Identifying the quality characteristics of pork floss structure based on deep learning framework.

Pork floss is a traditional Chinese food with a long history. Nowadays, pork floss is known to consumers as a leisure food. It is made from pork through a unique process in which the muscle fibers become flaky or granular and tangled. In this study, a deep learning-based approach is proposed to detect the quality characteristics of pork floss structure. Describe that the experiments were conducted using widely recognized brands of pork floss available in the grocery market, omitting the use of abbreviations. A total of 8000 images of eight commercially available pork flosses were collected and processed using sharpening, image gray coloring, real-time shading correction, and binarization. After the machine learning model learned the features of the pork floss, the images were labeled using a manual mask. The coupling of residual enhancement mask and region-based convolutional neural network (CRE-MRCNN) based deep learning framework was used to segment the images. The results showed that CRE-MRCNN could be used to identify the knot features and pore features of different brands of pork floss to evaluate their quality. The combined results of the models based on the sensory tests and machine vision showed that the pork floss from TC was the best, followed by YJJ, DD and HQ. This also shows the potential of machine vision to help people recognize the quality characteristics of pork floss structure.

Predicting VOCs content and roasting methods of lamb shashliks using deep learning combined with chemometrics and sensory evaluation.

A comparison was made between the traditional charcoal-grilled lamb shashliks (T) and four new methods, namely electric oven heating (D), electric grill heating (L), microwave heating (W), and air fryer treatment (K). Using E-nose, E-tongue, quantitative descriptive analysis (QDA), and HS-GC-IMS and HS-SPME-GC-MS, lamb shashliks prepared using various roasting methods were characterized. Results showed that QDA, E-nose, and E-tongue could differentiate lamb shashliks with different roasting methods. A total of 43 and 79 volatile organic compounds (VOCs) were identified by HS-GC-IMS and HS-SPME-GC-MS, respectively. Unsaturated aldehydes, ketones, and esters were more prevalent in samples treated with the K and L method. As a comparison to the RF, SVM, 5-layer DNN and XGBoost models, the CNN-SVM model performed best in predicting the VOC content of lamb shashliks (accuracy rate all over 0.95) and identifying various roasting methods (accuracy rate all over 0.92).

Raw to charred: Changes of protein oxidation and in vitro digestion characteristics of grilled lamb.

This study aimed to evaluate protein oxidation and in vitro digestion characteristics of lamb that was grilled from raw to charred (0-30 min). Results showed that protein oxidation was aggravated with the time of grilling, indicated by a significant linear increase in carbonyl groups and a linear decrease in sulfhydryl groups. Proteins had the highest simulated gastric and gastrointestinal digestibility at 10-15 min of grilling. Newly formed specific peptides were continuously released during the grilling process. The identified peptides were mainly derived from creatine kinase, phosphoglycerate kinase, actin and myosin light chain. Protein oxidation was closely related to digestive characteristics, and grilling for >15 min would aggravate protein oxidation and reduce its digestibility. Therefore, at 220 °C lamb should not be grilled for longer than 15 min.

Characterization of selected commercially available grilled lamb shashliks based on flavor profiles using GC-MS, GC × GC-TOF-MS, GC-IMS, E-nose and E-tongue combined with chemometrics.

HS-SPME-GC-MS, SPME-Arrow-GC × GC-TOF-MS, HS-GC-IMS, Electronic-nose, and Electronic-tongue systems were applied in a feasibility study of the flavor characterization of five commercially available Chinese grilled lamb shashliks. A total of 198 volatile organic compounds (VOCs) were identified (∼71% by GC × GC-TOF-MS). Using data fusion strategies, five predictive models were applied to the composition of VOCs and brand identification of the lamb shashliks. Compared with partial least squares regression, support vector machine, deep neural network, and RegBoost modeling, a momentum deep belief network model performed best in predicting VOCs content and identifying shashlik brands (R2 above 0.96, and RMSE below 0.1). Intelligent sensory technology combined with chemometrics is a promising approach to the flavor characterization of shashliks and other food matrices.

Raw to charred: Changes of precursors and intermediates and their correlation with heterocyclic amines formation in grilled lamb.

This work aimed to investigate the changes and correlations of precursors, intermediates and heterocyclic amines (HCAs) in lamb during charcoal grilling. 28 chemical compounds were detected by high-performance liquid chromatography and gas chromatography-mass spectrometry in grilled lamb from raw to charred. Results demonstrated the types and contents of HCAs were increased during grilling, of which 2-amino-1-methyl-6-phenylimidazo [4,5-b] pyridine (PhIP) was dominant and accounted for 61% at the end of grilling (42 min). Glucose and creatine (P < 0.05) decreased with grilling time, creatinine (P < 0.05) and total free amino acid increased. The types and contents of four intermediates (formaldehyde, acetaldehyde, phenylacetaldehyde, 2,5-dimethylpyrazine) increased during grilling. Glucose, creatine, creatinine, ten free amino acids and four intermediates showed significant correlation to HCAs. Also, the ratios of four precursors were significantly correlated with HCAs (P < 0.05), besides creatine/glucose ratio. These results suggested that the time of charcoal grilling should not exceed 14 min at 145 °C in order to reduce the formation of harmful compounds in lamb meat.

Development of a Check-All-That-Apply (CATA) Ballot and Machine Learning for Generation Z Consumers for Innovative Traditional Food.

Generation Z (Gen Z) consumers account for an increasing proportion of the food market. The aim of this study took lamb shashliks as an example and developed novel products from the perspective of cooking methods in order to develop a traditional food suitable for Gen Z consumers. The sensory characterization of electric heating air (EH), microwave heating (MH), air frying (AF), and control (traditional burning charcoal (BC) of lamb shashliks) was performed using the CATA methodology with 120 Gen Z consumers as assessors. A 9-point hedonic scale was used to evaluate Gen Z consumers' preferences for the cooking method, as well as a CATA ballot with 46 attributes which described the sensory characteristics of lamb shashliks. The machine learning algorithms were used to identify consumer preferences for different cooking methods of lamb shashliks as a function of sensory attributes and assessed the relationship between products and attributes present in the perceptual map for the degree of association. Meanwhile, sensory attributes as important variables play a relatively more important role in each cooking method. The most important variables for sensory attributes of lamb shashliks using BC are char-grilled aroma and smoky flavor. Similarly, the most important variables for AF samples are butter aroma, intensity aroma, and intensity aftertaste, the most important variables for EH samples are dry texture and hard texture, and the most important variables for MH samples are light color regarding external appearance and lumpy on chewing texture. The interviews were conducted with Gen Z consumers to investigate why they prefer innovative products-AF. Grounded theory and the social network analysis (SNA) method were utilized to explore why consumers chose AF, demonstrating that Gen Z consumers who had previously tasted AF lamb shashliks could easily perceive the buttery aroma. This study provides a theoretical and practical basis for developing lamb shashliks tailored to Gen Z consumers.

The purchase willingness of consumers for red meat in China.

The aim of this study was to explore the purchase willingness of Chinese consumers for pork, beef, lamb, and rabbit meat. A conceptual framework and focus group discussions were adopted to design the questionnaire which included experience, eating habits, purchase drivers, purchase location, seasonality, and willingness to purchase red meat among Chinese consumers. Data collection was undertaken using an online platform questionnaire, with 4039 meat consumers participating in this study. By constructing the partial least squares - path modeling (PLS-PM) to explore the concerns of Chinese consumers while purchasing various types of red meats as well as the effect of these questions on consumers' willingness intensity to purchase red meat. Willingness intensity to purchase lamb is significantly affected by experience, seasonality, purchase location, eating habits, willingness, purchase drivers, and personal information; beef is affected by experience, seasonality, purchase location, eating habits, willingness, and personal information; pork is mainly affected by eating habits and purchase drivers; while eating habits, purchase location, and personal information have positive impacts on willingness intensity to purchase rabbit meat. This study developed the orthogonal matching pursuit - stochastic gradient descent (OMP-SDG) model, which integrated the questionnaire collecting personal information with the questionnaire on Chinese consumers' perceptions of red meat. The program can more precisely forecast which types of red meat people like and their degree of willingness. Finally, Chinese consumers preferred beef, lamb, pork, and rabbit meat in that order. They also prefer local meat, believing it to be of high quality and providing a satisfactory sensory experience, appearance, and saturation.

Impact of oral processing on texture attributes and taste perception.

Mastication is the first step of food digestion, where foods are broken down and simultaneously impregnated by saliva resulting in the formation of semi-fluids known as food boluses. This review focuses on the impact of oral processing on texture attributes and taste perception. The article describes the oral actions in which texture characteristic are measured for the critical conditions that trigger swallowing. Taste perception also plays a key role in oral processing and oral sensations. There are still challenges in terms of determining different oral physiological characteristics. These include individual chewing behavior regardless of the temporal aspects of dominant processes of comminution, insalivation, bolus formation and swallowing. A comprehensive approach is essential to process favorable foods with respect to the food properties of texture and taste.

Evolution of Taste Compounds of Dezhou-Braised Chicken During Cooking Evaluated by Chemical Analysis and an Electronic Tongue System.

This paper aimed to study the time course changes in taste compounds of Dezhou-braised chicken during the entire cooking process mainly consisting of deep-frying, high-temperature boiling, and low-temperature braising steps. For this purpose, meat samples at different processing stages were analyzed for 5'-nucleotides and free amino acids, and were also subjected to electronic tongue measurements. Results showed that IMP, Glu, Lys, and sodium chloride were the main compounds contributing to the taste attributes of the final product. IMP and Glu increased in the boiling step and remained unchanged in the following braising steps. Meanwhile, decrease in Lys content and increase in sodium chloride content were observed over time in both boiling and braising steps. Intensities for bitterness, saltiness, and Aftertaste-B obtained from the electronic tongue analysis were correlated with the concentrations of these above chemical compounds. Therefore, the electronic tongue system could be applied to evaluate the taste development of Dezhou-braised chicken during processing.