Etlik Piliç Büyüme Eğrisinin Tahmininde Yapay Zeka ve Doğrusal Olmayan Modellerin Karşılaştırmalı Analizi

Year 2021, Volume: 7 Issue: 3, 515 - 523, 30.12.2021

Erdem Küçüktopcu , Bilal Cemek

https://doi.org/10.24180/ijaws.990297

Cited By: 1

Abstract

Büyüme modelleri için çok sayıda matematiksel ifade geliştirilmiştir, ancak her birinin kendine has özellikleri ve sınırlamaları bulunmaktadır. Dolayısıyla bu çalışmada yapay zeka (YZ) yöntemlerinin bu modellere alternatif olup olamayacağı araştırılmıştır. Bu amaçla büyümeyi analiz etmek için dört farklı doğrusal olmayan model (NL) (lojistik, Richards, Gompertz-Laird ve von Bertalanffy) ve üç farklı YZ tekniği - yapay sinir ağları (YSA) ve uyarlamalı sinirsel bulanık çıkarım sisteminin farklı yöntemleri ( ızgara bölümleme (ANFIS-GP) ve eksiltici kümeleme (ANFIS-SC)) kullanılmıştır. Modellerin performansını değerlendirmek için ortalama mutlak hata (MAE), ortalama karekök hata (RMSE) ve ortalama mutlak yüzde hata (MAPE) gibi bazı istatistiksel yöntemler ele alınmıştır. Çalışma sonucunda ANFIS-SC modelinin en düşük MAE, RMSE ve MAPE değerleri (sırasıyla 7.68 g, 11.93 g ve %1.06) ile gerçek ağırlık verileriyle daha iyi uyum sağladığı tespit edilmiştir. Sonuç olarak YZ modellerinin etlik piliç büyüme eğrisini belirlemek için alternatif olarak kullanılabileceği belirlenmiştir.

Keywords

Büyüme eğrisi, etlik piliç, yapay zeka, regresyon modeli

Supporting Institution

Ondokuz Mayıs University

Project Number

PYO.ZRT.1901.18.018

Comparative Analysis of Artificial Intelligence and Nonlinear Models for Broiler Growth Curve

Abstract

Numerous mathematical expressions for growth models have been developed, but each has its own characteristics and limitations. Therefore, this study has investigated whether artificial intelligence (AI) methods can be an alternative to these models. To this aim, four nonlinear (NL) models (logistic, Richards, Gompertz-Laird, and von Bertalanffy) and three AI techniques — artificial neural networks (ANN), integrated adaptive neuro-fuzzy inference systems with grid partitioning and subtractive clustering (ANFIS-GP and ANFIS-SC) — were used to analyze growth. Some statistical methods, including the mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE) were used to evaluate the model performance. As a result of the study, it was determined that the ANFIS-SC model yielded a better fit with the broiler data due to its low MAE, RMSE, and MAPE values (7.68 g, 11.93 g, and 1.06%, respectively). The overall recommendation of this study is that the AI models could be used as an alternative to determine a broiler growth curve.

Keywords

Growth curve, broiler, artificial intelligence, regression model

Project Number

PYO.ZRT.1901.18.018

References

• Abdurofi, I., Ismail, M. M., Kamal, H., & Gabdo, B. (2017). Economic analysis of broiler production in Peninsular Malaysia. International Food Research Journal, 24(2), 761-766.
• Adenaike, A. S., Akpan, U., Udoh, J. E., Wheto, M., Durosaro, S. O., Sanda, A. J., & Ikeobi, C. O. N. (2017). Comparative evaluation of growth functions in three broiler strains of nigerian chickens. Pertanika Journal of Tropical Agricultural Science, 40(4), 611-620.
• Ahmad, H. (2009). Poultry growth modeling using neural networks and simulated data. Journal of Applied Poultry Research, 18(3), 440-446.
• Balcioğlu, M. S., Kizilkaya, K., Karabağ, K., Alkan, S., Yolcu, H. İ., & Şahin, E. (2009). Comparison of growth characteristics of chukar partridges (Alectoris chukar) raised in captivity. Journal of Applied Animal Research, 35(1), 21-24.
• Berberoğlu, E., & Özkan, N. (2020). Estimation and comparison of growth curve in broilers through the artificial neural networks and gompertz models. Journal of Agricultural Faculty of Gaziosmanpasa University, 37(2), 68-76.
• Cetin, M., Sengul, T., Sogut, B., & Yurtseven, S. (2007). Comparison of growth models of male and female partridges. Journal of Biological Sciences, 7(6), 964-968.
• Chang, H.S. (2007). Overview of the world broiler industry: Implications for the Philippines. Asian Journal of Agriculture and Development, 4, 67-82.
• Demuner, L. F., Suckeveris, D., Muñoz, J. A., Caetano, V. C., Lima, C. G. D., Faria, D. E. D., & Faria, D. E. D. (2017). Adjustment of growth models in broiler chickens. Pesquisa Agropecuária Brasileira, 52, 1241-1252.
• Eleroğlu, H., Yıldırım, A., Şekeroğlu, A., Çoksöyler, F. N., & Duman, M. (2014). Comparison of growth curves by growth models in slow-growing chicken genotypes raised the organic system. International Journal of Agriculture and Biology, 16(3), 529-535.
• Haykin, S. (2010). Neural Networks and Learning Machines. Pearson Education, New Jersey.
• Koushandeh, A., Chamani, M., Yaghobfar, A., Sadeghi, A., & Baneh, H. (2019). Comparison of the accuracy of nonlinear models and artificial neural network in the performance prediction of Ross 308 broiler chickens. Poultry Science Journal, 7(2), 151-161.
• Narinc, D., Karaman, E., Aksoy, T., & Firat, M. Z. (2014). Genetic parameter estimates of growth curve and reproduction traits in Japanese quail. Poultry Science, 93(1), 24-30.
• Norris, D., Ngambi, J. W., Benyi, K., Makgahlele, M. L., Shimelis, H. A., & Nesamvuni, E. A. (2007). Analysis of growth curves of indigenous male Venda and Naked Neck chickens. South African Journal of Animal Science, 37(1), 21-26.
• Mouffok, C., Semara, L., Ghoualmi, N., & Belkasmi, F. (2019). Comparison of some nonlinear functions for describing broiler growth curves of Cobb500 strain. Poultry Science Journal, 7(1), 51-61.
• Porter, T., Kebreab, E., Kuhi, H. D., Lopez, S., Strathe, A. B., & France, J. (2010). Flexible alternatives to the Gompertz equation for describing growth with age in turkey hens. Poultry Science, 89(2), 371-378.
• Raji, A., Alade, N., & Duwa, H. (2014). Estimation of model parameters of the Japanese quail growth curve using Gompertz model. Archivos de zootecnia, 63(243), 429-435.
• Roush, W., Dozier, W., & Branton, S. (2006). Comparison of Gompertz and neural network models of broiler growth. Poultry Science, 85(4), 794-797.
• Sariyel, V., Aygun, A., & Keskin, I. (2017). Comparison of growth curve models in partridge. Poultry Science, 96(6), 1635-1640.
• Shanmuganathan, S. (2016). Artificial neural network modelling: An introduction. In S. Shanmuganathan, & S. Samarasinghe (Eds.), Artificial Neural Network Modelling. Studies in Computational Intelligence (pp. 1-14). Cham, Germany: Springer.
• Şekeroğlu, A., Tahtalı, Y., Sarıca, M., Gülay, M. Ş., Abacı, H. S., & Duman, M. (2013). Comparison of growth curves of broiler under different stocking densities by gompertz model. Kafkas Universitesi Veteriner Fakültesi Dergisi, 19(4), 669-672.
• Şengül, T., & Kiraz, S. (2005). Non-linear models for growth curves in large white turkeys. Turkish Journal of Veterinary and Animal Sciences, 29(2), 331-337.
• Tang, X., Li, J., Zhao, P., Liu, Z., & Chen, Q. (2010). Study on growth and development and fitting of growth curve of Huainan partridge duck. Journal of Henan Agricultural Sciences, 2, 105-107.
• Topal, M., & Bolukbasi, Ş. (2008). Comparison of nonlinear growth curve models in broiler chickens. Journal of Applied Animal Research, 34(2), 149-152.
• van der Klein, S., Kwakkel, R., Ducro, B., & Zuidhof, M. (2020). Multiphasic nonlinear mixed growth models for laying hens. Poultry Science, 99(11), 5615-5624.
• Vitezica, Z., Marie-Etancelin, C., Bernadet, M.-D., Fernandez, X., & Robert-Granie, C. (2010). Comparison of nonlinear and spline regression models for describing mule duck growth curves. Poultry Science, 89(8), 1778-1784.
• Waller, D. L. (2003). Operations management: A supply chain approach. Cengage Learning Business Press, Boston.
• Yakupoglu, C., & Atil, H. (2001). Comparison of growth curve models on broilers growth curve I: Parameters estimation. Online Journal of Biological Sciences, 1(7), 680-681.