ABSTRACT
The aim of this study was to analyze the physical and chemical characteristics of chicken droppings (n = 73), which were collected during different age periods and classified by visual inspection into normal (N) and abnormal (A). Significant differences were found in the texture, pH, dry matter (DM), fatty acids (FAs), short-chain fatty acids (SCFAs), and volatile compounds (VCs) between the tested dropping groups (p ≤ 0.05). The age period of the chicken had a significant influence on the color coordinates, texture, pH, DM, and SCFA contents in N and A as well as on all FAs content in N (p ≤ 0.05). Droppings from the N group had a harder texture, lower values of a* and b* color coordinates, higher DM content, higher level of linoleic FA, and lower level of α-linolenic FA than the droppings from the A group in each age period (p ≤ 0.05). The predominant SCFA was acetic acid, the content of which was significantly lower in the N group compared to that of the A group. The alcohol and organic acid contents were the highest in most of the A group at different age periods, while ketones dominated in the N and A groups. In conclusion, the majority of the tested dropping characteristics were influenced by the age period. While certain characteristics demonstrate differences between N and A, a likely broader range of droppings is required to provide more distinct trends regarding the distribution of characteristics across different droppings.
ABSTRACT
The use of artificial intelligence techniques with advanced computer vision techniques offers great potential for non-invasive health assessments in the poultry industry. Evaluating the condition of poultry by monitoring their droppings can be highly valuable as significant changes in consistency and color can be indicators of serious and infectious diseases. While most studies have prioritized the classification of droppings into two categories (normal and abnormal), with some relevant studies dealing with up to five categories, this investigation goes a step further by employing image processing algorithms to categorize droppings into six classes, based on visual information indicating some level of abnormality. To ensure a diverse dataset, data were collected in three different poultry farms in Lithuania by capturing droppings on different types of litter. With the implementation of deep learning, the object detection rate reached 92.41% accuracy. A range of machine learning algorithms, including different deep learning architectures, has been explored and, based on the obtained results, we have proposed a comprehensive solution by combining different models for segmentation and classification purposes. The results revealed that the segmentation task achieved the highest accuracy of 0.88 in terms of the Dice coefficient employing the K-means algorithm. Meanwhile, YOLOv5 demonstrated the highest classification accuracy, achieving an ACC of 91.78%.
ABSTRACT
Crop contamination with mycotoxins is a global problem with a negative impact on human and animal health as well as causing economical losses in food and feed chains. This study was focused on the evaluation of the effect of lactic acid bacteria (LAB) strain (Levilactobacillus brevis-LUHS173, Liquorilactobacillus uvarum-LUHS245, Lactiplantibacillus plantarum-LUHS135, Lacticaseibacillus paracasei-LUHS244 and Lacticaseibacillus casei-LUHS210) fermentation on the changes in the level of deoxynivalenol (DON) and its conjugates in Fusarium spp.-contaminated barley wholemeal (BWP). Samples, with different contamination of DON and its conjugates, were treated separately (for 48 h). In addition to mycotoxin content, enzymatic activities (amylolytic, xylanolytic, and proteolytic) of BWP (before and after fermentation) were evaluated. It was established that the effect of decontamination depends on the LAB strain used, and a significant reduction in DON and the concentration of its conjugates in Lc. casei fermented samples was achieved: the amount of DON decreased on average by 47%, and the amount of D3G, 15-ADON and 3-ADON decreased by 82.4, 46.1, and 55.0%, respectively. Lc. casei also showed viability in the contaminated fermentation medium and an effective production of organic acids was obtained. Additionally, it was found that enzymes are involved to the detoxification mechanism of DON and its conjugates in BWP. These findings indicate that fermentation with selected LAB strains could be applied for contaminated barley treatment in order to significantly reduce Fusarium spp. mycotoxin levels in BWP and improve the sustainability of grain production.
ABSTRACT
In this study, the effect of solid-state fermentation (SSF) with Lactobacillus sakei MI401 and Pediococcus acidilactici PA-2 strains on functional properties of extruded (130 °C; 25 rpm) corn-milling by-products (CMB) and their albumin, globulin, and prolamin fractions was evaluated in order to produce stabilized and functionalized food/feed stock. Extrusion resulted in a considerable reduction of microbial contamination of CMB by five log cycles, increased damaged starch, water-absorption capacity, and lowered protein and fat contents by 12.4% and 37%, respectively. The application of SSF for the extruded CMB have been shown to improve the water absorption, foaming, and emulsifying capacity of albumins and globulins and also increased the digestibility and free radical scavenging activity of prolamins. The essential amino acid content (EAA) in CMB and antioxidant activity of prolamins was lowered after extrusion but significantly increased after SSF. The combination of the abovementioned treatments can be confirmed as a prospective functionalization of CMB, capable of potentially enhancing its safety and improving nutritional, biochemical, and technological properties of proteins.
