida).
Pasupa, K., & Sunhem, W. (2016, October). A comparison between shallow and deep architecture classifiers on small dataset. In 2016 8th International Conference on Information Technology and Electrical Engineering (ICITEE) (pp. 1-6). IEEE.
Pinto, R. S., dos Santos Pinto, R. M., Melo, F. F. S., Campos, S. S., & Cordovil, C. M. D. S. (2018). A simple awareness campaign to promote food waste reduction in a University canteen. Waste management, 76, 28-38.
Pirani, S. I., Arafat, H., & Thompson, G. (2016). FRESH: A Food-service Sustainability Rating for Hospitality Sector Events. Available in: https://ecommons.cornell.edu/handle /1813/71008
Qiao, J., Guo, X., & Li, W. (2020). An online self-organizing modular neural network for nonlinear system modeling. Applied Soft Computing, 97, 106777.
Seyfi, Z. (2020). The approved rate of student food prices was announced to the universities. Mehr News Agency. September 16. Available from: https://www.mehrnews.com/news/5024681. (in Persian)
Steen, H., Malefors, C., Röös, E., & Eriksson, M. (2018). Identification and modelling of risk factors for food waste generation in school and pre-school catering units. Waste Management, 77, 172-184.
Talluri, K. T., & Van Ryzin, G. (2004). The Theory and Practice of Revenue Management. New York: Kluwer Academic Publishers.
The cost of student lunch and dinner is one thousand billion tomans! (2019, July 23). Shahrvand Newspaper, p.12. (in Persian)
The Law on the Sixth Five-Year Economic, Cultural and Social Development Plan for 2017-2021. (2017) (in Persian)
Tsai, T. (2014). A self-learning advanced booking model for railway arrival forecasting. Transportation Research Part C: Emerging Technologies, 39, 80-93.
Whitehair, K. J., Shanklin, C. W., & Brannon, L. A. (2013). Written messages improve edible food waste behaviors in a university dining facility. Journal of the Academy of Nutrition and Dietetics, 113(1), 63-69.
Yang, H., & Wang, F. (2019). Wireless network intrusion detection based on improved convolutional neural network. Ieee Access, 7, 64366-64374.
Yang, S., Ting, T. O., Man, K. L., & Guan, S. U. (2013). Investigation of neural networks for function approximation. Procedia Computer Science, 17, 586-594.
Yergök, D., Güven, C., & Acı, M. (2018). Artificial Neural Network Model Design for Daily Demand Prediction in Mass Meal Production. ICATCES'18, http://apbs.mersin.edu.tr/files/maci/Scientific_Meetings_001.pdf.
Yousefi, M., Yousefi, M., Fathi, M. and Fogliatto, F.S. (2020). Patient visit forecasting in an emergency department using a deep neural network approach. Kybernetes, 49(9), 2335-2348.
Yurtsever, M., & Tecim, V. (2020). Forecasting Meal Requirements Using Time Series Methods in Organization. In Economic and Financial Challenges for Balkan and Eastern European Countries (pp. 243-254). Springer, Cham.
Zhang, G. P. (2001). An investigation of neural networks for linear time-series forecasting. Computers & Operations Research, 28(12), 1183-1202.
Zhang, J., Che, H., Chen, F., Ma, W., & He, Z. (2021). Short-term origin-destination demand prediction in urban rail transit systems: A channel-wise attentive split-convolutional neural network method. Transportation Research Part C: Emerging Technologies, 124, 102928.
Zhao, Y., Triantis, K., Teodorović, D., & Edara, P. (2010). A travel demand management strategy: The downtown space reservation system. European Journal of Operational Research, 205(3), 584-594.