Filters
The application of convolutional neural networks, LF-NMR, and texture for microparticle analysis in assessing the quality of fruit powders: Case study – blackcurrant powders
Abstract It can be observed that dynamic developments in artificial intelligence contributing to the evolution of existing techniques used in food research. Currently, innovative methods are being sought to support unit processes such as food drying, while at the same time monitoring quality and extending their shelf life. The development of innovative technology using convolutional neural networks (CNNs) to assess the quality of fruit powders seems highly desirable. This will translate into obtaining homogeneous batches of powders based on the specific morphological structure of the obtained microparticles. The research aims to apply convolutional networks to assess the quality, consistency, and homogeneity of blackcurrant powders supported by comparative physical methods of low-field nuclear magnetic resonance (LF-NMR) and texture analysis. The results show that maltodextrin, inulin, whey milk proteins, microcrystalline cellulose, and gum arabic are effective carriers when identifying morphological structure using CNNs. The use of CNNs, texture analysis, and the effect of LF-NMR relaxation time together with statistical elaboration shows that maltodextrin as well as milk whey proteins in combination with inulin achieve the most favorable results. The best results were obtained for a sample containing 50% maltodextrin and 50% maltodextrin (MD50-MD70). The CNN model for this combination had the lowest mean squared error in the test set at 2.5741 × 10−4, confirming its high performance in the classification of blackcurrant powder microstructures.
The Rheology, Texture, and Molecular Dynamics of Plant-Based Hot Dogs
The rising demand for plant-based alternatives to traditional meat products has led to the development of plant-based sausages (PBSs) that closely mimic the texture and taste of their meat counterparts. This study investigates the rheological and textural properties, as well as proton molecular dynamics, of hot dog-type PBSs and batters used in their production. Various formulations were analyzed to understand how different ingredients and processing methods affect the characteristics of the final products. Our findings reveal that the incorporation of specific plant proteins and hydrocolloids significantly influences the rheological behavior and texture profile of sausages. The hardness of the samples ranged from 4.33 to 5.09 N/mm and was generally higher for the products with inorganic iron sources. Regarding the viscoelastic properties, all the samples showed larger values of the storage modulus than the loss modulus, which indicates their solid-like behavior. Additionally, the study utilized advanced proton nuclear magnetic resonance (NMR) techniques to elucidate the molecular dynamics within plant-based matrices, providing insights into water distribution and mobility. Key findings highlight the impact of different plant proteins and additives on the texture and stability of sausage analogs.