With the enhancement of consumers’ food safety awareness, consumers have become more stringent on meat quality. This study constructs an intelligent dynamic prediction model based on knowledge rules and integrates flexible humidity sensors into the non-destructive monitoring of the Internet of Things to provide real-time feedback and dynamic adjustments for the chilled chicken cold chain. The optimized sensing equipment can be attached to the inside of the packaging to deal with various abnormal situations during the cold chain, effectively improving the packaging effect. Through correlation analysis of collected data and knowledge rule extraction of critical factors in the cold chain, the established quality evaluation and prediction model achieved detailed chilled chicken quality level classification and intelligent quality prediction. The obtained results show that the accuracy of the prediction model is higher than 90.5%, and all the regression coefficients are close to 1.00. The relevant personnel (workers and cold chain managers) were invited to participate in the performance analysis and optimization suggestion to improve the applicability of the established prediction model. The optimized model can provide a more efficient theoretical reference for timely decision-making and further e-commerce management.

Chronic psychological stress affects the health of humans and animals (especially females or pregnant bodies). In this study, a stress-induced model was established by placing eight-week-old female and pregnant mice in centrifuge tubes for 4 h to determine whether chronic stress affects the intestinal mucosal barrier and microbiota composition of pregnant mice. Compared with the control group, we found that norepinephrine (NE), corticosterone (CORT), and estradiol (E₂) in plasma increased significantly in the stress group. We then observed a decreased down-regulation of anti-inflammatory cytokines and up-regulation of pro-inflammatory cytokines, which resulted in colonic mucosal injury, including a reduced number of goblet cells, proliferating cell nuclear antigen-positive cells, caspase-3, and expression of tight junction mRNA and protein. Moreover, the diversity and richness of the colonic microbiota decreased in pregnant mice. Bacteroidetes decreased, and pernicious bacteria were markedly increased. At last, we found E₂ protects the intestinal epithelial cells after H₂O₂ treatment. Results suggested that 25 pg/mL E₂ provides better protection for intestinal barrier after chronic stress, which greatly affected the intestinal mucosal barrier and altered the colonic microbiota composition.

Transportation pressure poses a serious threat to the health of live sheep and the quality of their meat. So, the edible Hu sheep was chosen as the research object for meat sheep. We constructed a systematic biosignal detecting, processing, and modeling method. The biosignal sensing was performed with wearable sensors (photoelectric sensor and infrared temperature measurement) for physiological dynamic sensing and continuous monitoring of the transport environment of meat sheep. Core waveform extraction and modern spectral estimation methods are used to determine and strip out the target signal waveform from it for the purpose of accurate sensing and the acquisition of key transport parameters. Subsequently, we built a qualitative stress assessment method based on external manifestations with reference to the Karolinska drowsiness scale to establish stage classification rules for monitoring data in the transportation environment of meat sheep. Finally, machine learning algorithms such as Gaussian Naive Bayes (GaussianNB), Passive-Aggressive Aggregative Classifier (PAC), Nearest Centroid (NC), K-Nearest Neighbor Classification (KNN), Random Forest (RF), Support Vector Classification (SVC), Gradient Boosting Decision Tree (GBDT), and eXtreme Gradient Boosting (XGB) were established to predict the classification models of transportation stress in meat sheep. Their classification results were compared. The results show that SVC and GBDT algorithms are more effective and the overall model classification accuracy reached 86.44% and 91.53%. XGB has the best results. The accuracy of the assessment of the transport stress state of meat sheep after the optimization of three parameters was 100%, 90.91%, and 93.33%, and the classification accuracy of the overall model reached 94.92%. The final results achieved improve transport reliability, reduce transport risk, and solve the problems of inefficient meat sheep transport supervision and quality control.

Environmental and physiological fluctuations in the live oyster cold chain can result in reduced survival and quality. In this study, a flexible wireless sensor network (F-WSN) monitoring system combined with knowledge engineering was designed and developed to monitor environmental information and physiological fluctuations in the live oyster cold chain. Based on the Hazard Analysis and Critical Control Point (HACCP) plan to identify the critical control points (CCPs) in the live oyster cold chain, the F-WSN was utilized to conduct tracking and collection experiments in real scenarios from Yantai, Shandong Province, to Beijing. The knowledge model for shelf-life and quality prediction based on environmental information and physiological fluctuations was established, and the prediction accuracies of TVB-N, TVC, and pH were 96%, 85%, and 97%, respectively, and the prediction accuracy of viability was 96%. Relevant managers, workers, and experts were invited to participate in the efficiency and applicability assessment of the established system. The results indicated that combining F-WSN monitoring with knowledge-based HACCP modeling is an effective approach to improving the transparency of cold chain management, reducing quality and safety risks in the oyster industry, and promoting the sharing and reuse of HACCP knowledge in the oyster cold chain.

Non-contact monitoring in precision livestock farming (PLF) needs reliable individual identification and face-anchored analytics to link animals with longitudinal health and behavior signals in variable barns. Evidence is fragmented across pipeline modules and deployment readiness is difficult to assess because robustness and operational KPIs are inconsistently reported. We map research evolution and synthesize deployment-oriented evidence and design principles. A two-stage review was conducted: CiteSpace bibliometric mapping of Web of Science Core Collection records (2005–2025; pre-2005 relevant records were sporadic), followed by a scoping synthesis of peer-reviewed empirical studies (2022–2025) searched mainly in ScienceDirect and supplemented by Web of Science, Scopus, IEEE Xplore, and CNKI. We included studies using livestock facial imagery (RGB and/or thermal/IR) for identity functions or face-coupled ROI analytics with quantitative cohort evaluation. Following QRD screening, 24 studies were retained. We consolidate deployment factors and reporting gaps and propose “Digital Individuals” as persistent identity anchors for multimodal longitudinal records and closed-loop decision support.