Search

Obtaining body mass in large-scale rearing and production environments is difficult, making non-contact assessment methods indispensable. This paper introduces an original pipeline for predicting pig body mass based on an adapted mask region convolutional neural network (mask R-CNN). The adaptation deploys ResNeSt as the backbone feature-extraction architecture, aiming to bolster the capacity to derive features from imagery. A feature pyramid network (FPN) was appended to this backbone to enable feature merging across multiple scales. Within the region proposal network (RPN), a channel attention mechanism (CAM) was installed alongside a spatial attention mechanism (SAM), enabling the dynamic combination of localized characteristics with their long-range interdependencies. This configuration captures holistic contextual knowledge, ultimately improving segmentation fidelity. The adapted architecture achieved precision (P) of 90.33%, recall (R) of 89.85%, and mean average precision (MAP) of 95.21%, thereby isolating pig areas in images with notable effectiveness. Five descriptive features drawn from the imagery were examined: back area, body length, body width, average depth, and eccentricity. Leveraging the pig depth images, five regression learning algorithms—ordinary least squares (OLS), AdaBoost, CatBoost, XGBoost, and random forest (RF)—were trained to forecast mass values. AdaBoost delivered the strongest predictive performance, evidenced by a coefficient of determination (R2) of 0.987, a mean absolute error (MAE) of 2.96 kg, a mean square error (MSE) of 12.87 kg², and a mean absolute percentage error (MAPE) of 8.45%. The experimental results confirm that machine learning models can reliably predict pig mass, providing a technical foundation for the informed management of pig production facilities.

Achieving food availability, advancing the long-term viability of farming, and propelling economic progress. However, current forecasting frameworks often overlook the specific characteristics of rice yield distributions, which vary across regions, exhibit skewness, and are constrained by fixed lower and upper thresholds, conforming to a four-parameter beta distribution. The consequence is outputs that are less reliable and can potentially misguide decision-making. Furthermore, a majority of techniques fall short in modeling the intricate variable interactions that arise when satellite observations are fused with field survey measurements, an integration widely viewed as essential for boosting forecast fidelity and streamlining cultivation methods. To remedy these deficiencies, the present research proposes a four-parameter beta Generalized Linear Mixed Model (GLMM) and advances it into a four-parameter beta Generalized Mixed Effect Tree (GMET). This four-parameter beta GMET extends the four-parameter beta GLMM architecture by embedding a regression tree mechanism, thereby providing superior flexibility for representing non-linear and interaction-laden dependencies. Deploying this analytical framework on empirical data from Central Kalimantan and Karawang yields significant gains over earlier approaches, as evidenced by markedly lower AIC and RRMSE metrics. Significantly, the investigation finds that time-lagged reflectance values from bands 4 and 8 and the NDVI index captured by Sentinel-2A satellites are the dominant determinants of rice productivity, overshadowing the explanatory contribution of farmer questionnaire responses. This finding underscores the promise of remotely sensed data as a cornerstone for rice yield estimation, offering a more streamlined, less resource-intensive alternative to reliance on farmer-reported data. By further refining satellite-based technologies, upcoming initiatives in yield forecasting can realize superior efficiency and precision, thereby underpinning evidence-based choices in agricultural governance.

Ensuring food quality, safety, and authenticity has become a central challenge for contemporary food systems because risks now emerge across production, processing, distribution, retail, and consumption. Artificial intelligence is increasingly used to interpret complex food data, including spectral signals, images, sensor outputs, molecular profiles, traceability records, and supply-chain alerts. These developments suggest that AI can support a shift from reactive food inspection toward predictive and preventive food integrity assurance. Despite this promise, AI applications in food quality, safety, and authenticity often remain separated across disciplinary and technological domains. Sensing studies focus on detection accuracy, prediction studies focus on model performance, traceability studies focus on chain-of-custody infrastructure, and explainable AI studies focus on interpretability. This fragmentation limits the field’s ability to understand how these components could function together as an integrated assurance system. This integrative review synthesises 31 peer-reviewed articles published between 2017 and 2025 across food science, analytical chemistry, sensing technology, food informatics, and artificial intelligence. The review examines four interconnected domains: sensing technologies and data sources, prediction models for quality and safety, traceability and authenticity verification, and explainable decision systems. Its purpose is not to report new empirical data, but to integrate diverse research streams into a coherent conceptual understanding of AI-enabled food integrity assurance. The review shows that AI has already demonstrated value in optical sensing, spectroscopy, imaging, authenticity testing, shelf-life prediction, risk assessment, fraud detection, and traceability analysis. However, most applications are still designed as isolated models rather than as connected decision systems. Three tables classify sensing technologies, categorise prediction models, and present an integrative framework linking detection, prediction, provenance, and explainable decisions. The central conclusion is that the technical components of AI-enabled food integrity assurance already exist, but they remain insufficiently integrated. Future research should move beyond stand-alone classification or prediction models and toward interoperable, explainable, and operationally validated systems. Such systems should connect sensing, prediction, traceability, and human decision-making across food supply chains.

Cold chains are essential food-system infrastructures because they preserve safety, quality, nutritional value, and marketability from production to consumption. Despite their importance, many cold-chain operations still depend on reactive checks, delayed audits, and fixed temperature protocols that are poorly aligned with the biological variability of food products. This reactive orientation allows quality deterioration to accumulate invisibly until products arrive at inspection points, retailers, or consumers. The central problem addressed in this article is the absence of an integrated architecture that connects continuous monitoring, predictive analytics, and automated decision support across the full cold-chain pathway. Sensors may detect temperature excursions, models may estimate shelf life, and logistics systems may manage routing, yet these capabilities often remain fragmented. Without architectural integration, cold chains cannot become truly intelligent, adaptive, or self-correcting. The objective of this article is to propose an Intelligent Cold Chain conceptual architecture for real-time quality preservation, spoilage prediction, and loss prevention. The architecture is designed to transform environmental and logistical data into predictive quality intelligence and operational decisions. It positions the cold chain as a cyber-physical system in which sensing, prediction, decision-making, and coordination interact continuously. The article develops its architecture through a conceptual synthesis of peer-reviewed research published between 2017 and 2025. The synthesis draws from cold-chain logistics, food quality engineering, IoT monitoring, machine learning, digital twins, and supply-chain systems design. It does not report new empirical data, but instead integrates existing technological and theoretical insights into an original systems framework. The proposed architecture defines four functional layers: sensing, prediction, decision, and coordination. These layers specify how sensor streams are acquired, how spoilage risk is inferred, how corrective actions are recommended, and how information is shared across actors. The architecture provides a blueprint for moving cold chains from passive refrigerated corridors toward proactive, data-driven systems that preserve quality and reduce food losses.

Digital twins are increasingly proposed as cyber-physical representations that may support precision agriculture through monitoring, simulation, prediction, optimization, and decision support. However, agricultural systems described as digital twins vary substantially in data quality, interoperability, synchronization, modelling depth, predictive reliability, decision functionality, validation, and operational governance. This article proposes a conceptual maturity framework that evaluates agricultural digital twins through capability progression rather than technology adoption alone. The framework begins with descriptive monitoring and advances through real-time farm representation, simulation and scenario analysis, prediction and optimization, and supervised autonomous decision support. Monitoring maturity depends on reliable sensing, remote sensing, Internet of Things integration, data fusion, spatial and temporal adequacy, traceability, and human-interpretable representation. Simulation and prediction maturity require explicit farm-system boundaries, calibrated models, uncertainty estimation, local validation, and evidence that analytical outputs remain valid for their intended context. Optimization maturity additionally requires transparent objectives, constraints, robustness assessment, and distinction between predictive accuracy and decision value. The highest proposed level permits only narrowly bounded and supervised decision initiation supported by human authority, explainability, safety mechanisms, governance, cybersecurity where relevant, and continuous feedback. The framework does not constitute a validated maturity standard or establish agronomic, environmental, economic, or autonomous decision benefits. Its principal contribution is an integrated structure for assessing capability readiness, identifying progression barriers, and preventing monitoring, simulation, prediction, or optimization functions from being overinterpreted as evidence of deployment-ready autonomy.