Automating egg damage detection for improved quality control in the food industry using deep learning January 22, 2025

The detection and classification of damage to eggs within the egg industry are of paramount importance for the production of healthy eggs. This study focuses on the automatic identification of cracks and surface damage in chicken eggs using deep learning algorithms. The goal is to enhance egg quality control in the food industry by accurately identifying eggs with physical damage, such as cracks, fractures, or other surface defects, which could compromise their quality. A total of 794 egg images were used in the study, comprising two different classes: damaged and not damaged (intact) eggs. Four different deep learning models based on convolutional neural networks were employed: GoogLeNet, Visual Geometry Group (VGG)-19, MobileNet-v2, and residual network (ResNet)-50. GoogLeNet achieved a classification accuracy of 98.73%, VGG-19 achieved 97.45%, MobileNet-v2 achieved 97.47%, and ResNet-50 achieved 96.84%. According to the results, the GoogLeNet model performed the damage detection with the highest accuracy rate (98.73%). This study encompasses artificial intelligence and deep learning techniques for the automatic detection of egg damage. The early detection of egg damage and accurate interventions highlights the significant importance of using these technologies in the food industry. This approach provides producers with the ability to detect damaged eggs more quickly and accurately, thereby minimizing product losses through timely intervention. Additionally, the use of these technologies offers a more efficient means of classifying and identifying damaged eggs compared to traditional methods.

Effect of oscillating magnetic field (OMF) on the supercooling behavior of iron‐oxide nanoparticle (IONP) agar model system January 20, 2025

Freezing extends the shelf life of foods but often leads to structural damage due to ice crystal formation, negatively impacting quality attributes. Oscillating magnetic field (OMF)-assisted supercooling has emerged as a potential technique to overcome these limitations by inhibiting ice nucleation and maintaining foods in a supercooled state. Despite its potential, the effectiveness and underlying mechanisms of OMF-assisted supercooling remain subjects of debate. In this study, the effects of OMF on the supercooling behavior of an agar-based food model system containing iron(III)-oxide nanoparticles (IONP) were investigated. Agar samples containing IONPs at various concentrations (3, 6, 12 and 15 mg per 100 mL) were prepared to simulate the presence of ferric materials responsive to OMF. The samples were exposed to an external OMF (10 mT, 10 Hz) at −8°C for 24 h. Higher supercooling probabilities were achieved in the IONP-containing samples, with probabilities of 75%, 75%, and 90% for the 3 mg, 6 mg, and 12 mg concentrations, respectively. In contrast, lower supercooling probabilities of 60% and 55% were exhibited by the control samples (without nanoparticles) and samples containing zinc nanoparticles (ZNPs), respectively. It is suggested that the enhanced supercooling stability in IONP samples is due to the interaction between the magnetic nanoparticles and the OMF, inhibiting ice nucleation possibly through the magneto-mechanical motion affecting water molecule orientation and hydrogen bonding networks.

Simultaneous extraction and purification of polysaccharides and proteins from Pleurotus ostreatus using an aqueous two‐phase system January 20, 2025

Pleurotus ostreatus is a nutrient-dense edible fungus renowned for its delicate texture, appealing flavor, and numerous potential health benefits. Simultaneous extraction within the framework of food resource processing facilitates the concurrent isolation and analysis of multiple target compounds. In this study, an ethanol/salt aqueous two-phase system (ATPS) was employed to extract polysaccharides (PS) and proteins from P. ostreatus. The impacts of pH, inorganic salts, and temperature on ATPS phase formation were systematically evaluated. The ethanol/K₂HPO₄ system demonstrated superior selective extraction performance under optimal conditions: 25.16% ethanol (w/w), 15.91% K₂HPO₄ (w/w), and 24.11% crude extract (w/w) without pH adjustment. The highest recovery efficiency of PS and proteins were 90.29% ± 0.24% and 76.35% ± 0.15%, respectively. The simultaneous extraction efficiency of PS and proteins was 12.49% ± 0.14% and 20.34% ± 0.09%, respectively. As a comparison, hot water extraction and alkali extraction methods were performed to assess the impact of ATPS on the physicochemical properties of PS and proteins. SDS-PAGE and HPLC analyses confirmed that the protein subunit distribution was consistent across different extraction methods, whereas the ATPS-extracted PS exhibited characteristics of homogeneous heteropolysaccharides with a molecular weight of 28.8 × 10⁶ Da. Monosaccharides such as mannose, glucuronic acid, and glucose were identified in the PS hydrolysate. The results demonstrate that ATPS preserves the physicochemical integrity of the extracted substances. This method holds promise for unlocking new possibilities and has the potential to become an effective method for large-scale extraction and purification of polysaccharides and proteins from edible fungi.

Soybean oil and probiotics improve meat quality, conjugated linoleic acid concentration, and nutritional quality indicators of goats January 20, 2025

This study aimed to investigate the impact of dietary soybean oil and probiotics on goat meat quality, total conjugated linoleic acids (TCLA) concentration, and nutritional quality indicators of goats. Thirty-six male crossbred goats (Anglo-Nubian♂× Thai native♀), weighing 18.3 ± 2.7 kg, were selected and randomly assigned to six groups in a 2 × 3 factorial design, with six replicates per group. The soybean oil supplementation levels were 25 and 50 g/kg, while the probiotic supplementation levels were 0, 2.5, and 5.0 g/h/day. The results showed that supplementing the diet with 50 g/kg soybean oil significantly improved the average daily gain (ADG) (p = 0.02) and carcass yield (p = 0.05), while reducing the feed conversion ratio (p = 0.05). Additionally, the addition of 2.5 g/h/day of probiotics significantly increased dry matter intake (p(L) = 0.05, p(Q) = 0.03). Notably, supplementation with 50 g/kg soybean oil reduced the Warner–Bratzler shear force (p = 0.05) and a* (p = 0.01) values of the Longissimus thoracis et lumborum. However, 2.5 g/h/day of probiotics significantly improved (p(L) = 0.01, p(Q) = 0.04) the a* value of Longissimus thoracis et lumborum. Soybean oil supplementation at 50 g/kg increased the ether extract composition of Biceps brachii (p = 0.05) and Semimembranosus (p = 0.05). Additionally, it significantly increased TCLA content (p < 0.01) and reduced the n−6/n−3 ratio (p < 0.01). Interestingly, the supplementation of 5.0 g/h/day probiotics significantly reduced the thrombogenic index (p = 0.03). Moreover, supplementing with 50 g/kg soybean oil (p = 0.03) and 5.0 g/h/day probiotics significantly improved the nutritive value index of goat muscle. Collectively, the findings suggest that the optimal supplementation levels of probiotics and soybean oil are 2.5 g/h/day and 50 g/kg, respectively. These levels have a more pronounced effect on improving the growth performance of growing goats, increasing CLA content, and enhancing meat quality.

Enhancing beer authentication, quality, and control assessment using non‐invasive spectroscopy through bottle and machine learning modeling January 20, 2025

Fraud in alcoholic beverages through counterfeiting and adulteration is rising, significantly impacting companies economically. This study aimed to develop a method using near-infrared (NIR) spectroscopy (1596–2396 nm) through the bottle, along with machine learning (ML) modeling for beer authentication, quality traits, and control assessment. For this study, 25 commercial beers from different brands, styles, and three types of fermentation were used. To obtain the ground-truth data, a quantitative descriptive analysis was conducted with 11 trained panelists to evaluate the intensity of 16 sensory descriptors, and volatile aromatic compounds were analyzed using gas chromatography–mass spectroscopy (GC–MS). The ML models were developed using artificial neural networks with NIR absorbance values as inputs to predict (i) type of fermentation (Model 1), (ii) intensity of 16 sensory descriptors (Model 2), and (iii) peak area of volatile aromatic compounds (Model 3). All models resulted in high overall accuracy (Model 1: 99%; Model 2: R = 0.92; Model 3: R = 0.94), and model deployment for new beer samples showed high performance (Model 1: 95%; Model 2: R = 0.83). This method enables brewers and retailers to analyze beers without opening bottles, preventing quality assurance issues, fraud, and provenance concerns. Further model training with new targets could assess additional quality traits like physicochemical parameters and origin.

EP 52: 2025 Food Industry M&A Forecast, 2025 Food Safety Trends, Securing Research Funding January 20, 2025

Get the latest insights from the food science and technology community in the January 2025 episodes of the Omnivore podcast.

EP 51: Talking Trends With Mintel’s Jenny Zegler, Traceability Rule Challenges, Legacy Brands Product Innovation January 6, 2025

Get the latest insights from the food science and technology community in the January 2025 episodes of the Omnivore podcast.

EP 50: Building Trust in Food Science, Food As Medicine, Food Safety Tech Game-Changers December 30, 2024

In this “Best of 2024” episode of Omnivore, Food Technology revisits the top food science and thought leader interview segments of the year.

EP 49: Ag Futurist Robert Saik, @TheBlackFoodScientist Shares the Science, The Potential of Generative AI December 16, 2024

In this “Best of 2024” episode of Omnivore, Food Technology revisits the top food science and thought leader interviews of the year.

EP 48: The Ins and Outs of Indoor Agriculture, Food Safety Tech Game-Changers, What’s Trending in Food Regulations and Policy November 25, 2024

Get the latest insights from the food science and technology community in the November 2024 episodes of the Omnivore podcast.