İşletmeler için Personel Yemek Talep Miktarının Yapay Sinir Ağları Kullanılarak Tahmin Edilmesi

Öz

Günümüzde kamu veya özel kurumların birçoğu, bünyelerinde çalışan personeller için profesyonel yemek hizmeti vermektedir. Söz konusu hizmetin planlanması konusunda, kurumlarda çalışan personel sayısının genel olarak fazla olması ve personellerin şahsi veya kuruma ait sebeplerle kurum dışında olmalarından dolayı birtakım aksamalar yaşanmaktadır. Bu yüzden, günlük yemek talebinin belirlenmesi zorlaşmakta ve bu durum kurumlar için maliyet, zaman ve emek kaybına sebep olmaktadır. Bu kayıpları ortadan kaldırmak veya en azından minimuma indirmek amacıyla istatistiksel veya sezgisel yöntemler kullanılmaktadır. Bu çalışmada, işletmeler için yapay sinir ağları kullanılarak günlük yemek talebini tahmin eden yapay zekâ tabanlı bir model önerilmiştir. Veriler, günlük yemek çıkaran ve farklı kademlerde görev alan 110 kişilik bir personel kapasitesine sahip özel bir işletmenin yemekhane veritabanından elde edilmiş olup son 2 yıllık (2016-2018) veriyi kapsamaktadır. Model, MATLAB paket programı kullanılarak oluşturulmuştur. Modelin performansı, Regresyon değerleri, Ortalama Mutlak Hata Yüzdesi (OMHY-MAPE) ve Ortalama Karesel Hata (OKH-MSE) dikkate alınarak belirlenmiştir. Ağın eğitiminde, ileri beslemeli geri yayılımlı ağ mimarisi kullanılmıştır. Denemeler sonucunda elde edilen en iyi model, sırasıyla eğitim R oranı: 0,9948, test R oranı: 0,9830 ve hata oranı ise 0,003783 olup çok katmanlı (8-10-10-1) bir yapıya sahiptir. Deney sonuçları, modelin hata oranının düşük, performansının yüksek olduğunu ve talep tahmini için yapay sinir ağları kullanımının olumlu etkisini ortaya koymuştur.

Anahtar Kelimeler

• İşletme,yapay sinir ağları,yemek,talep,tahmin

An Estimation of Personnel Food Demand Quantity for Businesses by Using Artificial Neural Networks

Öz

Today, many public or private institutions provide professional food service for personnels working in their own organizations. Regarding the planning of the said service, there are some obstacles due to the fact that the number of the personnel working in the institutions is generally high and the personnel are out of the institution due to personal or institutional reasons. Because of this, it is difficult to determine the daily food demand, and this causes cost, time and labor loss for the institutions. Statistical or heuristic methods are used to remove or at least minimize these losses. In this study, an artificial intelligence model was proposed, which estimates the daily food demand quantity using artificial neural networks for businesses. The data are obtained from a refectory database of a private institution with a capacity of 110 people serving daily meals and serving at different levels, covering the last two years (2016-2018). The model was created using the MATLAB package program. The performance of the model was determinde by the Regression values,  the Mean Absolute Percentage Error (MAPE) and the Mean Squared Error (MSE). In the training of the ANN model, feed forward back propagation network architecture is used. The best model obtained as a result of the experiments is a multi-layer (8-10-10-1) structure with a training R ratio of 0,9948, a testing R ratio of 0,9830 and an error rate of 0,003783, respectively. Experimental results demonstrated that the model has low error rate, high performance and positive effect of using artificial neural networks for demand estimating.

Anahtar Kelimeler

• Business,artificial neural networks,food,demand,estimation

Kaynakça

1. [1] Kılıç G., “Yapay Sinir Ağları İle Yemekhane Günlük Talep Tahmini”, Yüksek Lisans Tezi, Pamukkale Üniversitesi Fen Bilimleri Enstitüsü, (2015).
2. [2] Bulut Ş., "Orta Ölçekli Bir İşletmede Talep Tahmin Yöntemlerinin Uygulanması", Yüksek Lisans Tezi, Kırıkkale Üniversitesi Endüstri Mühendisliği Anabilim Dalı, Kırıkkale, (2006).
3. [3] Karaatli M., Helvacioğlu Ö. C., Ömürbek N., & Tokgöz G., “Yapay Sinir Ağları Yöntemi İle Otomobil Satış Tahmini”, Uluslararası Yönetim İktisat ve İşletme Dergisi, 8(17): 87-100, (2012).
4. [4] Aydinalp-Koksal M., & Ugursal V. I. “Comparison of neural network, conditional demand analysis, and engineering approaches for modeling end-use energy consumption in the residential sector”, Applied Energy, 85(4): 271-296, (2008).
5. [5] Murat Y. S., & Ceylan H., “Use of artificial neural networks for transport energy demand modeling”, Energy policy, 34(17): 3165-3172, (2006).
6. [6] Geem Z. W., & Roper W. E., “Energy demand estimation of South Korea using artificial neural network”, Energy policy, 37(10): 4049-4054, (2009).
7. [7] Dogan E., Sengorur B., & Koklu R., “Modeling biological oxygen demand of the Melen River in Turkey using an artificial neural network technique”, Journal of Environmental Management, 90(2): 1229-1235, (2009).
8. [8] Karahan M., "Yapay Sinir Ağları Metodu ile Ürün Talep Tahmini", Doktora Tezi, Selçuk Üniversitesi Sosyal Bilimler Ens. İşletme Anabilim Dalı, Konya, (2011).

9. [9] Sonmez M., Akgüngör A. P., & Bektaş S., “Estimating transportation energy demand in Turkey using the artificial bee colony algorithm”, Energy, 122, 301-310, (2017).
10. [10] Zeng Y. R., Zeng Y., Choi B., & Wang L., “Multifactor-influenced energy consumption forecasting using enhanced back-propagation neural network”, Energy, 127, 381-396, (2017).
11. [11] Moradi S., Liu S., Chow C. W., van Leeuwen J., Cook D., Drikas M., & Amal R., “Chloramine demand estimation using surrogate chemical and microbiological parameters”, Journal of Environmental Sciences, 57, 1-7, (2017).
12. [12] Ahmed A. M., “Prediction of dissolved oxygen in Surma River by biochemical oxygen demand and chemical oxygen demand using the artificial neural networks (ANNs)”, Journal of King Saud University-Engineering Sciences, 29(2): 151-158, (2017).
13. [13] Ay M., & Kişi Ö., “Estimation of dissolved oxygen by using neural networks and neuro fuzzy computing techniques”, KSCE Journal of Civil Engineering, 21(5): 1631-1639, (2017).
14. [14] Khoshravesh M., Sefidkouhi M. A. G. & Valipour M., “Estimation of reference evapotranspiration using multivariate fractional polynomial, Bayesian regression, and robust regression models in three arid environments”, Applied Water Science, 7(4): 1911-1922, (2017).
15. [15] Dogan H., Atik K., “Providing Persistance in Comfort Conditions by the Applicatıon of Artifıcial Neural Networks to Air-Conditioning Systems”, Technology, 7(2): (2004).
16. [16] Ataman F., Kaynak T., Yüncü S., “Analysing of Solutions Containing Artificial Intelligence Through System Modeling on Computer”, Electrical, Electronic and Computer Engineering 8th National Congress, s.677, Gaziantep, (1998).
17. [17] Demir Y., Tuntaş R., Köksal M., “Analysis of Switched Circuit with Neural Networks”, Electrical and Computer Engineering 8th National Congress, s 673, Gaziantep, (1998).
18. [18] Kalogirou S. A., Bojic M., “Artificial neural networks for the prediction of the energy consumption of a passive solar building”, Energy, 25(5): 479-491, (2000).
19. [19] Bayram S., Kaplan K., Kuncan M., Ertunç H. M., “Ball Bearings space of time Statistical Feature Extraction and Neural Networks with Error Estimation Method Size”, Automatic Control National Meeting, TOK2013, Malatya, 26-28 September, (2013).
20. [20] Sahin I., “Estimation of Surface Roughness of Al/Sic Composite Material with Artifıcial Neural Networks”, Journal of the Faculty of Engineering and Architecture of Gazi University, 29(1): 209-216, (2014).
21. [21] Ozdemir V., “Determination of Turkey's Carbonization Index Based on Basic Energy Indicators by Artificial Neural Networks”, Journal of the Faculty of Engineering and Architecture of Gazi University, 26(1): 9-15, (2011).
22. [22] Eker M., Dikmen M., Cambazoglu S., Duzgun S. H. and Akgun H., “Application of Artificial Neural Network and Logistic Regression Methods to Landslide Susceptibility Mapping and Comparison of the Results for the Ulus District”, Bartin Journal of the Faculty of Engineering and Architecture of Gazi University, 27(1): 163-173, (2012).
23. [23] Karahan M., “A Case Study on Forecasting of Tourism Demand With Artificıal Neutral Network Method”, Suleyman Demirel University The Journal of Faculty of Economics and Administrative Sciences, 20(2): 195-209, (2015).
24. [24] Efendigil T., Önüt S., & Kahraman C., “A decision support system for demand forecasting with artificial neural networks and neuro-fuzzy models: A comparative analysis”, Expert Systems with Applications, 36(3): 6697-6707, (2009).
25. [25] Yıldız B., “Using Artificial Neural Network for Estimation of Financial Failure and an Empirical Application in Public Companies”, Journal of IMKB, 5(17): 51-67, (2001).
26. [26] Neseli S., Tasdemir S. and Yaldız S., “Estimation of surface roughness on turning with Artificıal Neural Network”, Journal of Engineering and Architecture Faculty of Eskisehir Osmangazi University, XXII, 3, 65-75, (2009).
27. [27] Kalogirou S. A., “Artificial intelligence for the modeling and control of combustion processes: a review”, Progress in Energy and Combustion Science, 29(6): 515-566, (2003).
28. [28] Fındık T., Taşdemir Ş. & Şahin I., “The use of artificial neural network for prediction of grain size of 17-4 pH stainless steel powders”, Scientific Research and Essays, 5(11): 1274-1283, (2010).
29. [29] Askin D., Iskender I. & Mamizadeh A., “Dry type transformer winding thermal analysis using different neural network methods”, Journal of the Faculty of Engineering and Architecture of Gazi University, 26(4): 905-913, (2011).
30. [30] Karataş C., Sozen A. & Dulek E., “Modelling of residual stresses in the shot peened material C-1020 by artificial neural network”, Expert Systems with Applications, 36(2): 3514-3521, (2009).
31. [31] Hamzacebi C. & Kutay F., “Electric Consumption Forecasting of Turkey Using Artificial Neural Networks Up to Year 2000”, J. Fac. Eng. Arch. Gazi Univ, 19(3): 227-233, (2004).
32. [32] Huang J., Li Y. F. & Xie M., “An empirical analysis of data preprocessing for machine learning-based software cost estimation”, Information and Software Technology, 67: 108-127, (2015).
33. [33] Calp M. H., “Yazılım Projeleri İçin Yapay Zekâ Tabanlı Risk Yönetimi”, Doktora Tezi, Gazi Üniversitesi, Bilişim Enstitüsü, Yönetim Bilişim Sistemleri A.B.D., (2017).
34. [34] Erdal H., “Contribution of Machine Learning Methods to the Construction Industry: Estimation of Compressive Strength”, Pamukkale University Journal of Engineering Sciences, 21(3): 109-114, (2015).
35. [35] Turhan C., Akkurt G.G., Kazanasmaz T., “Predicting with Artificial Neural Networks Total Energy Consumption of High Rises in Izmir”, Journal of Installation Engineering, Vol: 134 , 61-68, (2013).
36. [36] Özkan M. T., Eldem C., & Köksal E., “Notch Sensitivity Factor Determination with Artificial Neural Network for Shafts under the Bending Stress”, Pamukkale University Journal of Engineering Sciences, 19(1): 24-32, (2013).
37. [37] Gandomi H. & Roke D. A., “Assessment of artificial neural network and genetic programming as predictive tools”, Advances in Engineering Software, 88: 63-72, (2015).