Quality assessment of poultry egg based on visible-near infrared spectroscopy and radial basis function networks

Abstract

In this research the possibility of a non-destructive prediction of two main quality parameters of poultry egg using principle component analysis and radial basis function network by the transmission visible- near infrared spectroscopy method was investigated. The studied parameters include Haugh unit and air cell height as a function of a 5-week storage duration at room (25°C and 40% relative humidity) and refrigerator (5°C and 75% relative humidity) conditions. The spectra were interpreted and a radial basis function network model was developed for both storage conditions at wavelength ranges of 300-1100 nm. The developed models yielded a good prediction accuracy of Haugh unit for intact egg (R2 value 0.745 and 0.76) as well as air cell height (R2 value 0.835 and 0.844) for room and refrigerator conditions, respectively. Results of the experiment showed the developed model can be used in the prediction of egg freshness indices satisfactorily.