Search Results (1,647)

Digital twins, understood as computational replicas of poultry production systems updated in real time by sensor data, are increasingly invoked as transformative tools for precision livestock farming and sustainable agriculture. They are credited with enhancing feed efficiency, reducing greenhouse gas emissions, enabling disease detection earlier and improving animal welfare. Yet close examination of the published evidence reveals that these promises rest on a surprisingly narrow empirical foundation. Across the available literature, no peer reviewed study has quantified the full lifecycle carbon footprint of digital twin infrastructure in poultry production. Only one field validated investigation reports a measurable improvement in feed conversion ratio attributable to digital optimization, and that study’s design constrains its general applicability. A standardized performance assessment framework specific to poultry has not been established. Quantitative evaluations of reliability are scarce, limited to a small number of studies reporting data loss, sensor degradation and cloud system downtime, and no work has documented abandonment timelines or reasons for discontinuation. The result is a pronounced gap between technological aspiration and verified performance. Progress in this domain will depend on small-scale, deeply instrumented deployments capable of generating the longitudinal, multidimensional evidence required to substantiate the environmental and operational benefits attributed to digital twins. Full article

Machine learning inference is increasingly deployed on shared and cloud infrastructures, where both user inputs and model parameters are highly sensitive. Confidential computing promises to protect these assets using Trusted Execution Environments (TEEs), yet existing TEE-based inference systems remain fundamentally constrained: they rely almost exclusively on low-level, memory-unsafe languages to enforce confinement, sacrificing developer productivity, portability, and access to modern ML ecosystems. At the same time, mainstream high-level runtimes, such as Python, are widely considered incompatible with enclave execution due to their large memory footprints and unsafe model-loading mechanisms that permit arbitrary code execution. To bridge this gap, we present the first Python-based ML inference system that executes entirely inside Intel SGX enclaves while safely supporting untrusted third-party models. Our design enforces standardized, declarative model representations (ONNX), eliminating deserialization-time code execution and confining model behavior through interpreter-mediated execution. The entire inference pipeline (including model loading, execution, and I/O) remains enclave-resident, with cryptographic protection and integrity verification throughout. Our experimental results show that Python incurs modest overheads for small models (≈$17\%$) and outperforms a low-level baseline on larger workloads (97% vs. 265% overhead), demonstrating that enclave-resident high-level runtimes can achieve competitive performances. Overall, our findings indicate that Python-based TEE inference is practical and secure, enabling the deployment of untrusted models with strong confidentiality and integrity guarantees while maintaining developer productivity and ecosystem advantages. Full article

Background: The rapid advancement in artificial intelligence (AI) has fundamentally reshaped gut microbiome research by enabling high-resolution analysis of complex, high-dimensional microbial communities and their functional interactions with the human host. Objective: This narrative review aims to synthesize recent methodological advances in AI-driven gut microbiome research and to evaluate their translational relevance for therapeutic optimization, personalized nutrition, and precision medicine. Methods: A narrative literature review was conducted using PubMed, Google Scholar, Web of Science, and IEEE Xplore, focusing on peer-reviewed studies published between approximately 2015 and early 2025. Representative articles were selected based on relevance to AI methodologies applied to gut microbiome analysis, including machine learning, deep learning, transformer-based models, graph neural networks, generative AI, and multi-omics integration frameworks. Additional seminal studies were identified through manual screening of reference lists. Results: The reviewed literature demonstrates that AI enables robust identification of diagnostic microbial signatures, prediction of individual responses to microbiome-targeted therapies, and design of personalized nutritional and pharmacological interventions using in silico simulations and digital twin models. AI-driven multi-omics integration—encompassing metagenomics, metatranscriptomics, metabolomics, proteomics, and clinical data—has improved functional interpretation of host–microbiome interactions and enhanced predictive performance across diverse disease contexts. For example, AI-guided personalized nutrition models have achieved AUC exceeding 0.8 for predicting postprandial glycemic responses, while community-scale metabolic modeling frameworks have accurately forecast individualized short-chain fatty acid production. Conclusions: Despite substantial progress, key challenges remain, including data heterogeneity, limited model interpretability, population bias, and barriers to clinical deployment. Future research should prioritize standardized data pipelines, explainable and privacy-preserving AI frameworks, and broader population representation. Collectively, these advances position AI as a cornerstone technology for translating gut microbiome data into actionable insights for diagnostics, therapeutics, and precision nutrition. Full article

Blockchain is increasingly applied in the agri-food sector to enhance traceability, data integrity, and accountability. However, its broader role in food system sustainability remains insufficiently characterized, particularly when examined against global megatrends shaping future agri-food transitions. This paper investigates how blockchain technology can reinforce sustainable, inclusive, and resilient food systems under the effect of major global megatrends. A structured literature review of peer-reviewed and industry sources was conducted to identify evidence on blockchain-enabled improvements in transparency, certification, and supply chain coordination. Complementary analysis of a curated dataset of European and international pilot implementations evaluated technological architectures, governance models, and demonstrated performance outcomes. Additionally, stakeholder-based foresight activities and scenarios representing alternative blockchain adoption pathways, developed within the TRUSTyFOOD project (GA: 101060534), were used to examine the interconnection between blockchain adoption and megatrends. Evidence from the literature and pilot cases indicates that blockchain can strengthen product-level traceability and improve verification of sustainability and safety claims. Cross-case analysis also reveals persistent constraints, including heterogeneous technical standards, limited interoperability, high deployment costs for smallholders, and governance risks arising from consortium-led platforms. Blockchain can function as an enabling digital layer for sustainable and resilient food systems and should be embedded in wider, participatory strategies that align digital innovation with long-term sustainability and equity goals in the agri-food sector. Full article

Credit card fraud detection remains a major challenge due to extreme class imbalance and evolving attack patterns. This paper proposes a practical hybrid pipeline that combines conditional tabular generative adversarial networks (CTGANs) for targeted minority-class synthesis with Light Gradient Boosting Machine (LightGBM) for classification. Inspired by symmetry principles in machine learning, we leverage the adversarial equilibrium of CTGAN to generate realistic fraudulent transactions that maintain distributional symmetry with real fraud patterns, thereby preserving the structural and statistical balance of the original dataset. Synthetic fraud samples are merged with real data to form augmented training sets that restore the symmetry of class representation. We evaluate Simple Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) classifiers, and a LightGBM model on a public dataset using stratified 5-fold validation and an independent hold-out test set. Models are compared using sensitivity, precision, F-measure(F₁), and area under the precision–recall curve (PR-AUC), which reflects symmetry between detection and false-alarm trade-offs. Results show that CTGAN-based augmentation yields large and consistent gains across architectures. The best-performing configuration, CTGAN + LightGBM, attains sensitivity = 0.986, precision = 0.982, F₁ = 0.984, and PR-AUC = 0.918 on the test data, substantially outperforming non-augmented baselines and recent methods. These findings indicate that conditional synthetic augmentation materially improves the detection of rare fraud modes while preserving low false-alarm rates, demonstrating the value of symmetry-aware data synthesis in classification under imbalance. We discuss generation-quality checks, risk of distributional shift, and deployment considerations. Future work will explore alternative generative models with explicit symmetry constraints and time-aware production evaluation. Full article

The integration of artificial intelligence into education has driven growing interest in predicting student learning styles and developing recommendation systems that personalize learning pathways. While previous reviews examined these domains, most focus on pre-2023 research, overlooking recent methodological shifts. We conduct a systematic literature review of 40 studies published between 2017 and 2025, with emphasis on publications from 2023 to 2025 (70% of reviewed studies). Our analysis identifies three qualitative shifts: adoption of ensemble and deep learning methods over single classifiers, emergence of multimodal inputs including physiological signals, and evolution from isolated prediction to integrated adaptive systems. Beyond methodological synthesis, this review critically examines factors underlying observed trends and barriers to deployment. The Felder-Silverman Learning Style Model dominates research (58.3%) due to historical path dependency and instrument availability rather than demonstrated pedagogical superiority. While ensemble methods achieve high reported accuracy (87–98%), methodological concerns emerge: 65% of studies employ random rather than temporal validation, potentially inflating performance, and only 23% address production-level requirements, including privacy, scalability, and integration. We systematically analyze implementation barriers spanning computational requirements, LMS integration, educator acceptance, ethical considerations, and scalability—revealing that the gap between research prototypes and deployable systems remains substantial. Our contributions include a stakeholder impact framework, evaluation metrics taxonomy, critical analysis of reported performance claims, and identification of five research gaps with actionable recommendations. This review offers researchers and practitioners both a comprehensive synthesis of advances and a critical roadmap for bridging the implementation gap in AI-powered personalized education. Full article

Municipal solid waste challenges (MSW) and concerns about fossil fuel dependence motivate efforts to recover energy from waste, including refuse-derived fuel (RDF). Techno-economic assessment (TEA) evaluates the feasibility of systems by quantifying investment performance. However, most RDF-TEA studies typically rely on isolated sensitivity analyses. That provides limited insight into interaction effects in emerging markets. This study maps the multivariable feasibility of RDF production from MSW in Ghana under realistic economic conditions. Using a pilot-calibrated case study, the assessment integrates discounted cash flow analysis with response surface methodology–design of experiment (RSM-DoE). A central composite design evaluates interaction effects among operational and economic variables for a system capacity of 2875 tonnes RDF/year. The results indicate economic viability with a net present value (NPV) of USD 892,556.44, a payback period (PBP) of 6.61 years and a levelised production cost (LPC) of USD 18.96/tonne. The RSM models show high explanatory power (R², R²adj, R²pred > 90%). Sensitivity results demonstrate that support mechanisms can significantly reduce LPC and PBP while preserving investment viability. The study quantifies the feasibility thresholds and the support instruments within the RDF design levers. It further provides a transferable framework for assessing deployment and upscaling in emerging markets. The findings highlight the need for structured pricing mechanisms and regulatory support for the long-term sustainability of RDF as an AF. Full article

Spray-induced gene silencing (SIGS) represents a transformative paradigm in sustainable pest management, utilizing the exogenous application of double-stranded RNA (dsRNA) to achieve sequence-specific silencing of essential genes in arthropod pests. Unlike transgenic approaches, sprayable RNA interference (RNAi) biopesticides offer superior versatility across crop systems, flexible application timing, and a more favorable regulatory and public acceptance profile. The 2023 U.S. EPA registration of Ledprona, the first sprayable dsRNA biopesticide targeting Leptinotarsa decemlineata, marks a significant milestone toward the commercialization of non-transformative RNAi technologies. Despite the milestone, large-scale field deployment faces critical bottlenecks, primarily environmental instability, enzymatic degradation by nucleases, and variable cellular uptake across pest taxa. This review critically analyzes the mechanistic basis of spray-applied RNAi and synthesizes the recent technological breakthroughs designed to overcome physiological and environmental barriers. We highlight advanced delivery strategies, including nuclease inhibitor co-application, liposome encapsulation, and nanomaterial-based formulations that enhance persistence on plant foliage and uptake efficiency. Furthermore, we discuss how innovations in microbial fermentation have drastically reduced synthesis costs, rendering industrial-scale production economically viable. Finally, we outline the roadmap for broad adoption, addressing essential factors such as biosafety assessment, environmental fate, resistance management protocols, and the path toward cost-effective manufacturing. Full article

Unmanned aerial vehicles open new possibilities for developing technologies that support more sustainable and efficient agriculture. This paper presents a non-invasive method for repelling rodents from crop fields using ultrasound. The proposed system is implemented as a spherical-cap ultrasound loudspeaker array consisting of eight transducers, mounted on a drone that overflies the field while emitting sound in the 20–70 kHz range. The hardware design includes both the loudspeaker array and a custom printed circuit board hosting power amplifiers and a signal generator tailored to drive multiple ultrasonic transducers. In parallel, a genetic algorithm is used to compute flight paths that maximize coverage and increase the probability of driving rodents away from the protected area. As part of the validation phase, artificial intelligence models for rodent detection using a thermal camera are developed to provide quantitative feedback on system performance. The complete prototype is evaluated through a series of experiments conducted both in controlled laboratory conditions and in the field. Field trials highlight which parts of the concept are already effective and identify open challenges that need to be addressed in future work to move from a research prototype toward a deployable product. Full article

The accelerating global demand for sustainable energy, driven by population growth, industrialization, and environmental concerns, has intensified the search for renewable alternatives to fossil fuels. Biofuels, including bioethanol, biodiesel, biogas, and biohydrogen, offer a viable and practical pathway to reducing net carbon dioxide (CO₂) emissions. Yet, their large-scale production remains constrained by biomass recalcitrance, high pretreatment costs, and the enzyme-intensive nature of conversion processes. Recent advances in enzyme immobilization using magnetic nanoparticles (MNPs), covalent organic frameworks, metal–organic frameworks, and biochar have significantly improved enzyme stability, recyclability, and catalytic efficiency. Complementary strategies such as cross-linked enzyme aggregates, carrier-free immobilization, and site-specific attachment further reduce enzyme leaching and operational costs, particularly in lipase-mediated biodiesel synthesis. In addition to biocatalysis, nanozymes—nanomaterials exhibiting enzyme-like activity—are emerging as robust co-catalysts for biomass degradation and upgrading, although challenges in selectivity and environmental safety persist. Green synthesis approaches employing plant extracts, microbes, and agro-industrial wastes are increasingly adopted to produce eco-friendly nanomaterials and bio-derived supports aligned with circular economy principles. These functionalized materials have demonstrated promising performance in esterification, transesterification, and catalytic routes for biohydrogen generation. Technoeconomic and lifecycle assessments emphasize the need to balance catalyst complexity with environmental and economic sustainability. Multifunctional catalysts, process intensification strategies, and engineered thermostable enzymes are improving productivity. Looking forward, pilot-scale validation of green-synthesized nano- and biomaterials, coupled with appropriate regulatory frameworks, will be critical for real-world deployment. Full article

In recent years, the rapid development of commercial satellite projects, such as low-Earth orbit (LEO) communication and remote sensing constellations, has driven the satellite industry toward low-cost, rapid development, and large-scale deployment. Commercial off-the-shelf (COTS) components have been widely adopted across various commercial satellite platforms due to their advantages of low cost, high performance, and plug-and-play availability. However, the space environment is complex and hostile. COTS components were not originally designed for such conditions, and they often lack systematically flight-verified protective frameworks, making their reliability issues a core bottleneck limiting their extensive application in critical missions. This paper focuses on COTS solid-state drives (SSDs) onboard the Jilin-1 KF satellite and presents a full-lifecycle reliability practice covering component selection, system design, on-orbit operation, and failure feedback. The core contribution lies in proposing a full-lifecycle methodology that integrates proactive design—including multi-module redundancy architecture and targeted environmental stress screening—with on-orbit data monitoring and failure cause analysis. Through fault tree analysis, on-orbit data mining, and statistical analysis, it was found that SSD failures show a significant correlation with high-energy particle radiation in the South Atlantic Anomaly region. Building on this key spatial correlation, the on-orbit failure mode was successfully reproduced via proton irradiation experiments, confirming the mechanism of radiation-induced SSD damage and providing a basis for subsequent model development and management decisions. The study demonstrates that although individual COTS SSDs exhibit a certain failure rate, reasonable design, protection, and testing can enhance the on-orbit survivability of storage systems using COTS components. More broadly, by providing a validated closed-loop paradigm—encompassing design, flight verification and feedback, and iterative improvement—we enable the reliable use of COTS components in future cost-sensitive, high-performance satellite missions, adopting system-level solutions to balance cost and reliability without being confined to expensive radiation-hardened products. Full article

With rising demand for clean energy and uncertainty surrounding large-scale renewable deployment, ammonia has emerged as a viable carrier for hydrogen storage and transportation. This study conducts a global patent-based analysis of ammonia-to-hydrogen production technologies to determine technological maturity, dominant design pathways, and emerging innovation trends. A statistically robust retrieval, screening, and classification process, based on the PRISMA guidelines, was employed to screen, sort, and analyze 708 relevant patent families systematically. Patent families were categorized according to synthesis processes, catalyst types, and technological fields. The findings indicate that electrochemical, plasma-based, photocatalytic, and hybrid systems are being increasingly investigated as alternatives to low-temperature processes. At the same time, thermal catalytic cracking remains the most established and widely used method. Significant advances in reactor engineering, system integration, and catalyst design have been observed, especially in Asia. While national hydrogen initiatives, such as those in Brunei, highlight the policy importance of ammonia-based hydrogen systems, the findings primarily provide a global overview of technological maturity and innovation trajectories, thereby facilitating long-term transitions to cleaner hydrogen pathways. Full article

Rice blast, caused by the fungal pathogen Pyricularia oryzae, remains one of the most destructive diseases threatening global rice production. Although the deployment of resistant cultivars is widely regarded as the most effective and sustainable control strategy, resistance based solely on host genetics often has limited durability due to the rapid adaptation of the pathogen. Increasing evidence suggests that plant-associated microbial communities contribute to host health and disease resistance, yet the role of seed-associated microbiota in shaping rice blast resistance remains insufficiently understood. In this study, we investigated seed endophytic bacterial communities across multiple indica–japonica hybrid rice varieties from the Yongyou series that exhibit contrasting levels of resistance to rice blast. By integrating amplicon sequencing, we identified distinct seed bacterial assemblages associated with blast-resistant and blast-susceptible varieties were identified. Notably, the microbial communities in blast-resistant varieties exhibited significantly higher Shannon index, with a median value of 3.478 compared to 2.654 in susceptible varieties (p < 0.001), indicating a greater diversity and more balanced community structure compared to those in susceptible varieties. Several bacterial taxa consistently enriched in resistant varieties showed negative ecological associations with P. oryzae, both at the local scale and across publicly available global metagenomic datasets. These findings indicate that seed endophytic bacterial communities are non-randomly structured in relation to host resistance phenotypes and may contribute to rice blast resistance through persistent ecological interactions with the pathogen. This work highlights the potential importance of seed-associated microbiota as intrinsic components of varietal resistance and provides a microbial perspective for improving durable disease resistance in rice breeding programs. Full article

Steel surface defect detection is essential for maintaining industrial production quality and operational safety. However, existing deep learning-based methods often encounter high computational costs, hindering their deployment on mobile devices. To effectively address this challenge, we propose a lightweight and efficient steel surface defect detection network based on feature segmentation and partially connected structures, termed LESSDD-Net. In LESSDD-Net, we first introduce a lightweight downsampling module called the cross-stage partial-based dual-branch downsampling module (CSPDDM). This module significantly reduces the number of model parameters and computational costs while facilitating more efficient downsampling operations. Next, we present a lightweight attention mechanism known as coupled channel attention (CCAttention), which enhances the model’s capability to capture essential information in feature maps. Finally, we improve the faster implementation of cross-stage partial bottleneck with two convolutions (C2f) and design a lightweight version called the lightweight and partial faster implementation of cross-stage partial bottleneck with two convolutions (LP-C2f). This module not only enhances detection accuracy but also further diminishes the model’s size. Experimental results on the data-augmented Northeastern University surface defect detection (NEU-DET) dataset indicate that the mean average precision (mAP) of LESSDD-Net improves by 3.19% compared to the baseline model YOLO11n. Additionally, in terms of model complexity, LESSDD-Net reduces the number of parameters and computational costs by 39.92% and 20.63%, respectively, compared to YOLO11n. When compared with other mainstream object detection models, LESSDD-Net achieves top detection accuracy with the highest mAP value and demonstrates significant advantages in model complexity, characterized by the lowest number of parameters and computational costs. Full article

Coccidiosis, caused by an obligate intracellular parasite of the genus Eimeria, is the most economically parasitic disease in poultry. Long-term reliance on synthetic anticoccidials and ionophores has accelerated the emergence of drug resistance and intensified the need for effective, residue-free alternatives. This narrative review synthesizes findings from peer-reviewed studies published between 1998 and 2025, summarizing advances in non-antibiotic control strategies encompassing five domains: (i) phytochemicals and botanicals, (ii) functional nutrition and mineral modulators, (iii) microbial and gut modulators, (iv) host-directed immunological and biotechnological approaches, and (v) precision and omics-guided biotherapeutic platforms. These approaches consistently reduce lesion severity, oocyst shedding, oxidative stress, and mortality while improving growth parameters in a variety of Eimeria models. However, translation to field settings remains constrained by variable bioactive composition, limited standardization, inadequate pharmacokinetic data, and the scarcity of large-scale, multi-farm validation studies. This review provides a concise summary of current evidence and delineates critical knowledge gaps to guide the development, optimization, and deployment of next-generation anticoccidial strategies. Together, natural products and emerging biotechnologies provide a promising foundation for sustainable, high-welfare, antibiotic-independent coccidiosis control. Full article