Change of bioactive properties, spectral reflectance, and color characteristics of European cranberry (Viburnum opulus L.) juice as affected by foam mat drying technique.

The European cranberry bush, known for its health benefits, can only be consumed through fermentation. This study aimed to develop a fruit leather made from European cranberry bush using quince seed gel and the foam drying method. For this purpose, quince seed gel was added to European cranberry juice to increase consistency. Then, European cranberry fruit leather was obtained by drying at 70, 80, and 90 °C air temperatures using foam mat drying technology. Spectral reflectance, color, drying kinetics, anthocyanin, ascorbic acid, and total phenolic content, antiradical activity, and macro-micronutrient concentrations of the resulting fruit pulp were investigated. The foam mat drying process at 90 °C had the greatest values of ascorbic acid (0.996 mg g- 1), anthocyanin (275.9 mg kg- 1), DPPH (47.77%), and ABTS.+ (68.76 µg TE g- 1). In addition, the highest value of total phenolic content (37.75 mg g- 1) was obtained in the foam mat drying process at 80 °C. The highest concentration of P, Na, Mg, K, Ca, and Mn in fruit leather was obtained at 70 °C, and the highest concentration of S, Cu, and Zn was obtained at 90 °C. The lowest spectral reflectance values were measured at 90 °C. In conclusion, the present study explored the fact that adding quince seed gel, extremely rich in biochemical content, significantly enhanced the bioactivity properties of European cranberry bush fruit leather.

Machine learning and computer vision technology to analyze and discriminate soil samples.

Soil texture is one of the most important elements to consider before planting and tillage. These features affect the product selection and regulate its water permeability. Discrimination of soils by determining soil texture features requires an intense workload and is time-consuming. Therefore, having a powerful tool and knowledge for texture-based soil discrimination could enable rapid and accurate discrimination of soils. This study focuses on presenting new models for 6 different soil sample groups (Soil_1 to Soil_6) based on 12 different machine learning algorithms that can be utilized for various problems. As a result, overall accuracy values were determined as greater than 99.2% (Trilayered Neural Network). The greatest accuracy value was found in Bayes Net (99.83%) and followed by Subspace Discriminant (99.80%). In the Bayes Net algorithm, MCC (Matthews Correlation Coefficient) and F-measure values were obtained as 0.994 and 0.995 for Soil_4 and Soil_6 sample groups while these values were 1.000 for other soil groups. Soil types can visually vary based on their texture, mineral composition, and moisture levels. The variability of this can be influenced by fertilization, precipitation levels, and soil cultivation. It is important to capture the images in soil conditions that are more stable. In conclusion, the present study has proven the feasibility of rapid, non-destructive, and accurate discrimination of soils by image processing-based machine learning.