The bioactive properties of the combination of microencapsulated cell-free supernatant (CFS) from Streptococcus thermophilus and thyme extract on food-related bacteria (Photobacterium damselae, Proteus mirabilis, Vibrio vulnificus, Staphylococcus aureus ATCC29213, Enterococcus faecalis ATCC29212, and Salmonella Paratyphi A NCTC13) were investigated. The microencapsulated CFS of S. thermophilus, in combination with ethanolic thyme extract, had a particle size in the range of 1.11 to 11.39 µm. The microencapsulated CFS of S. thermophilus had a wrinkled, spherical form. In the supernatant, especially at 2% (v/w), the thyme extract additive caused a decrease in the wrinkled form and a completely spherical structure. A total of 11 compounds were determined in the cell-free supernatant of S. thermophilus, and acetic acid (39.64%) and methyl-d3 1-dideuterio-2-propenyl ether (10.87%) were the main components. Thyme extract contained seven components, the main component being carvacrol at 67.96% and 1,2,3-propanetriol at 25.77%. Significant differences (p < 0.05) were observed in the inhibition zones of the extracts on bacteria. The inhibitory effect of thyme extract on bacteria varied between 25.00 (P. damselae) and 41.67 mm (V. vulnificus). Less antibacterial activity was shown by the microencapsulated CFS from S. thermophilus compared to their pure form. (p < 0.05). As a result, it was found that microencapsulated forms of CFS from S. thermophilus, especially those prepared in combination with 2% (v/w) thyme extract, generally showed higher bioactive effects on bacteria.

This study aims to predict the freshness of sea bass (Dicentrarchus labrax) using deep learning models based on image data. For this purpose, 10 fish were monitored daily from the day of purchase until three days after spoilage, with multi-angle imaging (eight distinct perspectives per fish, both with and without background) and corresponding quality analyses. A total of 22 quality parameters—10 categorical (sensory-based) and 12 numerical (color-based)—were evaluated, with the purchasability parameter defined as the most critical indicator of freshness. Using seven popular transfer learning algorithms (EfficientNetB0, ResNet50, DenseNet121, VGG16, InceptionV3, MobileNet, and VGG19), 2464 predictive models (1120 classification and 1344 regression) were trained. Classification models were evaluated using accuracy, precision, recall, F1-score, and response time, while regression models were assessed using mean absolute error and tolerance-based error metrics. The results showed that the MobileNet algorithm achieved the best overall performance, successfully predicting 15 of the 22 parameters with the lowest error or highest accuracy. Importantly, in the prediction of the most critical parameter—purchasability—the DenseNet121 architecture yielded the best classification performance with an accuracy of 0.9894. The findings indicate that deep learning-based image analysis is a viable method for evaluating the freshness of fish.