Search Results (1,049)

Unmanned Aerial Vehicles (UAVs) are gradually emerging as key platforms for Integrated Sensing, Communication, and Computation (ISCC) systems in next-generation wireless networks. However, strict resource constraints and task coupling make static allocation inefficient in dynamic environments. This paper studies a UAV-driven ISCC system in which a single UAV dynamically allocates communication bandwidth, sensing resources, and computing power. Considering that sensing data in mission-critical applications is highly time-sensitive, minimizing the response time is paramount. To reduce system latency while maintaining sensing quality and energy efficiency, we propose D3PG-Light, a deployment oriented and stability-enhanced refinement of the deep reinforcement learning framework, specifically tailored for real-time resource scheduling under UAV hardware constraints. D3PG-Light incorporates an adaptive gradient stabilization mechanism, Long Short-Term Memory (LSTM), and feature fusion to enhance training stability. Simulation results based on real air–ground channel measurements show that D3PG-Light converges faster and achieves more stable learning behavior than DDPG, TD3, and the original D3PG. In particular, the proposed method reduces the 95th-percentile latency from over 100 ms to approximately 24 ms, achieves higher converged reward values, and requires fewer than 50 k model parameters. These results demonstrate the effectiveness of D3PG-Light for latency-sensitive UAV-ISCC applications. Full article

Predicting the motion of ships and floating structures is essential for ensuring economical and environmentally friendly operations in the ocean. In this study, we propose a hybrid encoder–decoder Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) architecture to predict motions of a moored Floating Production Storage and Offloading (FPSO) vessel under varying sea conditions. The model integrates a CNN for spatial wave-field feature extraction and an LSTM encoder–decoder to capture temporal dependencies in vessel motion. Synthetic datasets were generated using mid-fidelity dynamics simulations of a coupled FPSO–mooring–riser system subjected to wave excitations. Five sea states ranging from calm to severe were considered to evaluate the model’s robustness. A key preprocessing step involved determining the optimal spatial domain for wave field input, and a wave field size of 600 m × 600 m was identified as the most cost-effective configuration while maintaining accuracy. The model was validated using the Root Mean Square Error (RMSE) or relative RMSE (RRMSE). Despite low RRMSE values in low sea states, predictions were noisier due to high-frequency, low-amplitude responses. In contrast, higher sea states yielded more stable predictions despite higher RRMSE values. The proposed method offers high-resolution motion forecasting capability, which can enhance operational safety and energy efficiency of offshore platforms, particularly when integrated with stereo camera-based wave monitoring systems. Full article

This research introduces a novel approach for seismic fragility assessment by employing a long short-term memory (LSTM) neural network to identify the most effective scalar and vector intensity measures (IMs). This approach enables the rapid and accurate plotting of vector fragility surfaces for shield tunnels embedded in layered soils and subjected to seismic actions. First, an extensive suite of two-dimensional, fully nonlinear soil–structure interaction analyses was executed to generate ground–motion–structure response pairs. These records were subsequently leveraged to train the LSTM network, which received free-field acceleration time histories and directly output critical engineering demand parameters along the tunnel lining. The developed framework significantly mitigates computational expenses while maintaining an acceptable level of fidelity relative to the reference finite element results. Consequently, it serves as an alternative to traditional time history evaluation techniques. Second, we conducted an IM screening process using the results of the LSTM predictions. On the basis of criteria such as relevance, efficiency, practicality, and professionalism, we benchmarked 17 scalar IM and 3 vector IM candidate schemes. The findings indicate that the peak ground velocity (PGV) serves as the most effective scalar IM, whereas the combination of peak ground acceleration (PGA) and PGV forms the optimal vector IM. Finally, probabilistic demand and capacity models are integrated within a fully analytical fragility formulation to derive both scalar and vector fragility estimates. Comparative evaluation reveals that vector IM based fragility surfaces markedly reduce epistemic uncertainty and furnish refined probabilistic descriptions of damage states (DSs) across the seismic demand space. Full article

Against the backdrop of sustainable development and global climate governance, this study focuses on the evaluation and trend prediction of provincial carbon emission efficiency and constructs a multi-model integrated analytical framework featuring “data preprocessing—efficiency decomposition—dynamic forecasting—policy deduction”. First, economic, energy consumption and carbon emission data for 30 provinces in China from 2009 to 2019 are collected. Data cleaning is performed through outlier identification and Lagrange interpolation, and a cross-regionally comparable quantification system is established based on a unified carbon emission standard, laying a foundation for subsequent analysis. Second, data envelopment analysis (DEA) is adopted to decompose carbon emission efficiency. It is found that approximately 23% of provinces lie on the technical efficiency frontier, with the average variance share of technical inefficiency being 0.62; 6% of provinces have the potential for scale expansion; and 10% suffer from diseconomies of scale, reflecting significant structural efficiency losses in regions concentrated with high-carbon industries. Third, the long short-term memory (LSTM) neural network is employed for dynamic forecasting and scenario simulation of carbon emissions by 2025. The model’s prediction error in 2019 is controlled within 8.7%. Simulation results show that when the share of clean energy rises to 35%, China’s national carbon emission growth rate can be reduced to 1.2% by 2025. However, multi-scenario sensitivity analysis indicates that the achievement of this target highly depends on policy enforcement intensity and power grid accommodation capacity. In addition, stochastic frontier analysis (SFA) reveals the heterogeneous contributions of different energy types to economic and social outputs. The consumption elasticities of electricity, liquefied petroleum gas and gasoline are significantly positive, whereas the negative elasticities of oil, fuel oil and coal deeply reflect the low energy utilization efficiency and rigid lock-in of high-carbon industries in some regions. Finally, combined with efficiency evaluation, trend prediction and mechanism analysis, differentiated emission reduction strategies are proposed for technologically backward provinces, scale-imbalanced provinces and clean energy base provinces, forming a complete closed loop from “efficiency diagnosis” to “future deduction” and then to “policy feedback”. This study breaks through the limitations of a single model. Through the coupling of parametric and non-parametric methods, as well as the integration of dynamic forecasting and scenario simulation, it effectively addresses issues such as data heterogeneity. It provides scientific support for local governments to formulate emission reduction policies and optimize energy structures, establishes a methodological foundation for industrial efficiency analysis and international carbon responsibility allocation research, and helps to promote regional clean, low-carbon, and sustainable development. Full article

To address the limitations of traditional runoff prediction methods—namely, the oversimplification of meteorological factor selection, ambiguous interactions among core variables, and the disruptive influence of redundant inputs—this study focuses on the Zijiang River Basin as a representative case. A suite of machine learning models, including Long Short-Term Memory Neural Network (LSTM), Convolutional Neural Network (CNN)-LSTM, Temporal Convolutional Network (TCN), and Gradient Boosting Regression Tree (GBRT), was constructed and trained using 13 distinct combinations of meteorological variables. These configurations were systematically evaluated to assess their compatibility with each model in simulating daily runoff patterns. Additionally, the Shapley Additive Explanations (SHAP) algorithm was employed to quantitatively assess the contribution of each factor to predictive accuracy. Among the models tested, the TCN model consistently demonstrated superior performance, particularly in mitigating the effects of irrelevant or redundant features. The GBRT model showed distinctive strengths in accurately predicting peak flow timings. Of all input configurations, the combination of “runoff + precipitation + evaporation + temperature” emerged as the most effective. Findings indicate that the predictive value of individual meteorological variables hinges primarily on their direct correlation with runoff, while the effectiveness of multi-factor schemes depends on the degree of functional integration—specifically, the coupling of hydrological recharge, consumption, and regulatory processes. The presence of redundant variables was found to impair model performance unless they contributed to a meaningful synergistic relationship with core inputs. The SHAP analysis further reinforced these insights: precipitation-related variables proved to be the most critical to prediction accuracy, whereas temperature and evaporation served more complementary roles. Notably, the inclusion of relative humidity tended to suppress runoff responses and increased deviation in peak timing estimates. These findings shed light on the nuanced interplay between meteorological input design and model selection, offering a robust foundation for optimizing data-driven runoff prediction frameworks. Full article

Virtual power plants efficiently aggregate distributed energy resources with small capacities but large quantities to participate in electricity market transactions through advanced control technologies. As the number of distributed power sources increases, issues such as output volatility and optimal decision-making need to be addressed. To tackle these problems, this paper proposes an optimal economic dispatch strategy for virtual power plants that accounts for flexible resource responses under uncertain scenarios. First, a combined prediction model based on variational mode decomposition (VMD) and an improved bidirectional multi-gated long short-term memory network is established to achieve accurate prediction of renewable energy output. On this basis, a price–demand elasticity matrix is constructed to characterize the spatiotemporal coupling effect of time-of-use electricity prices on load, and a demand response model based on optimal time-of-use electricity pricing is established. Meanwhile, an improved Particle Swarm Optimization (PSO) algorithm is employed to achieve efficient and precise solutions. Finally, the effectiveness and feasibility of the proposed method are validated and illustrated through an improved IEEE-33 bus test system. Full article

Historic buildings exhibit coupled response characteristics during long-term service, characterized by slowly varying global inclination evolution superimposed with local component-level deformation. Meanwhile, multi-source measurements are susceptible to environmental noise and structural non-integrality, which poses challenges to obtaining stable and physically interpretable inclination measurements. To address these issues, this study proposes a multi-source fusion monitoring method for global inclination and local deformation of historic buildings using an extended Kalman filter with fractional-order state modeling (FEKF). A state-space model incorporating global inclination, local component-level additional deformation, and their projection relationships is established, in which global inclination information derived from Global Navigation Satellite System (GNSS) and local observations obtained from inclinometers are formulated within a unified measurement framework. Fractional-order dynamics are introduced into the state evolution model to represent the long-memory and non-stationary characteristics of structural responses in historic buildings. By adopting a finite-memory approximation, the fractional-order model is embedded into the extended Kalman filtering framework, enabling joint estimation and physical decoupling of multi-source measurements. Numerical simulation results demonstrate that the proposed method can stably separate global inclination and local deformation components under noisy conditions, while improving the stability of global inclination estimation. Further validation using measured data from a historic building shows that the fusion results effectively suppress high-frequency disturbances in GNSS measurements and allow reliable reconstruction of local component-level inclination responses, indicating good stability and practical applicability. These results demonstrate that the proposed approach provides a physically consistent and robust solution for long-term posture and deformation monitoring of historic buildings. Full article

Epigenetic dysregulation is a central driver of cancer progression, therapeutic resistance, and phenotypic plasticity. Among epigenetic mechanisms, microRNAs (miRNAs) and DNA methyltransferases (DNMTs) engage in reciprocal regulatory interactions that extend beyond transient gene control. Emerging evidence indicates that DNMT–miRNA feedback loops function as epigenetic memory units, stabilizing malignant cell states and enabling durable phenotypic inheritance even after removal of initiating stimuli under conditions shaped by persistent redox and stress signaling cues. In this review, we synthesize mechanistic, computational, and translational studies demonstrating how double-negative DNMT–miRNA feedback architectures generate bistable regulatory circuits that lock cancer cells into epithelial–mesenchymal transition, stem-like, and therapy-resistant states through redox-sensitive regulatory thresholds rather than static epigenetic alterations. This framework provides a unifying explanation for why transient environmental or therapeutic cues can induce long-lasting epigenetic reprogramming and why conventional single-target epigenetic inhibitors often fail to achieve durable clinical responses. Building on this concept, we propose that herbal medicines and plant-derived phytochemicals act as epigenetic reset signals capable of destabilizing pathological epigenetic attractor states encoded by DNMT–miRNA memory circuits by modulating intracellular redox balance and redox-responsive signaling pathways. Owing to their multi-component and systems-level regulatory properties, herbal interventions modulate miRNA expression, DNMT activity, and upstream stress-responsive pathways in a coordinated manner, facilitating transitions from memory-dominated states toward renewed epigenetic plasticity. We further discuss the translational implications of combining miRNA-based therapies with herbal medicine as a strategy for epigenetic reprogramming rather than transient suppression within a redox-guided therapeutic framework. Finally, we address key challenges and clinical feasibility considerations, including delivery, heterogeneity, and safety, and outline future directions for biomarker-guided and systems-informed epigenetic therapies that incorporate redox state as a functional determinant of epigenetic responsiveness. By reframing DNMT–miRNA interactions through the lens of epigenetic memory, this review highlights miRNA–herbal combination strategies as a forward-looking approach for overcoming therapeutic resistance and achieving durable reprogramming in cancer through selective manipulation of redox-sensitive epigenetic signaling circuits. Full article

For decades, immunology has followed a clear paradigm: immunological memory resides only within the adaptive immunity, as a unique property of lymphocytes giving the host the ability to recognize specific antigens and offer long-term protection. However, this raises an important question: how valid is this belief in light of new evidence? The discovery of trained immunity shows that innate immune cells can also develop lasting functional changes. This finding prompts a profound reconsideration of the traditional framework. Trained immunity is a functional reprogramming of the innate immune cells driven by long-term epigenetic and metabolic reprogramming, resulting in enhanced responses upon subsequent exposure to the same pathogen or even to unrelated stimuli. The presence of pattern recognition receptors (PRRs) on innate immune cells already suggested a certain level of specificity in this compartment thanks to the engagement of a PRR by a pathogen-associated molecular pattern (PAMP) inducing memory-like properties in the responding cell. While such partial specificity can enhance protection, it may also amplify aberrant inflammatory circuits, thereby contributing to the initiation or worsening of autoimmune and chronic inflammatory diseases. This dual nature of trained immunity raises important questions for the field: is trained immunity ultimately harmful or beneficial in autoimmunity, and can its mechanisms be harnessed therapeutically rather than pathologically? The present Perspective will address these issues by examining recent findings that reveal the specificity, pathogenic potential, and translational opportunities in given examples of autoimmune diseases (ADs). Full article

Soil salinization is a primary bottleneck for the sustainable development of agriculture in the Yellow River Delta (YRD). Conventional remote sensing monitoring predominantly relies on single-phase instantaneous spectral responses, which are highly vulnerable to transient environmental interferences, such as surface moisture fluctuations. This study proposes a novel predictive framework based on legacy vegetation signals. By integrating multi-temporal Sentinel-2 imagery from the 2024 growing season, we quantified the cumulative physiological feedback of crops from the preceding year and developed a spring soil salinity content (SSC) inversion model for 2025 using the LightGBM algorithm. The results demonstrate that the median compositing technique significantly enhances model robustness against outliers. Furthermore, the optimal time window for capturing these legacy signals for spring salinity monitoring was identified as July to September. Compared with traditional immediate monitoring models, the LightGBM model based on previous-season legacy signals achieved superior predictive accuracy (R² = 0.84), effectively mitigating the impact of stochastic noise. This research validates the critical role of long-term vegetation memory in salinity early warning and provides a robust scientific foundation for the precision management of coastal saline-alkali land. Full article

The primary focus of enhancing the efficiency of operations in the Industry 4.0 setting is Predictive and Preventive Maintenance (PPM). The paper introduces a predictive-maintenance system based on the Unified Namespace (UNS), which involves real-time sensor measurements, photogrammetry, and modelling of a digital twin to improve fault prediction and responsiveness to maintenance. This experiment was conducted over six months in a medium-sized discrete electromechanical production plant equipped with motors, Variable Speed Drives (VSDs), robot/cobots, precision grip systems, pipework systems, Magnemotion/linear motor drives, and a CNC machine. The continuous data, such as high-frequency vibration, temperature, current, and pressure, were monitored and analysed with machine-learning models, including support-vector machines, Gradient Boosting, long-short-term memory, and Random Forest, through which temporal degradation can be predicted. UNS architecture integrated all sensor and imaging data into a vendor-neutral data model through OPC UA to help ensure that all experiments could be integrated consistently and be updated in real time to real digital twins. The suggested system correctly identified mechanical and electrical failures and predicted failures before they really took place. Consequently, machine downtime was reduced by 42.25%, and Mean Time to Repair (MTTR) by 36%, compared to the prior six-month baseline period. These improvements were associated with earlier anomaly detection and digital-twin-supported pre-inspection. Overall, the findings indicate that the integration of UNS with multi-modal sensing and digital-twin technologies may enhance predictive maintenance performance in comparable industrial settings. The framework provides a data-driven, scalable solution to organisations that aim to modernise their maintenance processes, attain greater reliability and better equipment utilisation, as well as enhanced Industry 4.0 preparedness. Full article

As modern software systems continue to grow in scale and structural complexity, log anomaly detection has become an essential component of system monitoring and fault diagnosis. However, existing approaches often struggle to adequately capture sequential dependencies in log data and to remain robust under distributional changes. To mitigate these issues, this paper presents BERT-LogAnom, an unsupervised framework for log anomaly detection that combines contextual representation learning, sequential modeling, and adaptive decision mechanisms. Specifically, a BERT-based encoder is employed to learn global contextual semantics from log sequences, while a gated residual bidirectional Long Short-Term Memory (GR-BiLSTM) network is introduced to model bidirectional temporal dependencies without disrupting the learned contextual information. To characterize normal system behavior from unlabeled logs, two self-supervised objectives—masked log key prediction and volume hypersphere minimization—are jointly optimized during training. Furthermore, a Dynamic Thresholding Prediction Module (DTPM) is incorporated to adjust anomaly decision boundaries in response to short-term statistical fluctuations and longer-term distribution drift. Experiments conducted on three public benchmark datasets (HDFS, BGL, and Thunderbird) show that BERT-LogAnom achieves consistently superior performance compared with representative baseline methods across precision, recall, and F1-score. Additional ablation studies further confirm the contribution of each major component in the proposed framework. Full article

In complex urban traffic scenes, reliable pedestrian trajectory prediction is essential for Automated and Connected Electric Vehicles (ACEVs) and active safety systems. Despite recent progress, many existing approaches still suffer from limited long-term prediction accuracy, redundant temporal features, and high computational cost, which restricts their deployment on vehicles with constrained onboard resources. To address these issues, this paper presents a lightweight trajectory prediction framework named BiTraP-DGF. The model adopts parallel Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) temporal encoders to extract motion information at different time scales, allowing both short-term motion changes and longer-term movement tendencies to be captured from observed trajectories. A conditional variational autoencoder (CVAE) with a bidirectional GRU decoder is further employed to model multimodal uncertainty, where forward prediction is combined with backward goal estimation to guide trajectory generation. In addition, a gated sparse attention mechanism is introduced to suppress irrelevant temporal responses and focus on informative time segments, thereby reducing unnecessary computation. Experimental results on the JAAD dataset show that BiTraP-DGF consistently outperforms the BiTraP-NP baseline. For a prediction horizon of 1.5 s, CADE is reduced by 20.9% and CFDE by 22.8%. These results indicate that the proposed framework achieves a practical balance between prediction accuracy and computational efficiency for autonomous driving applications. Full article

This review develops a materials-to-clinic framework for patient-specific, functionally graded (FG) NiTi shape memory alloy (SMA) rods as a complementary paradigm for scoliosis correction that targets durable alignment with motion preservation. The article synthesizes the thermomechanical basis of NiTi (thermoelastic martensitic transformation, near constant superelastic plateau, and hysteretic damping) while leveraging additive manufacturing (AM) capabilities to spatially program transformation temperatures (e.g., A_f), effective stiffness, and geometric inertia along the rod. Consolidated process–structure–property linkages are provided for the PBF-LB, DED, and BJAM routes, together with contamination and composition-control strategies (mitigation of Ni volatilization; management of O/C uptake; gradient heat treatments) and segment-level quality assurance (DSC mapping, micro-CT, EBSD/indentation, and bench bending/torsion in physiologic media). Building on clinical curve classification, the methodology formalizes a grading mask and target moment vector that drive multi-objective optimization of the segmental A_f, relative density/architecture, and cross-section, followed by route-specific build plans and acceptance tolerances. A phenomenological constitutive description provides the forward map from local design variables to temperature-dependent moment–curvature loops for finite element verification and uncertainty control. Surgical handling and activation policies are codified (cold shaping in martensite and controlled intra-/postoperative warming within tissue-safe bounds), and a translational roadmap is outlined, encompassing prospective calibration of classification-to-design mappings, AM process maps with in situ monitoring, digital twin planning, and long-horizon fatigue/corrosion protocols. The proposed graded structures provide an adaptive transformation temperature gradient and tunable mechanical response, representing an important design direction toward 3D-printed, patient-specific SMA rods for durable, adjustable, and efficient scoliosis correction. Full article

All-optical memristors possess light-sensing and storage capabilities while simultaneously simulating human synaptic functions, demonstrating immense potential in the field of brain-inspired computing for realizing bionic synapses and brain-like intelligence. In this work, we successfully produced ε-Ga₂O₃ films, ε/β-Ga₂O₃ mixed-phase films, and β-Ga₂O₃ films via chemical vapor deposition (CVD). The optical output and optical response characteristics of the thin films are investigated under 254 nm and 365 nm lasers. The CVD-grown ε-Ga₂O₃ is found to process a small amount of defects and insignificant memristive properties and the β-Ga₂O₃ obtained from the annealing of ε-Ga₂O₃ exhibits superior crystal quality but lacks memristive properties, while the ε/β-Ga₂O₃ mixed-phase films grown directly by CVD contain a fair amount of defects and demonstrate persistent resistance retention exceeding 104 s. Based on the excellent memristive properties of ε/β-Ga₂O₃ mixed-phase films, we conducted experiments simulating optical synapses. By adjusting optical pulse parameters (intensity, repetition rate, and duration), we successfully modeled the short-term plasticity (STP) and long-term plasticity (LTP) observed in biological synapses. Experiments confirm that light stimulation can effectively induce synaptic behaviors, such as the progressive conversion of short-term memory (STM) into long-term memory (LTM), and further fully reproduce the neuroplasticity process of “learning-forgetting-relearning.” This study demonstrates a photoconductive synapse memristor based on the wide-bandgap material gallium oxide, exhibiting exceptional air stability with sustained photoconductivity maintained for over a year. This study provides new insights into the practical application feasibility of all-optical artificial synapses based on gallium oxide. Full article