Search Results (2,013)

Digital twins have become a central paradigm for cultural heritage documentation, monitoring, and preventive preservation. Yet, when cultural heritage systems promise prediction, simulation, intervention planning, and decision support, a more explicit account is needed of the computational commitments behind such claims. This position paper proposes the notion of the heritage world model as a conceptual and architectural abstraction that uses the semantic digital twin as its representational layer and extends it toward prediction, memory, uncertainty-aware reasoning, and intervention evaluation. We define a heritage world model as a structured, temporally updated, semantically grounded, and action-aware model of a heritage asset and its preservation environment, capable of integrating observations, estimating latent risk states, predicting plausible future trajectories, and evaluating interventions under uncertainty. The paper does not present a validated deployed system. Rather, it clarifies the architectural conditions under which a decision-support digital twin infrastructure could support the kind of world-model-like preservation system proposed here. It further argues that such a model becomes operationally meaningful only when it includes a human-supervised controller layer that maps semantic state, predicted risk trajectories, uncertainty, memory, and institutional constraints into preservation-relevant actions, alerts, monitoring adaptations, or requests for expert review. Sensor data, remote sensing, computational models, risk assessments, policies, and conservation actions are interpreted as possible observational, dynamic, and intervention layers of a heritage world model. The paper reviews adjacent work in heritage digital twins, semantic and reactive ontologies, risk-aware preservation, agentic AI, and modern AI world models, and proposes a research agenda for moving toward predictive, memory-bearing, and intervention-aware preservation intelligence. Full article

The transition towards sustainable manufacturing necessitates complex optimization that integrates economic goals with environmental factors, such as energy consumption and greenhouse gas emissions. This research addresses the critical challenge of optimizing the Incoming Quality Control (IQC) policy for raw material batches. The primary objective is formulated as a multi-criteria control problem that jointly minimizes the weekly final product cost, carbon footprint, and energy consumption. To handle sequential decision making under uncertainty, we adopt a scalarized reinforcement learning (RL) reward that combines these objectives into a single value function and explores different trade-offs through alternative weight configurations. To effectively handle the uncertainty in incoming quality and the sequential decision making required for dynamic control, the optimization problem is modeled as a Bayesian Adaptive Markov Decision Process (BAMDP). To maintain computational tractability despite the continuous belief space inherent in the BAMDP formulation, we employ a Deep Q-Network (DQN) architecture acting as an approximate dynamic programming solver. The Bayesian framework represents model uncertainty explicitly, updates beliefs as new inspection evidence becomes available, and allows prior domain knowledge on supplier quality to be incorporated into the learning process. The BAMDP formulation is used to learn a set of adaptive inspection policies that adjust the IQC strategy over time to achieve conflicting goals: reducing inspection costs while maintaining standard quality, minimizing energy consumption, and lowering CO₂-equivalent emissions. The goal is to find robust policies that balance these trade-offs under different quality and demand conditions. This methodology aligns with the principles of Industry 5.0 by leveraging advanced artificial intelligence (AI) methods, such as reinforcement learning (RL), coupled with a stochastic simulation of the production system, based on a geometric/physical model of the component’s tolerance chains, to support decision-makers in designing and assessing sustainable IQC strategies. Comparative simulations on the case study, including a benchmark against ISO 2859-1 sampling plans, confirm that this dynamic and risk-aware optimization paradigm can reduce overall cost, energy use, and environmental impact across various quality conditions, while preserving outgoing quality. Full article

This research advances the study of learning under non-stationary conditions by proposing a unified framework for concept drift detection and adaptive regression in evolving data streams. Unlike traditional batch models that assume static data distributions, the proposed approach operates sequentially, enabling real-time adaptation to drifting concepts in both time series and regression tasks. The method integrates Least Squares Support Vector Regression (LS-SVR) with Least Squares Support Vector Data Description (LS-SVDD) to jointly perform prediction and drift monitoring within a single kernel-based structure. LS-SVDD serves as a distributional drift detector, while LS-SVR incrementally updates model parameters to maintain predictive accuracy as data evolves. The framework accommodates both abrupt and gradual drifts, making it suitable for dynamic, high-dimensional environments. Experimental evaluations on synthetic data show that this proposal is able to outperform conventional batch and static methods in accuracy, responsiveness and computational efficiency. This method was compared using a real-world dataset, namely the high-dimensional Drosophila microarray time series, to demonstrate that the proposed approach is able to detect the meaningful change points using the whole data which is not doable using existing methods. Existing methods only used subsets of the dataset. These results highlight the potential of LS-SVR and LS-SVDD integration for real-time, adaptive learning across diverse domains where data distributions change over time. Full article

Using a complex network evolutionary game model, this study examines the effects of policy incentives, certification mechanisms, price premiums, production costs, and neighborhood learning on farmers’ adoption of organic farming technologies. It aims to reveal the dynamic mechanisms of organic farming technology diffusion under subsidy policies and certification mechanisms. Numerical simulations are conducted to analyze the effects of the subsidy rate and the effectiveness of organic certification on the diffusion level of organic farming technologies. The results show that both subsidy policies and certification mechanisms can promote the diffusion of organic farming technologies; however, the effect of subsidy policies is relatively limited, whereas certification mechanisms play a more significant role. Furthermore, the effects of the subsidy rate and certification effectiveness are influenced by factors such as the proportion of consumers with a preference for organic products, increased production costs, and the organic price premium. Under different levels of bounded rationality and strategy updating rules, the combined “subsidy–certification” policy consistently outperforms single-policy scenarios, with certification mechanisms generally exerting a stronger promotional effect than subsidy policies. In addition, the initial adoption proportion and network size also affect the evolutionary outcomes of the system. A higher initial adoption proportion cannot sustain a higher steady-state diffusion level in the long run, while an increase in network size tends to weaken the effectiveness of policy interventions. Finally, this study proposes policy recommendations, including improving certification and market development mechanisms and strengthening information dissemination and technical service systems, thereby providing practical insights for promoting the diffusion of organic farming technologies. Full article

Micro quadrotor unmanned aerial vehicles (UAVs) are highly sensitive to external disturbances and model uncertainties because of their small mass, low moment of inertia, and limited onboard computational resources. To improve the disturbance rejection and trajectory tracking performance of micro quadrotor UAVs, this paper proposes an event-triggered extended state observer (ET-ESO)-based prescribed-time funnel control (PTFC) method. First, a control-oriented dynamic model of the micro quadrotor is established, in which wind disturbances, unmodeled aerodynamic effects, damping uncertainties, and parameter perturbations are represented as lumped disturbances in the translational and rotational subsystems. Then, two event-triggered ESOs are designed to estimate the lumped disturbances of the velocity and angular velocity channels. Compared with conventional continuously sampled ESO schemes, the proposed event-triggered mechanism reduces the frequency of sensor-to-controller information transmission while preserving disturbance estimation capability. Furthermore, a prescribed-time funnel control law is developed to constrain the position and attitude tracking errors within predefined performance boundaries and ensure convergence to the desired accuracy region within a user-specified time. Lyapunov-based stability analysis is provided to prove the boundedness of all closed-loop signals and the validity of the prescribed funnel constraints. Finally, MATLAB/Simulink simulations based on the Parrot Mambo mini-drone parameters are conducted to verify the effectiveness of the proposed method. The results demonstrate that the proposed controller achieves robust trajectory tracking, effective disturbance compensation, improved transient performance, and reduced control update frequency. Full article

This paper investigates the tracking control problem for a class of networked nonlinear systems in a non-ideal communication environment, where both internal communication constraints (delays and packet dropouts) and external random deception attacks are taken into account. From a symmetry perspective, the backward and forward channels constitute a paired sensing–actuation structure, and channel-dependent imperfections may destroy their functional coordination. To compensate for the resulting sensing–actuation mismatch, a data-driven sliding-mode predictive tracking control scheme is developed without relying on an explicit system model. First, an equivalent dynamic linearization is adopted to represent the input–output behavior using a data-dependent incremental model. Then, using delayed measurements together with historical input–output data, an online estimator is constructed to update the pseudo partial derivative (PPD). Based on the estimated PPD, a multi-step predictor is further designed to generate the predicted outputs, and a data-driven sliding-mode predictive tracking controller is proposed by imposing a discrete reaching law on the predicted outputs. Rigorous analysis is provided to ensure the stability of the closed-loop system and to guarantee that the tracking error remains bounded, together with an explicit bound that reveals the influence of the delay horizon, estimation mismatch, and attack amplitudes. Finally, numerical simulations under square-wave and sinusoidal references validate the effectiveness and robustness of the proposed approach. Full article

City-scale unmanned aerial vehicle vision-and-language navigation (UAV-VLN) requires accurate upstream target localization from an overhead map, onboard observation, and language description. Existing VLM-based methods often treat road names, landmarks, and spatial relations as raw text, leaving the model to search a large map and implicitly infer geometric constraints. This paper proposes GPOD, an inference-time candidate-prior interface for the upstream target-localization stage in city-scale UAV-VLN. GPOD converts language anchors, spatial relations, target-category cues, static map objects, and vehicle detections into ranked candidate priors through branch-specific candidate generation, thereby reformulating unconstrained full-map coordinate regression as candidate-prior-conditioned coordinate prediction. The static branch aligns language constraints with map-object geometries, while the dynamic branch uses YOLOv8l-VisDrone with Slicing Aided Hyper Inference (SAHI) to construct detection-conditioned vehicle candidates. In the GPOD-VLM setting, ranked candidates are injected as structured spatial prompts and the base VLM predicts the final continuous coordinates; GPOD-Direct is a candidate-direct diagnostic variant that directly uses candidate centers without VLM coordinate regression. On the CityNav localization protocol, GPOD improves FlightGPT Overall SR@20m from 15.23% to 25.61% and consistently reduces Mean Navigation Error (Mean NE) across splits and backbones. On Val-Unseen, GPOD-Direct (Top-1) reaches 32.59% SR@20m, showing that ranked candidate priors provide strong discrete localization signals. These results show that inference-time candidate priors can reduce city-scale search ambiguity without updating the base VLM parameters, while also revealing a candidate-utilization gap in the current prompt-based continuous coordinate-regression interface. Full article

Rockfall from slope unstable rock masses is a typical geological hazard induced by brittle failure, with abrupt occurrence, limited macroscopic deformation before failure, and a short warning lead time. Conventional static analysis methods are useful for design-stage stability checks, but they cannot continuously capture structural-plane damage or update the stability state in real time. Dynamic evaluation based on structural dynamics links measurable parameters such as natural frequency, damping ratio, mode shape, vibration trajectory, wave velocity, and energy dissipation to the degradation of structural planes. This review synthesizes the dynamic behavior mechanism, parameter system, theoretical models, sensing technologies, and engineering applications for slope unstable rock masses. Different from previous reviews that mainly summarize rockfall monitoring or conventional slope stability analysis, this paper organizes the literature by failure mode, monitoring scale, model assumptions, field validation, uncertainty sources, and engineering applicability. The single-degree-of-freedom models for sliding-, toppling-, and falling-type rock masses, multi-block chain-collapse models, and data-physics dual-driven surrogate models are compared critically. Contact monitoring based on MEMS sensors, non-contact LDV monitoring, acoustic emission, microseismic monitoring, coda wave interferometry, and cloud-edge early-warning architectures are further reviewed. Key challenges include field-scale validation under heterogeneous and anisotropic geological conditions, environmental compensation, robust threshold calibration, and probabilistic linkage between dynamic indicators and failure probability. The review provides guidance for selecting dynamic evaluation models, designing field monitoring systems, and developing full-life-cycle digital-twin platforms for rockfall risk mitigation. Full article

Due to the indispensable use of the internet, malicious actors have exploited URLs as a threat source of network information security and integrity. URL detection based on traditional methods has become inefficient against the uncontrolled increase of URLs, especially when facing dynamic and large-scale threats. To address the limitations of traditional methods and to provide intelligent and scalable detection of malicious URLs, this study proposes the hybrid framework (NetGuard) by integrating probabilistic data structures (PDSs) with machine learning (ML) capabilities. The proposed NetGuard utilizes PDSs to develop a Hybrid Scalable Detection Filter (HSDF), which combines the strengths of counting Bloom filters (CBFs) (deletion capability) and Scalable Bloom filters (SBFs). The proposed HSDF provides efficient membership queries under bounded false-positive rates (approximately 0.01) and ensures efficient data management and low-latency lookups on a scale of 10⁻⁵ s. On the other hand, NetGuard leverages the ML classifier capabilities to train and package a learned classifier for detecting malicious URLs. The proposed framework utilizes Decision Trees (DTs) and Random Forest (RF) classifiers. The proposed classifiers are trained by a novel SupURLsIdDs dataset which includes fifteen distinctive lexical and structural URL features extracted from four URL classes: benign, defacement, malware, and phishing URLs. The experimental results indicated the effectiveness of the HSDF in insertion and deletion operations, with minimal memory consumption (approximately 2.7 MB for 222,000 URLs) while maintaining a controlled false-positive rate (approximately 0.01 on Real-only subset up to 0.12 with synthetic data). The HSDF memory footprint represents a 99.88% enhancement compared to the RF model (which demands 2253.17 MB); thus, the HSDF complements RF as an ultra-lightweight first line of defense. The ML classifiers showed the superiority of RF, which achieved an overall classification accuracy of approximately 96% on large-scale URL data. These experiments are conducted using benchmark datasets constructed from aggregated real and synthetic data to demonstrate the scalability, adaptability, and resource efficiency of the first phase of NetGuard as a practical foundation for real-time web threat detection. The real-time integration and dynamic updates are presented as a deployment architecture and constitute future work. Full article

Accurate estimation of the utility harmonic impedance at the Point of Common Coupling (PCC) is critical for harmonic pollution management in industrial power grids. Existing non-invasive methods rely heavily on restrictive assumptions that are rarely satisfied in practice, and conventional filtering-based approaches suffer from accuracy degradation in dynamic scenarios due to fixed-rule updates of the noise covariance. This paper proposes a deep reinforcement learning (RL)-optimized adaptive extended Kalman filter (AEKF) method for robust harmonic impedance estimation. A state-space model is established without restrictive assumptions, and a deep Q-network (DQN) framework is designed to optimize noise covariance updates adaptively. Simulation results show that the method achieves reliable estimation under normal conditions. Although errors rise under strong noise, it remains stable and exhibits better noise robustness than conventional methods. Field measurements in actual power grid environments further verified the feasibility and application potential of the proposed method in field engineering. Full article

Real-time monitoring of lithium-ion capacitors (LICs) is crucial for ensuring reliability and predictive maintenance in dynamic applications such as electric transportation. However, traditional electrochemical impedance spectroscopy (EIS) techniques are complex and costly for onboard diagnostics due to their reliance on external excitation signals and dedicated hardware. Therefore, this paper presents an innovative framework for online state of health (SOH) estimation that bypasses these limitations by utilizing fast Fourier transform (FFT)-based passive impedance extraction directly from operational current and voltage signals. From experimental data, the equivalent circuit model (ECM) is developed, as well as its parameters, such as ohmic resistance, charge-transfer resistance, and Warburg diffusion. These parameters are identified through the extraction of impedance points in the low frequency region through FFT and the series resistance point using ohmic measurement, then performing a periodic curve fitting to these points. These curve fittings provide extracted ECM parameters. These parameters are used with a trained model to estimate the SOH of the monitored cell and are updated online. The proposed method was experimentally validated on five LIC cells aged under various C-rates (1C, 4C, 7C) and temperatures (35 °C, 40 °C, 50 °C), showing consistent impedance evolution with capacity fade. Validation of the utilized machine learning models, such as Polynomial Regression (PR), principal components analysis (PCA), and random forest (RF) regression, achieved SOH prediction errors as low as 2.23% compared to experimental results. The developed framework is particularly suitable for applications such as flash-charged electric buses but is broadly applicable across other energy storage systems as well. This advanced method enables real-time diagnostics without hardware modification, offering significant potential for integration into existing battery management systems (BMSs). Full article

As Flying Ad Hoc Networks (FANETs) are highly vulnerable to security threats such as identity spoofing, session replay and man-in-the-middle attacks in open-air channels, it is crucial to design an authentication key agreement (AKA) scheme to ensure the security of unmanned aerial vehicle (UAV) swarm networking within FANETs. However, existing AKA schemes for FANETs often struggle to balance authentication efficiency and high dynamism within UAV swarms whilst meeting necessary security requirements. To address the issue, this paper proposes CUBAT-AKA (Collaborative UAV Batch Authentication and Tree-based Key Agreement), a lightweight UAV swarm authentication and key agreement scheme based on batch verification and a binary tree structure. The scheme constructs a secure and lightweight three-party authentication mechanism based on aggregated verification and the Chinese Remainder Theorem (CRT). By offloading computational tasks to the authentication center and aggregating authentication responses in batches, it significantly improves the efficiency of UAV access authentication in large-scale FANET scenarios. To address the dynamic nature of UAVs frequently joining and leaving clusters in FANETs, an improved binary tree-based key agreement method has been designed, reducing key update overhead to a logarithmic level and enabling lightweight session key distribution and updates for UAV clusters. Security analysis demonstrates that, under the random oracle model, CUBAT-AKA is resistant to eavesdropping, replay, man-in-the-middle, impersonation and collusion attacks, whilst ensuring forward and backward security during member changes. Performance analysis indicates that this scheme offers significant advantages over comparable solutions in terms of both UAV cluster access authentication efficiency and dynamic key agreement overhead. Full article

The adaptive regulation of student productivity remains a challenging problem in technology-enhanced learning environments due to the continuous and uncertain nature of cognitive effort, attention, and behavioral fluctuations. While existing educational intervention models are predominantly based on discrete-time decision frameworks, they often provide limited support for the representation of stochastic productivity dynamics and continuous effort adaptation. This paper proposes a continuous-time stochastic optimal control framework for adaptive effort allocation in student productivity regulation. The learner productivity level is modeled as a bounded stochastic diffusion process evolving on the interval ([0, 1]), where the drift and diffusion coefficients depend on both effort allocation and learner-specific psychological characteristics. The control objective is formulated as the maximization of an expected cumulative productivity reward penalized by excessive cognitive effort over a finite study horizon. Using the Hamilton–Jacobi–Bellman (HJB) framework, we derive an optimal state-dependent feedback policy that dynamically adjusts effort allocation according to the current productivity level, the remaining study horizon, and the learner profile. We establish the well-posedness of the controlled stochastic dynamics and show that the productivity state remains invariant within the admissible interval. The resulting HJB equation is solved numerically using a semi-implicit finite-difference approximation combined with iterative feedback updates. Simulation experiments conducted on synthetic learner profiles illustrate the qualitative behavior of the proposed controller under heterogeneous psychological configurations. Compared with constant-effort and threshold-based heuristic strategies, the adaptive feedback policy produces smoother productivity trajectories and more stable effort allocation patterns under stochastic perturbations. The proposed framework provides a mathematically grounded approach for studying adaptive productivity regulation under uncertainty and establishes a foundation for future data-driven calibration and personalized intervention systems. Full article

In this paper, we propose a self-learning digital twin (SLDT) architecture that incorporates real-time battery degradation modeling and optimum operational management for grid-scale lithium-ion battery energy storage systems (BESS). This work extends the Adaptive Real-Time Degradation Model (ARDM) framework to allow real-time updates of the parameters based only on live operational data without pre-cycling experiments and further improves its robustness under various depth-of-discharge (DoD), charging/discharging current (C-rate), and temperature conditions. The ARDM is incorporated in a real-time digital twin that maintains synchronized health, state of charge (SoC), and degradation cost predictions. The digital twin is linked to an Optimization and Control Layer (OCL), which plans the charge/discharge day-ahead in advance based on dynamic power rates. The Musical Chairs Algorithm (MCA) is used for parameter identification and scheduling due to its better convergence characteristics compared to swarm-reduction forms of benchmark optimization algorithms. Experimental validation is carried out on two commercial 48 V Li-ion modules with various cycling patterns, and sub-millipercent root-mean-square error (RMSE) is achieved in capacity-fade tracking. The economic analysis for a 5-MW/10-MWh system indicates that dynamic tariff scheduling results in about nine times greater arbitrage revenue compared to fixed rates, 41–58% higher yearly net income, and lower degradation costs. The results confirm that the SLDT is a practical and accurate platform for degradation-aware operational planning in modern smart-grid environments. Full article

Based on outer raceway control theory and a five-degree-of-freedom quasi-static model of angular contact ball bearings, a raceway wear model considering curvature radius variation is proposed, which couples the quasi-static model with a modified Archard wear formulation and a dynamic curvature radius update mechanism. As wear accumulates, the worn curvature radii are fed back into the quasi-static model to recalculate the raceway contact dynamic parameters. Taking the SKF 7012ACE/HCP4A spindle bearing as an example, the wear depth evolution and the variations of contact ellipse area, contact stress, sliding velocity, and wear coefficient with wear time are investigated under combined loads. The results indicate that as wear progresses, the raceway curvature radii increase, leading to a decrease in contact ellipse area but an increase in contact stress and sliding velocity, which in turn accelerates the wear process. The findings demonstrate that the degradation of raceway curvature radius has a cumulative and non-negligible influence on wear evolution and should be incorporated into bearing wear calculations for more accurate life prediction. Full article