Artificial neural networks (ANN) have become popular for optimization and prediction\nof parameters in foods, beverages, agriculture and medicine. For brewing, they have been explored\nto develop rapid methods to assess product quality and acceptability. Different beers (N = 17) were\nanalyzed in triplicates using a robotic pourer, RoboBEER (University of Melbourne, Melbourne,\nAustralia), to assess 15 color and foam-related parameters using computer-vision. Those samples\nwere tested using sensory analysis for acceptability of carbonation mouthfeel, bitterness, flavor and\noverall liking with 30 consumers using a 9-point hedonic scale. ANN models were developed using\n17 different training algorithms with 15 color and foam-related parameters as inputs and liking of\nfour descriptors obtained from consumers as targets. Each algorithm was tested using five, seven\nand ten neurons and compared to select the best model based on correlation coefficients, slope and\nperformance (mean squared error (MSE). Bayesian Regularization algorithm with seven neurons\npresented the best correlation (R = 0.98) and highest performance (MSE = 0.03) with no overfitting.\nThese models may be used as a cost-effective method for fast-screening of beers during processing\nto assess acceptability more efficiently. The use of RoboBEER, computer-vision algorithms and\nANN will allow the implementation of an artificial intelligence system for the brewing industry to\nassess its effectiveness.
Loading....