Neural network with principal component analysis for poultry carcass classification

This paper reports the results of applying principal component analyses (PCA) of spectral reflectance data to reduce the number of input nodes for neural networks for classification of wholesome and unwholesome poultry carcasses. The results showed that the models with PCA pretreatment of input data performed better than those models without pretreatment. When sensing moving poultry carcasses in an environment without room light with a visible/near-infrared spectrophotometer, the neural network classification models with PCA pretreatment achieved 100% accuracies for training, validating, and testing. For carcasses moving at 60 birds/min, 50 factors were required for perfect classification, while for 90 birds/min 30 factors were required. When sensing in room light, the best model was generated with 30 factors for a shackle speed of 60 birds/min, with a test set accuracy of 95.8%. For 90 birds/min, the best model with a test set accuracy of 96.8% was obtained when 15 factors were used. This study showed that PCA reduced the number of input nodes to the neural network classifiers and, in most cares, improved the model's classification accuracy. It also required fewer training samples and reduced training time.