Effects of combined radio frequency heating with oven baking on product quality of sweet potato

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.

Optimal conditions for beef tenderization through radiofrequency heating with cold air

High-temperature (15-37°C) aging can shorten the tenderizing time of beef; however, the use of constant temperature heating can lead to microbial spoilage. This study tested radiofrequency (RF) tenderization (RF-T) to find the appropriate conditions for the aging-like effect of beef without microbial spoilage. After subjecting beef to 22 h RF-T with four different cooling temperatures (15, 5, -10, and -20°C), the proliferated aerobic bacteria on the surface showed a concentration of 6-6.2 log CFU/g at -10 and -20°C, lower than 7-7.5 log CFU/g at 15 and 5°C. When beef was treated with 25 W/kg RF heating power for 48 h RF-T, the estimated reduction rate of the sliced shear force (SSF) and the increase rate of glutamic acid based on the weight before RF-T were 22.6% and 1.51-fold, which were greater than 19.6% and 1.37-fold with 20 W/kg, and 11.0% and 1.11-fold with 15 W/kg. The optimal specific RF heating power was calculated as 30 W/kg from the results' extrapolation. When processed for 48 h under optimal conditions (30 W/kg specific RF heating power, -20°C cooling air), the tenderization rate and the increased rates of free amino acids based on the weight before RF-T of beef reached over 20% and 1.5-fold with 5.22 log CFU/g aerobic bacteria, which was lesser than the Korean regulation value of 6.7 log CFU/g (5 × 106  CFU/g). Therefore, RF-T could be proposed as a promising high-temperature tenderization method with lowered risk of microbial spoilage. PRACTICAL APPLICATION: We showed that lowering the chamber temperature during RF-T was effective in surface drying and inhibiting aerobic bacteria. RF-T for 24-48 h with 30 W/kg specific RF heating power had an aging-like effect given tenderization and increase in FAAs. Moreover, by providing the matching circuit and impedance during RF-T, this method could be industrially reproducible.

Effects of Heat Treatments on Various Characteristics of Ready-to-Eat Zucchini Purees Enriched with Anise or Fennel

Galactagogue herbs, also known as natural lactation adjuvants, are frequently used to stimulate breast milk production. Due to their antioxidant activity and phenolic content, anise (Pimpinella anisum L.) and fennel (Foeniculum vulgare L.) were chosen to increase the added value of zucchini (Cucurbita pepo L.) purees. At the same time, this work aimed to determine the influence of heat treatment on various characteristics of the final product. The phytochemical content, color parameters, and rheological and textural parameters of zucchini purees enriched with herbal aqueous extracts were determined after processing and after one week of storage (4 °C). In the case of antioxidant activity, samples registered a variation between 6.62 ± 1.71 and 38.32 ± 3.85 µM Trolox/g DW for the samples processed by steam convection. The total difference color parameter (ΔE) increased seven times after one week of storage compared to samples at T₀. Fennel and anise aqueous extracts helped improve the rheological behavior of zucchini samples both by steam and hot air convection. This study may serve as a springboard for future investigations and clinical trials into the scientific validity and safety of ready-to-eat foods with special destinations.

Advances in prepared dish processing using efficient physical fields: A review

Prepared dishes are increasingly popular convenience food that can be eaten directly from hygienic packaging by heating. Physics field (PF) is food processing method built with physical processing technology, which has the characteristics of high efficiency and environmental safety. This review focuses on summarizing the application of PFs in prepared dishes, evaluating and comparing PFs through quality changes during processing and storage of prepared dishes. Currently, improving the quality and extending the shelf life of prepared dishes through thermal and non-thermal processing are the main modes of action of PFs. Most PFs show good potential in handing prepared dishes, but may also react poorly to some prepared dishes. In addition, the difficulty of precise control of processing conditions has led to research mostly at the laboratory stage, but as physical technology continues to break through, more PFs and multi-physical field will be promoted for commercial use in the future. This review contributes to a deeper understanding of the effect of PFs on prepared dishes, and provides theoretical reference and practical basis for future processing research in the development of various enhanced PFs.

Machine and Deep Learning in the Evaluation of Selected Qualitative Characteristics of Sweet Potatoes Obtained under Different Convective Drying Conditions

This paper discusses the use of various methods to distinguish between slices of sweet potato dried in different conditions. The drying conditions varied in terms of temperature, the values were: 60 °C, 70 °C, 80 °C, and 90 °C. Examination methods included instrumental texture analysis using a texturometer and digital texture analysis based on macroscopic images. Classification of acquired data involved the use of machine learning techniques using various types of artificial neural networks, such as convolutional neural networks (CNNs) and multi-layer perceptron (MLP). As a result, in the convective drying, changes in color darkening were found in products with the following temperature values: 60 °C (L = 83.41), 70 °C (L = 81.11), 80 °C (L = 79.02), and 90 °C (L = 75.53). The best-generated model achieved an overall classification efficiency of 77%. Sweet potato dried at 90 °C proved to be completely distinguishable from other classes, among which classification efficiency varied between 61–83% depending on the class. This means that image analysis using deep convolutional artificial neural networks is a valuable tool in the context of assessing the quality of convective-dried sweet potato slices.