ASABE Technical Library - Abstract
Member and Access Notice
Detection of Eggshell Crack using Electronic Nose
Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org
Citation: Transactions of the ASABE. 53(3): 789-794. (doi: 10.13031/2013.30052) @2010Authors: S. Cheng, Y. Wang, J. Wang, Z. Wei, Q. Lu
Keywords: Egg, Eggshell crack, Electronic nose, Linear discriminant analysis, Neural network, Principal component analysis
The objective of this study was to investigate the potential of an electronic nose (E-nose) technique for detecting eggshell crack. An E-nose was developed with eight sensors for distinguishing intact eggs and cracked eggs. Pattern recognition was conducted using principal component analysis (PCA), linear discriminant analysis (LDA), back-propagation neural network (BPNN), and the combination of genetic algorithm and BP neural network (GANN). The results proved that the E-nose coupled with LDA and PCA can distinguish between intact egg and cracked egg after one week or two weeks of storage, and the LDA method had better classification results. Furthermore, the E-nose using BPNN and GANN can distinguish between intact egg and cracked egg, and a greater distinguishing effect can be obtained with increased storage time. A better predicted rate was obtained by GANN than by BPNN.
(Download PDF) (Export to EndNotes)