“…As a feed-forward neural network, BP neural networks are connected by neurons that allow information to flow in only one direction, from the input layer to the hidden layer and finally to the output layer [ 50 ]. From the MFA evaluation, it can be seen that preference and Arg, Ala, Gly, Pro, K + , and Ca 2+ showed a high positive correlation.…”
This study took a consumer sensory perspective to investigate the relationship between taste components and consumers’ preferences and emotions. Abdomen meat (M), hepatopancreas (H), and gonads (G) of Chinese mitten crabs, one from Chongming, the Jianghai 21 variety (C-JH), and two from Taixing, the Jianghai 21 (T-JH) and Yangtze II varieties (T-CJ), were used to evaluate flavor quality. The results indicated that in the abdomen meat, differences in taste components were mainly shown in the content of sweet amino acids, bitter amino acids, K+, and Ca2+; M-C-JH had the highest EUC value of 9.01 g/100 g. In the hepatopancreas, bitter amino acids were all significantly higher in H-C-JH (569.52 mg/100 g) than in the other groups (p < 0.05). In the gonads, the umami amino acid content was significantly higher in G-T-JH than in the other groups (p < 0.05) (EUC values: G-T-JH > G-C-JH > G-T-CJ). Consumer sensory responses showed that different edible parts of the crab evoked different emotions, with crab meat being closely associated with positive emotions and more complex emotional expressions for the hepatopancreas and gonads. In comparison, consumers were more emotionally positive when consuming Yangtze II crab. H-C-JH evoked negative emotions due to high bitter taste intensities. Multifactor analysis (MFA) showed arginine, alanine, glycine, proline, K+, and Ca2+ were found to have a positive correlation with consumer preference; an artificial neural network model with three neurons was built with good correlation (R2 = 0.98). This study can provide a theoretical foundation for the breeding of Chinese mitten crabs, new insights into the river crab industry, and the consumer market.
“…As a feed-forward neural network, BP neural networks are connected by neurons that allow information to flow in only one direction, from the input layer to the hidden layer and finally to the output layer [ 50 ]. From the MFA evaluation, it can be seen that preference and Arg, Ala, Gly, Pro, K + , and Ca 2+ showed a high positive correlation.…”
This study took a consumer sensory perspective to investigate the relationship between taste components and consumers’ preferences and emotions. Abdomen meat (M), hepatopancreas (H), and gonads (G) of Chinese mitten crabs, one from Chongming, the Jianghai 21 variety (C-JH), and two from Taixing, the Jianghai 21 (T-JH) and Yangtze II varieties (T-CJ), were used to evaluate flavor quality. The results indicated that in the abdomen meat, differences in taste components were mainly shown in the content of sweet amino acids, bitter amino acids, K+, and Ca2+; M-C-JH had the highest EUC value of 9.01 g/100 g. In the hepatopancreas, bitter amino acids were all significantly higher in H-C-JH (569.52 mg/100 g) than in the other groups (p < 0.05). In the gonads, the umami amino acid content was significantly higher in G-T-JH than in the other groups (p < 0.05) (EUC values: G-T-JH > G-C-JH > G-T-CJ). Consumer sensory responses showed that different edible parts of the crab evoked different emotions, with crab meat being closely associated with positive emotions and more complex emotional expressions for the hepatopancreas and gonads. In comparison, consumers were more emotionally positive when consuming Yangtze II crab. H-C-JH evoked negative emotions due to high bitter taste intensities. Multifactor analysis (MFA) showed arginine, alanine, glycine, proline, K+, and Ca2+ were found to have a positive correlation with consumer preference; an artificial neural network model with three neurons was built with good correlation (R2 = 0.98). This study can provide a theoretical foundation for the breeding of Chinese mitten crabs, new insights into the river crab industry, and the consumer market.
“…Back propagation neural network (BPNN) is one of the most classic neural network algorithms, and it is a neural network training system for calculating backpropagation errors [ 30 ]. The main feature of the BPNN network is that the signal is forwarded, and the error is propagated back.…”
This study proposes a novel method for detection of aflatoxin B1 (AFB1) in peanuts using olfactory visualization technique. First, 12 kinds of chemical dyes were selected to prepare a colorimetric sensor to assemble olfactory visualization system, which was used to collect the odor characteristic information of peanut samples. Then, genetic algorithm (GA) with back propagation neural network (BPNN) as the regressor was used to optimize the color component of the preprocessed sensor feature image. Support vector regression (SVR) quantitative analysis model was constructed by using the optimized combination of characteristic color components to achieve determination of the AFB1 in peanuts. In this process, the optimization performance of grid search (GS) algorithm and sparrow search algorithm (SSA) on SVR parameter was compared. Compared with GS-SVR model, the model performance of SSA-SVR was better. The results showed that the SSA-SVR model with the combination of seven characteristic color components obtained the best prediction effect. Its correlation coefficients of prediction (RP) reached 0.91. The root mean square error of prediction (RMSEP) was 5.7 μg·kg−1, and ratio performance deviation (RPD) value was 2.4. The results indicate that it is reliable to use the colorimetric sensor array with strong specificity for the determination of the AFB1 in peanuts. In addition, it is necessary to properly optimize the parameters of the prediction model, which can obviously improve the generalization performance of the multivariable model.
“…Back-propagation neural network (BPNN) is one of the classical neural networks, and its full name is a neural network based on error back propagation algorithm. 17 It is generally composed of three or more layers of neurons, respectively: input layer, hidden layer and output layer. 18 When the signal is propagated from the input layer to the output layer through the implicit layer, the signal is propagated in the positive direction.…”
In this study, a colorimetric sensor was used to collect odor information from fermentation samples. The optimal model was established by introducing different combinations of intelligent optimization algorithms to determine ethanol content.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.