首页|Evaluating and predicting egg quality indicators through principal component analysis and artificial neural networks
Evaluating and predicting egg quality indicators through principal component analysis and artificial neural networks
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NSTL
Elsevier
Egg quality is a multidimensional concept that depends on many different parameters. Many studies have evaluated different egg quality attributes subjected to various storage conditions. The present work aimed to study the influence of three environmental parameters (temperature, storage time and relative humidity) on egg quality indicators. Through application of response surface methodology, it was verified that the temperature is the most important environmental factor affecting egg quality attributes followed by the storage time and relative humidity, respectively. Principal Component Analysis showed that most quality indexes are similar except for the eggshell percentage that represents an exterior quality indicator. An artificial neural network composed by one hidden layer and four neurons provided accurate predictions of the Yolk index and is a promising tool to evaluate egg quality.
NSTL
Elsevier
