Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Chemometrics: Theory and Application
Chemometrics: Theory and Application
Hi-index | 0.00 |
A new Vis/NIR inspection system interface was developed to test and implement an automated chicken inspection system for online operation on commercial chicken processing lines. The spectroscopic system demonstrated effective spectral acquisition and data processing for real-time classification of chickens on a 140bpm processing line. Real-time online testing successfully differentiated between wholesome and unwholesome birds using a neural network classification model with 20 input nodes that correctly classified 94% and 92% of wholesome and unwholesome birds, respectively. This work demonstrates the effectiveness of the Vis/NIR inspection system for accurate real-time product and shackle tracking on commercial chicken processing lines.