Data on Machine Learning - Artificial Neural Networks Reported by H.Zheng and Co-Researchers

摘要

2011 MAR 14 - (VerticalNews.com) -- "Artificial neural network (ANN) and partialrnleast-squares regression (PLSR) models were developed to predict the changes of anthocyaninrn(AC), ascorbic acid (AA), total phenols (TP), total flavonoid (TF), and DPPH radicalrnscavenging activity (SA) in bayberry juice during storage based on fractal analysis (FA) and red,rngreen, and blue (RGB) intensity values. The results show the root mean squared error (RMSE)rnof ANN-FA decreased 2.44 and 12.45% for AC (RMSE = 18.673 mg/100 mL, R-2 = 0.939) andrnAA (RMSE = 8.694 mg/100 mL, R-2 = 0.935) compared with PLSR-RGB, respectively,"rninvestigators in Jinhua, People's Republic of China report.