Filters
Field Cricket (Gryllus bimaculatus) and Spirulina (Arthrospira platensis) Powders as Environmentally Friendly Protein Enrichment Ingredients in Corn Snacks
Unconventional protein sources are currently extensively studied as food ingredients. This study aimed to evaluate the effect of 1.5% and 3% field cricket powder (GB) and 2–8% of its mixture (1:1) with spirulina powder (S) on the nutritional value, physicochemical properties, and sensory characteristics of corn extrudates. Additionally, 2% baking powder (BP) was added to assess its impact on the properties of the enriched extrudates. The results showed that both GB and GB + S improved nutritional value, with protein content increasing by up to 46% and higher levels of essential amino acids, particularly leucine and valine. However, these ingredients decreased the expansion ratio (by up to 15%), colour lightness (by up to 30%), and yellowness (by up to 47%) and increased the hardness (by up to 25%) of the corn extrudates. The S addition positively influenced product storage stability but decreased its sensory acceptance, especially aroma and taste. The BP addition mitigated the negative effects of higher GB and GB + S concentrations, particularly on sensory characteristics. In conclusion, incorporating up to 6% of the GB + S mixture provides a higher protein content with only minor changes to the product’s characteristics compared to GB. Ratings exceeding 4.2 points indicate the good acceptability of these snacks.
Efficiency of Identification of Blackcurrant Powders Using Classifier Ensembles
In the modern times of technological development, it is important to select adequate methods to support various food and industrial problems, including innovative techniques with the help of artificial intelligence (AI). Effective analysis and the speed of algorithm implementation are key points in assessing the quality of food products. Non-invasive solutions are being sought to achieve high accuracy in the classification and evaluation of various food products. This paper presents various machine learning algorithm architectures to evaluate the efficiency of identifying blackcurrant powders (i.e., blackcurrant concentrate with a density of 67 °Brix and a color coefficient of 2.352 (E520/E420) in combination with the selected carrier) based on information encoded in microscopic images acquired via scanning electron microscopy (SEM). Recognition of blackcurrant powders was performed using texture feature extraction from images aided by the gray-level co-occurrence matrix (GLCM). It was evaluated for quality using individual single classifiers and a metaclassifier based on metrics such as accuracy, precision, recall, and F1-score. The research showed that the metaclassifier, as well as a single random forest (RF) classifier most effectively identified blackcurrant powders based on image texture features. This indicates that ensembles of classifiers in machine learning is an alternative approach to demonstrate better performance than the existing traditional solutions with single neural models. In the future, such solutions could be an important tool to support the assessment of the quality of food products in real time. Moreover, ensembles of classifiers can be used for faster analysis to determine the selection of an adequate machine learning algorithm for a given problem.