Search Results (1,106)

The electricity demand of artificial intelligence (AI) data centers is growing faster than the grids hosting them can decarbonize, yet carbon-aware computing is rarely audited at the system level: workloads follow scalar-price or carbon signals, whose claimed savings need not survive network-wide dispatch. We develop a carbon-aware co-optimization framework that schedules checkpoint intervals, workload migration, dynamic voltage and frequency scaling, and behind-the-meter storage jointly with unit commitment, pricing system CO${}_2$ emissions beyond the market-internalized level, with split-conformal scenario bands and an out-of-sample cost certificate. On IEEE 39/118-bus systems mapped to 2025 French and German measurements, carbon-priced dispatch reduces emissions by 29.5% at a generation-cost premium below 0.01% (the carbon-signal headroom of this mapped system); system-level decomposition attributes more than 99% of this reduction at reference penetration to generation redispatch, an operator-side instrument. AI-load flexibility adds 0.23% of system emissions today, equivalent to about one quarter of the data-center fleet’s own carbon footprint, and 3.3% at gigawatt scale, where it cuts worst-day load shedding by up to 49%. The endogenous checkpoint policy recovers the reliability-optimal interval, whereas following the average carbon-intensity signal can increase system-level emissions. Conformal calibration maintains at-or-above-nominal coverage (97.5%); empirical bands under-cover (86.0%). Full article

Traditional weight measurement methods need cutting or weighing of the fruit, and this is not practical for preharvest evaluation and market transactions. The suggested approach gives a practical solution for farmers and sellers by giving accurate weight predictions using only external characteristics. Modern technologies, especially artificial intelligence, data analytics and machine learning, are making big changes in the agricultural area. One of the machine learning models used in agriculture is Artificial Neural Networks (ANN). ANN became an important tool in analyzing agricultural data, predicting plant growth processes, finding diseases, determining the effects of environmental factors, reaching productivity goals and detecting weeds and harmful plants. A dataset is created by comprehensively examining 52 watermelons. The dataset includes acoustic properties, geometric measurements, and visual characteristics. The dataset is divided into 40 training samples and 12 test samples. Balanced representation is ensured by using stratified sampling when selecting test samples. The Min-Max normalization method is used for data preprocessing. Nine different training algorithms are comprehensively evaluated within the scope of the study. Eight critical parameters of the ANN models are optimized using four different optimization algorithms to increase the accuracy rate and avoid overfitting. Artificial Bee Colony (ABC), Artificial Fish Swarm Algorithm (AFSA), Whale Optimization Algorithm (WOA) and Grey Wolf Optimizer (GWO) are used as optimization methods. Assessed by five-fold cross-validation, the best configuration (One Step Secant with WOA) achieved a mean absolute error of 0.92 ± 0.28 kg and an RMSE of 1.23 ± 0.37 kg, corresponding to about 10% of the mean fruit weight. Developing a real-time mobile application using the optimized best model will provide practicality in large-scale agricultural enterprises, controlled environments such as greenhouses, and agricultural markets. Full article

Accurate and efficient early pregnancy diagnosis (EPD) in livestock is crucial for optimizing breeding management and enhancing productivity in modern animal husbandry. Over the past century, EPD technology has evolved from empirical methods to sophisticated techniques, encompassing biochemical marker detection, ultrasonic imaging, and further extending to emerging non-invasive approaches such as infrared thermography (IRT) and spectroscopic analysis. These advancements have not only improved diagnostic accuracy but also broadened the research scope to include small livestock and multiple species. This review critically examines the historical evolution, current methodologies, and applications of EPD technology, with a focus on analyzing the advantages and limitations of both traditional and emerging techniques. Additionally, it explores the potential of multimodal fusion strategies and artificial intelligence (AI) in EPD. At present, machine vision, wearable monitoring, and several AI applications remain prospective approaches rather than validated tools for routine EPD. The conclusion highlights that, despite significant progress, current technologies still face limitations in achieving in situ, non-contact, and high-throughput detection. Looking ahead, the integration of cutting-edge technologies, such as AI, small wearable sensors, and physiological time-series data analysis, holds promise for overcoming these bottlenecks, enabling more intelligent and efficient pregnancy diagnosis, and providing scientific support for modern animal husbandry. Full article

Automated guided vehicles (AGVs) and autonomous mobile robots (AMRs) are among the key enabling technologies driving intelligent logistics and industrial automation. Despite their widespread adoption and rapid technological evolution, the literature often addresses AGV and AMR systems in a fragmented manner, lacking a structured methodological perspective that highlights their architectural foundations, levels of autonomy, and technological maturity. This paper presents a methodological survey of AGV and AMR technologies, focusing on system-level architectures and core functional components rather than isolated algorithms. The survey systematically analyzes key technological dimensions, including sensing and perception, localization and positioning strategies, navigation and path-planning approaches, communication infrastructures, and multi-robot coordination mechanisms. A clear distinction is drawn between classical AGV systems, which rely on fixed infrastructure and predefined routes, and AMR systems, which exhibit adaptive, perception-driven, and self-configuring behaviors enabled by artificial intelligence techniques. Rather than proposing new algorithms, this paper organizes existing approaches into a coherent framework that highlights technological transitions from infrastructure-dependent guidance to autonomous, data-driven navigation. Recent trends such as cloud–edge integration, learning-based navigation, scalable fleet management architectures, and cooperative multi-robot systems are reviewed and discussed from a methodological standpoint, emphasizing their role in increasing flexibility, robustness, and operational efficiency in industrial and logistics environments. The survey also addresses cross-cutting challenges, including system transparency, safety and certification, interoperability, and sustainability. Finally, this paper outlines research directions aligned with the principles of Industry 5.0, highlighting the need for human-centered, resilient, and scalable AMR and AGV systems capable of safe and explainable operation in complex industrial contexts. Full article

Forensic research may involve living persons, deceased persons, human tissues, genetic data, records and images, judicial exhibits, animals, and artificial-intelligence systems. Although existing ethical instruments establish essential principles, they provide limited operational guidance for determining what must be authorised, protected, and documented before a specific study begins. FORETHICS was developed through a normative functional analysis of internationally recognised ethical instruments and selected forensic literature. Requirements were organised according to the governance function performed and examined across object-specific research scenarios. The resulting framework translates general principles into a common decision grammar comprising five foundational components, seven independent ethical axes, eight object-specific modules, cross-cutting modifiers, fifteen Hard Stops, a ten-gate decision pathway, and ten study-specific Decision Cards. Its Core Rule requires every project to establish who lawfully controls access for the proposed use, why the research is scientifically necessary, which safeguards are required, and what minimum documentation demonstrates decision readiness. The ethical object assessed is therefore the proposed research use rather than the specimen, record, or dataset in isolation. FORETHICS does not replace national law, ethical review, judicial authority, data-protection assessment, or animal-welfare oversight. It provides a candidate architecture for making forensic research governance more explicit, traceable, and comparable across jurisdictions while preserving locally lawful pathways. The framework has undergone internal scenario-based examination but has not yet been externally or empirically validated. Multidisciplinary consensus, inter-rater testing, cross-jurisdictional evaluation, and prospective usability studies are therefore required before implementation as an international decision-support standard. Full article

The rapid evolution of Large Language Models (LLMs) has opened new frontiers in cybersecurity automation, enabling intelligent agents capable of multi-step reasoning, tool invocation, and autonomous decision-making across complex security tasks. While individual applications have emerged across threat intelligence, vulnerability assessment, penetration testing, and security operations center (SOC) automation, a systematic understanding of the LLM-based agent paradigm in cybersecurity—encompassing both single-agent and multi-agent architectures—remains lacking. This paper presents a systematic literature review following PRISMA guidelines, identifying records through 59 structured web-search queries whose results resolve predominantly to arXiv, Semantic Scholar, the ACM Digital Library, IEEE Xplore, USENIX, MDPI, SpringerLink, and Elsevier ScienceDirect, supplemented by citation chaining, for works published between January 2022 and April 2026; the full query record is published with the paper. We applied structured inclusion and exclusion criteria and classified 59 primary studies along five dimensions: security function, agent architecture pattern, knowledge augmentation strategy, human-in-the-loop posture, and evaluation rigor. Our analysis reveals that penetration testing and threat intelligence are the most extensively studied domains, while incident response and compliance verification remain critically underrepresented. Penetration testing alone accounts for over half the corpus (50.8%). Single-agent tool-calling remains the most prevalent architecture (30.5% of studies), whereas centralized multi-agent orchestration—present in 18.6%—yields the strongest reported performance gains, up to 4.3× on zero-day exploitation; prevalence and performance therefore point in opposite directions. No included study achieves production-grade (E4) evaluation: the entire field currently rests on controlled laboratory assessments. An independent search of six bibliographic databases recovers 86.3% of the studies the primary search had surfaced (79.7% of the full corpus) while indicating a total eligible literature of roughly 400 studies, so the corpus is reported as a documented subset rather than an exhaustive census. We propose a unifying taxonomy, identify cross-cutting challenges including hallucination, prompt injection, and benchmark fragmentation, and outline open research directions with particular emphasis on multi-agent orchestration design. Financial sector applicability under DORA and the EU AI Act is treated as a documented evidence gap rather than a synthesis: the corpus’s only compliance and risk assessment study is also its only banking-specific system. Full article

The construction industry’s dependence on ordinary Portland cement (OPC) makes low-carbon binder systems an urgent priority; yet, the nonlinear interactions among multiple supplementary cementitious materials (SCMs) and nanomaterials complicate rational mix design. This study fuses explainable artificial intelligence (XAI) with a hierarchy of closed-form mathematical formalisms and an experimental durability programme for a quaternary sustainable concrete in which OPC is partially replaced by sugarcane bagasse ash (SCBA, 40 kg/m³), ground granulated blast furnace slag (GGBS, 60 kg/m³), natural zeolite (20 or 40 kg/m³) and nano-silica (0–20 kg/m³) at a constant water–binder ratio of 0.45. Thirteen mixes were tested for compressive and flexural strength, rapid chloride penetration (RCPT) and sulfuric acid resistance at 7, 28 and 56 days. The optimum blend (12 kg/m³ nano-silica) reached 45.0 MPa at 28 days, 49.5% above the control, while reducing chloride charge by 70% and acid mass loss by 65%. Information theoretic discrimination among three competing hydration kinetics laws selects the hyperbolic rate model with an Akaike weight of 1.000 (ΔAIC_c > 32), showing the blend raises the ultimate strength ceiling by 46% while delaying half-strength by only two days. Within this mix series, effective binder (k-value) analysis indicates that, at low dosage, one kilogram of nano-silica contributes 28-day strength broadly comparable to that of several tens of kilograms of OPC (a dataset-specific, dose-dependent estimate rather than a general mass equivalence), and three independent estimators—the experimental peak, the response surface stationary point (12.8 kg/m³) and the marginal efficiency zero (13.2 kg/m³)—converge on an optimum nano-silica dosage of 3.0–3.3% of binder. Principal component analysis compresses the six-dimensional strength–durability response into a single latent statistical axis (interpreted as an indicator of pore connectivity) carrying 91.5% of the variance, and a Fickian error function solution seeded by Berke–Hicks conversion of RCPT charge projects a 3.4-fold extension of the chloride-initiation service life (36.7 versus 10.8 years at 50 mm cover). Six machine learning models were benchmarked; extremely randomized trees performed best (R² = 0.9905, RMSE = 0.920 MPa; leave-one-out R² = 0.986; bootstrap 95% CI on R² [0.981, 0.996]), and SHAP force plot attributions were triangulated with Sobol global sensitivity indices (curing age 75.4%, nano-silica 23.1% of output variance) and response surface significance tests. The optimized mixes cut embodied CO₂ by 26–32% and improve eco-strength efficiency 2.1-fold; grey relational analysis over six strength, durability and carbon criteria ranks the 12 kg/m³ nano-silica mixes first. The framework demonstrates how interpretable machine learning, information theoretic model selection, diffusion theoretic service-life projection and experimental durability evidence can be unified into a transparent, physically validated basis for sustainable concrete mix design. Full article

The increasing importance of artificial intelligence (AI), digital transformation, and sustainability challenges requires organizations to rethink traditional approaches to strategic performance management and enterprise value creation. Although the Balanced Scorecard (BSC) remains one of the most widely used strategic management frameworks, its traditional architecture does not fully capture the growing importance of AI-driven decision-making and sustainable digital transformation. This study develops an extended BSC framework that retains the four traditional perspectives—financial, customer, internal process, and learning and growth—while incorporating two complementary components with distinct architectural roles. AI-enabled decision and innovation capability is positioned as an enabling layer that converts organizational knowledge, digital skills, data, and technological resources into improved decision-making, experimentation, and innovation. Sustainable digital governance is positioned as a cross-cutting dimension that aligns digital transformation with ESG priorities, cybersecurity, resilience, responsible AI use, and long-term stakeholder value. A pilot expert content-validity assessment involving 14 experts was conducted to preliminarily assess the conceptual coherence, professional plausibility, and operational feasibility of the proposed architecture, relationships, and KPIs. The pilot findings provide expert-perceived preliminary support for the coherence of the framework and identify areas requiring further refinement, particularly the operationalization of selected AI- and governance-related indicators. The pilot assessment should therefore be interpreted as an initial content-validity and plausibility assessment rather than as statistical validation or empirical confirmation of the proposed causal relationships. Full article

Accurate portioning of bone-in pork ribs remains challenging because of their curved geometry, uneven meat thickness, and irregular bone–meat distribution. To address this issue, we developed a semi-automatic two-stage pork rib cutting system based on 3D line laser scanning. In the first stage, inter-rib seams were identified from the point cloud of a whole rib rack to determine cutting positions. The separated rib strips were then manually reloaded, aligned, and rescanned. In the second stage, skeleton curves were extracted and adaptive equal-arc-length cutting positions were generated within a preset range of 40–50 mm. The segmentation method was evaluated on 20 independent pork rib racks and achieved mean precision, recall, F1-score, and overall accuracy values of 0.936, 0.918, 0.927, and 0.931, respectively. In the cutting experiment, three racks containing 32 rib strips produced 163 final portions. The pooled rib-seam cutting success, length qualification, bone fracture, and overall cutting success rates were 89.66%, 89.57%, 5.52%, and 87.73%, respectively. The operating cycle time was approximately 120 s per rack, corresponding to a nominal throughput of 30 racks h⁻¹. These results indicate that the system can identify rib seams and produce uniform portions, providing a feasible approach for semi-automatic processing of bone-in pork ribs. Full article

Advanced manufacturing and cutting machinery often operate under variable material properties and uncertain load conditions, making real-time process optimization difficult when high-fidelity simulations and physical experiments are costly. To address this problem, this study proposes a physics-guided surrogate-assisted reinforcement learning framework for multi-objective speed regulation of coal–rock cutting machinery. The haulage speed and drum rotational speed are jointly optimized to balance production rate, cutting specific energy consumption, current load, vibration impact, and speed-regulation stability. First, an EDEM–RecurDyn–Simulink co-simulation model was established to obtain cutting current and vibration response data under different coal–rock structures and speed combinations. Similar-material cutting experiments were conducted to validate the vibration response, with root mean square (RMS) relative errors of 3.38%, 4.21%, 5.75%, and 5.03% under full-coal, single-gangue-layer, double-gangue-layer, and full-rock conditions, respectively. Based on these data, an improved physics-informed neural network (PINN) surrogate model was developed by embedding an equivalent coal–rock difficulty factor, a speed-matching factor, a semi-empirical current prior, and a vibration residual calibration mechanism. The surrogate model achieved R² values of 0.9623 and 0.9147 for cutting current and vibration kurtosis, respectively. It was then integrated into a Soft Actor–Critic (SAC) control environment to learn continuous dual-variable speed-regulation policies. Across five independent SAC training seeds, the improved SAC achieved an average theoretical productivity of 207.8033 ± 6.5641 t·h⁻¹ and a cutting specific energy consumption of 0.3387 ± 0.0114 kW·h·t⁻¹. Compared with the fixed-speed, empirical speed-regulation, and conventional SAC strategies, the proposed method increased the average theoretical productivity by 2.65%, 5.01%, and 1.77%, respectively, while reducing the corresponding specific cutting energy consumption by 1.37%, 4.05%, and 2.22%. These results demonstrate that the proposed framework provides an efficient intelligent optimization method for condition-aware speed regulation in complex industrial cutting processes. Full article

Existing DNAPL groundwater source inversion approaches are confronted with prominent bottlenecks: shallow surrogate models often fail to capture strong nonlinear multiphase flow relationships, traditional heuristic optimizers suffer from premature convergence, and ill-posed equifinality further degrades inversion reliability, together with prohibitive computational costs from repeated multiphase numerical simulation. Taking a typical chemical-contaminated site in Northeast China as the research object, this study establishes a multiphase flow numerical model that fully reproduces the migration and transformation mechanisms of chlorobenzene-based DNAPLs after systematic generalization of the site’s geological and hydrogeological conditions. To drastically cut the computational burden incurred during iterative inversion, high-quality datasets are generated via parameter sensitivity analysis and Latin hypercube sampling, based on which a deep convolutional neural network (DCNN)-driven high-fidelity surrogate model is constructed and embedded into the optimization framework as an equality constraint. A separated nonlinear programming model is formulated to independently quantify pollution source characteristics and hydrogeological parameters, with the objective of minimizing the residual error between field-measured and numerically simulated contaminant concentrations. A hybrid homotopy-particle swarm optimization (HH-PSO) algorithm is further proposed to address the limitations of conventional optimizers, including strong dependence on initial guesses and susceptibility to local optima. On this basis, a closed-loop feedback iteration scheme is developed, where source identification and parameter calibration are implemented alternately with bidirectional constraints and progressive correction to continuously refine and stabilize inversion outputs. This work presents distinct innovations in the methodology, algorithm, and practical application of DNAPL groundwater source inversion. Results from synthetic benchmark cases and on-site field applications demonstrate that the DCNN surrogate model achieves far higher fitting accuracy than shallow learning approaches (e.g., Kriging and support vector regression), with the coefficient of determination R² exceeding 0.99. After the feedback correction iteration procedure, the average relative error for retrieved source locations, release histories, and hydrogeological parameters drops to 3.72%, and the overall computational efficiency is elevated by approximately 99.84%. The integrated simulation–optimization inversion framework proposed in this work integrates monitoring signal denoising, multiphase numerical simulation, deep learning surrogate modeling, hybrid intelligent optimization, and feedback iterative correction. This integrated system effectively resolves core technical bottlenecks in DNAPL groundwater source inversion, such as nonlinear ill-posedness, equifinality induced by mutual interference between source terms and aquifer parameters, prohibitive computational costs of multiphase simulations, and premature convergence of traditional optimization algorithms. The established framework can serve as a robust theoretical foundation and technical tool for rapid, precise source tracing, pollution liability confirmation, and remediation design at complex contaminated sites. Full article

The growing deployment of distributed renewable generation, storage, electric vehicles, heat pumps, smart buildings, and controllable demand is expanding the flexibility available to local energy systems. Energy communities provide the governance context for collective participation and value creation, while community virtual power plants provide the operational mechanism for aggregating distributed resources and connecting them to local optimisation, flexibility markets, grid services, and resilience functions. This PRISMA-ScR-informed framework development study synthesises the literature from Scopus, Web of Science, and IEEE Xplore to examine how artificial intelligence supports community VPP operation, where agentic AI adds capabilities beyond established optimisation, reinforcement learning, and multi-agent systems, and which design requirements follow governed orchestration. The synthesis shows that current evidence is strongest for component-level forecasting, scheduling, bidding, adaptive control, distributed coordination, and digital-twin validation, whereas integrated agentic orchestration remains an emerging direction. Classical multi-agent systems already provide decentralised representation, communication, negotiation, and coordinated control; the additional role proposed for agentic AI is therefore narrower and concerns context-aware multi-step workflow orchestration, governed tool use, exception handling, grounded explanation, and bounded delegation across existing analytical and control services. The study introduces operational flexibility intelligence as the capability to transform potential distributed flexibility into deployable, authorised, market-, grid-, resilience-, and community-compatible action. It further develops a conceptual layered reference architecture in which agentic orchestration operates through governed tools and interfaces rather than bypassing validated resource controllers. Fairness, comfort, privacy, cybersecurity, resilience, auditability, and human-in-command authority are treated as cross-cutting operational constraints. The architecture defines a design and validation agenda rather than an empirically validated implementation. Full article

Digital twin (DT) technology has become a transformative engineering paradigm for metal-cutting machine tool systems and materials-processing equipment, enabling real-time synchronisation, predictive analytics, and intelligent decision-making throughout the entire production cycle. This systematic review summarises the latest advances in the engineering-oriented implementation of digital twins, with a focus on their modelling frameworks, tool condition monitoring, compensation for geometric, kinematic, thermal and dynamic errors, fault diagnosis and adaptive control, and on the application of this technology to lathes, milling machines and grinding machines. The search for and selection of literature were carried out in accordance with the PRISMA 2020 guidelines. In total, 680 records were identified in Google Scholar in May 2026, of which 197 studies met the inclusion criteria and were synthesised narratively within six thematic sections. The analysis demonstrates that modern digital twin architectures integrate multiphysics modelling, multi-sensor data fusion, and machine learning to create high-precision virtual replicas of physical assets. Predictive maintenance and fault diagnosis systems use machine learning and deep learning to detect incipient faults in feed systems, spindles, and other critical components before failure. The review also analyses existing challenges and outlines future research directions for reliable industrial digital twins. Full article

Organic waste causes severe pollution, while agriculture lacks quality fertilizers. Solid-state fermentation solves both issues. Nevertheless, traditional methods are slow and lead to nitrogen loss. They also emit greenhouse gases and yield uneven products. This fails to reach modern low-carbon standards. We urgently need efficient solid-state fermentation systems. Therefore, this review summarizes recent advances in parameter optimization and cutting-edge innovations. Firstly, key solid-state fermentation operational parameters, such as carbon-to-nitrogen ratio, aeration frequency, temperature, humidity and pH, are analyzed. The optimization of these parameters facilitates nitrogen retention and mitigates pollutant emissions. Secondly, emerging enhancement strategies are discussed. Elaboration on the electron-shuttle effect of modified biochar and advances in synthetic microbial consortia is provided. For process coupling, the mechanisms of hydrothermal carbonization (HTC) combined with solid-state fermentation are explored. Bioelectrochemically assisted solid-state fermentation (MCFT/BFC) based on Direct Inter-Species Electron Transfer (DIET) is also examined. Furthermore, feasible mitigation approaches for pollutants including greenhouse gases and antibiotic resistance genes (ARGs) are summarized. Subsequently, the applications of mathematical models, the Internet of Things (IoT), and artificial intelligence in solid-state fermentation are introduced. Finally, current challenges in large-scale application and risk management are analyzed. Future prospects involving multi-omics, life cycle assessment (LCA), and functional customization are discussed. Low-carbon solutions for high-value waste utilization are provided in this review. Full article

Digital technologies are increasingly reshaping contemporary visual art, not only through artificial intelligence and generative systems but also through material-based artistic practices. While existing scholarship has extensively explored computational creativity, digital aesthetics, and AI-generated imagery, less attention has been paid to how digital fabrication transforms artistic practice through its interaction with physical materials and spatial perception. This paper addresses this issue through a practice-based investigation of contemporary glass art. Drawing upon the author’s long-term artistic practice, the study examines two interconnected projects: the Glass Calligraphy Series and the Spatial Cutting Series. The first project explores how traditional Chinese calligraphy is translated into glass through digital drawing, vector-based design, and waterjet fabrication, revealing how artistic agency is redistributed among artist, software, fabrication systems, and material processes. The second project investigates how layered glass structures generate spatial depth, optical relationships, and embodied viewing experiences. The paper argues that digital fabrication should not be understood merely as a technical tool. Instead, it functions as a creative framework that reconfigures artistic agency, activates the material and spatial qualities of glass, and transforms viewer experience. By examining the intersection of computation, material practice, and visual perception, this paper proposes a broader understanding of digital fabrication as an integral component of contemporary visual art. It argues that digital technologies are not external instruments applied to artistic production but active agents in the formation of artistic methods, material relationships, and aesthetic experience. Full article