This research presented the procedural framework of developing and optimizing an artificial intelligence model for predicting the change of bread texture by different baking enhancers. Emphasis was placed on the impact of various baking enhancers on the Mixolab thermo-mechanical properties of wheat flour and consequent alterations in bread texture. The application of baking enhancers positively contributed to dough formation and stability, producing bread with a soft texture. However, a relatively low Pearson correlation coefficient was observed between a single Mixolab parameter and bread texture (r<0.59). To more accurately predict the texture of bread from the thermo-mechanical features of wheat flour with baking enhancers, five AI models (multiple linear regression, decision tree, stochastic gradient descent, random forest, and multilayer perceptron neural network) were applied, and their prediction performance was compared. The multilayer perceptron neural network model was further utilized to enhance the prediction of bread texture by mitigating overfitting risks. Finally, the hyperparameter tuning (activation function [Leaky ReLU], regularization [0.0001], and dropout [0.1]) led to enhanced model performance (R2 = 0.8109 and RMSE = 0.1096).

Marigold powder is recognized to be a good source of lutein that plays significant roles in promoting the health of eyes and reducing age-related cataract risk. Because lutein cannot be synthesized in a human body, it needs to be supplied from the diet. However, there are no lutein-incorporated food products in a market other than capsules or powders. In this study, the processing performances of marigold powder in a fresh noodle system was investigated in terms of pasting, viscoelastic, and textural properties. In addition, the levels of lutein in the marigold powder-incorporated fresh noodles were quantitatively analyzed before and after cooking by HPLC. The pasting and dynamic viscoelastic parameters of wheat flour were reduced with increasing levels of marigold powder. The SEM images demonstrated that the wheat flour paste samples with higher levels of marigold powder show a highly cellular structure. However, the use of marigold powder at a level of 2% did not significantly affect the tensile properties of fresh noodles. When marigold powder was incorporated into the formulation of fresh noodles, their lutein contents were ranges from 61.22 to 204.91mg/100 g noodles. After cooking, the lutein contents were reduced by almost 50% while they seemed to satisfy the recommended dietary intake of lutein.

As one of the staple crops, rice has been widely applied to value-added products, giving the food industry new avenues of use. Although the quality attributes of various rice products have been reported, there is a lack of detailed information on the rheological behaviors of rice products during digestion that are related to their bioaccessibility in the human body. In this study, three rice varieties with different amylose contents were utilized to produce flours and extruded noodles. In-vitro methods simulating starch digestion processes were then established to monitor their oral-gastric-intestinal rheological behaviors. The rice flour with high amylose content exhibited lower values of water absorption index/swelling power and higher pasting parameters that were in good agreement with the Mixolab thermo-mechanical results. The extruded rice noodles showed lower cooking loss and higher hardness with increasing levels of amylose. When the in-vitro viscosities of rice flours and noodles were measured using a rotational rheometer with the custom-made starch cell, their viscosities had a tendency to decrease as the in-vitro digestion progressed. Specifically, the rice samples with high amylose content exhibited higher viscosity than those with low amylose content under the simulated oral, gastric, and intestinal conditions. Hence, this study was conducted to investigate the physicochemical and in-vitro rheological properties of rice flours and extruded noodles with different amylose content. The results provided a promising opportunity for the food industry to study in-vitro digestion of rice-based products with the advantages of being more rapid and less expensive.