Performance of Artificial Neural Networks Model under Various Structures and Algorithms to Prediction of Fat Tail Weight in Fat Tailed Breeds and Their Thin Tailed Crosses
Subject Areas : Camelک. نوبری 1 , S.D. Sharifi 2 , N. Emam Jomea Kashan 3 , M. Momen 4 , A. Kavian 5
1 - بخش تحقیقات علوم دامی، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی استان گلستان، سازمان تحقیقات، آموزش و ترویج کشاورزی، گرگان، ایران
2 - Department of Animal and Poultry Science, College of Abouraihan, University of Tehran, Tehran, Iran
3 - Department of Animal and Poultry Science, College of Abouraihan, University of Tehran, Tehran, Iran
4 - Department of Animal Science, Faculty of Agriculture, Shahid Bahonar University of Kerman, Kerman, Iran
5 - Department of Animal Science, Golestan Agricultural and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization (AREEO), Gorgan, Iran
Keywords: Artificial Neural Network, Sheep, Breeding, fat-tail, Prediction model, Algorithms, ANN structure,
Abstract :
Today’s large fat tail lost its importance because of rearing condition and consumers’ demands. Therefore, recording fat tail weight on live animals is important to selecting animals for reduced fat tail weight. The study was conducted to predict the fat tail weight of five different genetic groups of lambs obtained from a mating system between fat-tailed and thin-tailed parents. An Artificial Neural Networks (ANN) procedure was used for prediction performance of different structures (40 levels) and algorithms (5 levels). Eight measurements, including birth type (2 levels), sex (2 levels), breed composition (5 levels), live body weight and four morphological assessments were used as ANN model’s inputs. The results showed that ANN model with adequate structure and algorithm can accurately predict the tail weights and compositions of the studied breeds. Our results indicate that with increase of neurons in first hidden layers, the prediction accuracies were increase dramatically. Back propagation algorithm (BP) was the best algorithm with higher stable R2 and lower stable root mean squire error (RMSE) in different structures. BP algorithm with 4 and 2 neurons in the first and second hidden layer, respectively, had more ability to predict fat-tail weight in different genetic groups. Best ANN model provided 0.962, 0.997 and 0.988 R2 values and 338.156, 43.689 and 117.306 of RMSE for testing, training and the overall data sets, respectively. The study showed that, an ANN model based on the BP algorithm, have high potential to predict fat-tail weight as an important economic trait in sheep rearing systems.
Akkol S., Akilli A. and Cemal İ. (2017). Comparison of Artificial Neural Network and Multiple Linear Regression for prediction of live weight in hair goats. Yuzuncu Yil Univ. J. Agric. Sci. 27(1), 21-29.
Ali M., Eyduran E., Tariq M.M., Tirink Abbas C.F., Bajwa M.A., Baloch M.H., Nizamani A.H., Waheed A., Awan M.A., Shah S.H., Ahmad Z. and Jan S. (2015). Comparison of artificial neural network and decision tree algorithms used for predicting live weight at post weaning period from some biometrical characteristics in Harnai sheep. Pakistan J. Zool. 47, 1579-1585.
Anastasiadis D.A., Magoulas G.D. and vrahatis M.N. (2005). New globally convergent training scheme based on the resilient propagation algorithm. Neurocomputing. 64, 253-270.
Atil H. and Akilli A. (2015). Investigation of dairy cattle traits by using artificial neural networks and cluster analysis. Pp. 23-27 in Proc. 7th Int. Conf. Inform. Commun. Technol. Agric. Food Environ., Kavala, Greece.
Atkins K.D., Murray J.J., Gilmour A.R. and Luff A.L. (1991). Genetic variation of live weight and ultrasonic fat depth in Australian pool Dorset sheep. Australian J. Agric. Res. 42, 629-640.
Atti N., Bocquier F. and Khaldi G. (2004). Performance of the fat-tailed Barbarine sheep in its environment: Adaptive capacity to alternation of underfeeding and re-feeding periods. Anim. Res. 53(3), 165-176.
Bishop C.M. (2006). Pattern Recognition and Machine Learning. Springer, New York, USA.
Davidson A. (2006). The Oxford Companion to Food. Oxford University Press, Oxford, United Kingdom.
Ehret A., Hochstuhl D., Gianola D. and Thaller G. (2015). Application of neural networks with back-propagation to genome-enabled prediction of complex traits in Holstein-Friesian and German Fleckvieh cattle. Genet. Sel. Evol. 47, 22-31.
Farid A. (1991). Slaughter and carcass characteristics of three fat-tailed sheep breed and their crosses with Corriedal and Targhee rams. Small Rumin. Res. 5(3), 255-271.
Ghazanfari S., Nobari K. and Tahmoorespur M. (2011). Prediction of egg production using Artificial Neural Network. Iranian J. Anim. Sci. 1(1), 11-16.
Grzesiak W. and Zaborski D. (2012). Examples of the use of data mining methods in animal breeding. Pp. 303-324 in: Data Mining Applications in Engineering and Medicine. A. Karahoca, Ed. InTech, Rijeka, Croatia.
Intrator O. and Intrator N. (1993). Using Neural Nets for Interpretation of Nonlinear Models. Pp. 244-249 in Proc. Stat. Comput. Section, San Francisco, USA.
Kashan N.E.J., Manafi-Azar G.H., Afzalzadeh A. and Salehi A. (2005). Growth performance and carcass quality of fattening lambs from fat-tailed and tailed sheep breeds. Small Rumin. Res. 60, 267-271.
Mehri M. (2012). Development of artificial neural network models based on experimental data of response surface methodology to establish the nutritional requirements of digestible lysine, methionine, and threonine in broiler chicks. Poult. Sci. 91, 3280-3285.
Mehri M. (2013). Comparison of neural network models, fuzzy logic, and multiple linear regression for prediction of hatchability. Poult. Sci. 92, 1138-1142.
Moradi M.H., Nejati-Javaremi A., Moradi-Shahrbabak M., Dodds K.G. and McEwan J.C. (2012). Genomic scan of selective sweeps in thin and fat tail sheep breeds for identifying of candidate regions associated with fat deposition. BMC Genet. 13, 10-12.
Norouzian M.A. and Vakili-Alavijeh M. (2016). Comparison of Artificial Neural Network and multiple regression analysis for prediction of fat tail weight of sheep. Iranian J. Appl. Anim. Sci. 6(4), 895-900.
Perai A.H., Nassiri-Moghaddam H., Asadpour S., Bahrampour J. and Mansoori G. (2010). A comparison of artificial neural networks with other statistical approaches for the prediction of true metabolizable energy of meat and bone meal. Poult. Sci. 89, 1562-1568.
Riedmiller M. (1994). Rprop-Description and Implementation Details. Technical Report, University of Karlsruhe, USA.
Riedmiller M. and Braun H. (1993). A direct adaptive method for faster backpropagation learning: The RPROP algorithm. Pp. 48-52 in Proc. IEEE Int. Conf. Neural Networks (ICNN), San Francisco, USA.
Saatci M., Appewi I., Jones H.E. and Ulutas Z. (1998). Genetic parameter and estimated breeding value of live weight, fat and muscle depth in Welsh Mountain rams. Pp. 238-240 in Proc. 6th World Congr. Gen. Appl. Livest. Prod., Armidale, Australia.
Takma Ç., Atil H. and Aksakal V. (2012). Comparison of Multiple Linear Regression and Artificial Neural Network models goodness of fit to lactation milk yields. Kafkas Univ. Vet. Fak. Derg. 18(6), 941-644.
Vatankhah M. and Talebi M.A. (2008). Heritability estimates and correlations between production and reproductive traits in Lori-Bakhtiari sheep in Iran. South African J. Anim. Sci. 38(2), 110-118.
Wright D. (2015). The genetic architecture of domestication in animals. Bioinform. Biol. Insight. 9(4), 11-20.
Zamiri M.J. and Izadifard J. (1997). Relationships of fat-tail weight with fat-tail measurements and carcass characteristics of Mehraban and Ghezel rams. Small Rumin. Res. 15, 261-266.