Application of appropriate models to approximate the performance function warrants more precise prediction and helps to make the best decisions in the poultry industry. This study reevaluated the factors affecting hatchability in laying hens from 29 to 56 wk of age. Twenty-eight data lines representing 4 inputs consisting of egg weight, eggshell thickness, egg sphericity, and yolk/albumin ratio and 1 output, hatchability, were obtained from the literature and used to train an artificial neural network (ANN). The prediction ability of ANN was compared with that of fuzzy logic to evaluate the fitness of these 2 methods. The models were compared using R2, mean absolute deviation (MAD), mean squared error (MSE), mean absolute percentage error (MAPE), and bias. The developed model was used to assess the relative importance of each variable on the hatchability by calculating the variable sensitivity ratio. The statistical evaluations showed that the ANN-based model predicted hatchability more accurately than fuzzy logic. The ANNbased model had a higher determination of coefficient (R2 = 0.99) and lower residual distribution (MAD = 0.005; MSE = 0.00004; MAPE = 0.732; bias = 0.0012) than fuzzy logic (R2 = 0.87; MAD = 0.014; MSE = 0.0004; MAPE = 2.095; bias = 0.0046). The sensitivity analysis revealed that the most important variable in the ANN-based model of hatchability was egg weight (variable sensitivity ratio, VSR = 283.11), followed by yolk/albumin ratio (VSR = 113.16), eggshell thickness (VSR = 16.23), and egg sphericity (VSR = 3.63). The results of this research showed that the universal approximation capability of ANN made it a powerful tool to approximate complex functions such as hatchability in the incubation process.
Modeling of a biological process (e.g., growth rate, egg production, and hatchability) in domestic animals and poultry is one of the most important steps to approach maximum productivity and make economic decisions. In some cases, the effect of input variables are
not fully understood in the system, and latent relationships between inputs and output may exist. Therefore, classical methods of data processing (e.g., multiple linear regression) may not be efficient to elicit the complicated interrelationships of biological responses and influencing factors. Research has shown that the application of appropriate mathematical models may release more precise information on the system output along with accurate prediction of performance (Baş and Boyacı, 2007b; Ahmadi and Golian, 2010, 2011; Savegnago et al., 2011; Mehri, 2012; Peruzzi et al., 2012).
Publisher : Poultry Science Association Inc
By : M. Mehri
File Information: English Language/ 5 Page / size: 707 KB
سال : 2013
ناشر : Poultry Science Association Inc
کاری از : M. Mehri
اطلاعات فایل : زبان انگلیسی / 5 صفحه / حجم : KB 707
لینک دانلود : روی همین لینک کلیک کنید