Search Results (12,144)

Ensuring the long-term performance of infrastructure in cold regions necessitates evaluating the frost durability of subgrade materials. This study comprehensively investigates the mechanical behavior of cement-stabilized silty clay, a common material for subgrade improvement, under freeze–thaw (F–T) cycles. A series of unconfined compressive strength (UCS) and resilient modulus (MR) tests were conducted to quantify the effects of cement content (3%, 6%, 9%), initial moisture content (OMC − 2% to OMC + 6%), and the number of F–T cycles (0 to 9). The results demonstrate that increasing the cement content significantly enhances the MR, with the most effective improvement observed up to 6%. Specifically, increasing cement from 3% to 6% boosted MR by 11.62% to 26.69%, while a further increase to 9% yielded a smaller gain of 4.59% to 12.60%, indicating an optimal content. Both UCS and MR peak at the optimum moisture content (OMC) and degrade markedly with F–T cycles, with the first cycle causing over 50% of the total MR loss in most cases. Properties tend to stabilize after approximately six cycles. The stabilized soil exhibits superior performance, with its MR being 2.29–2.43 times that of the original soil at OMC after nine F–T cycles. Furthermore, a logarithmic model (R² = 0.87–0.94) effectively captures the attenuation of MR with F–T cycles, while a strong linear relationship (R² = 0.90–0.96) exists between the initial moisture content and the degradation coefficient. An empirical predictive model for UCS, integrating cement content, moisture content, and F–T cycles, is proposed and shows excellent correlation with experimental data (R² > 0.92). Microstructural analysis reveals that the enhancement mechanism is attributed to hydration, cation exchange, and flocculation, which collectively form a stable cementitious network. The findings and proposed models provide critical quantitative insights for optimizing the design of frost-resistant cement-stabilized subgrades, thereby contributing to the enhanced durability and performance of overlying structures in seasonal freeze–thaw environments. Full article

Automatic sleep staging technology based on wearable photoplethysmography can provide a non-invasive and continuous solution for large-scale sleep health monitoring. This study accordingly developed a novel cross-scale dynamically coupled extended long short-term memory network (SleepXLSTM) to realize automatic sleep staging based on heart rate signals collected by wearable devices. SleepXLSTM models the relationship between heart rate fluctuations and sleep stage labels by correlating physiological features with clinical semantics using a knowledge graph neural network. Furthermore, an excitation–inhibition dual-effect regulator is applied in an improved multiplicative long short-term memory network along with memory mixing in a scalar long short-term memory network to extract and strengthen the key heart rate timing features while filtering out noise produced by motion artifacts, thereby facilitating subsequent high-precision sleep staging. The benefits and functions of this comprehensive heart rate feature extraction were demonstrated using sleep staging prediction and ablation experiments. The proposed model exhibited a superior accuracy of 91.25% and Cohen’s kappa coefficient of 0.876 compared to an extant state-of-the-art neural network sleep staging model with an accuracy of 69.80% and kappa coefficient of 0.040. On the ISRUC-Sleep dataset, the model achieved an accuracy of 87.51% and F1 score of 0.8760. The dynamic coupling strategy employed by SleepXLSTM for automatic sleep staging using the heterogeneous temporal representation of heart rate data can promote the development of smart wearable devices to provide early warning of sleep disorders and realize cost-effective technical support for sleep health management. Full article

Background: Auricular defects resulting from congenital anomalies, trauma, or oncologic resection pose significant functional and psychosocial challenges. When autologous reconstruction is not feasible or not desired, implant-retained auricular prostheses represent a reliable alternative with high patient satisfaction. This study aimed to systematically evaluate the clinical performance of craniofacial implants used for auricular prosthetic rehabilitation, focusing on implant survival, prosthetic outcomes, workflow typologies, and complications. A secondary objective was to illustrate the long-term validity of a minimally invasive navigation technique through a clinical case with 6-year follow-up. Methods: A systematic review was conducted according to PRISMA guidelines. Clinical studies published between 2005 and 2025 reporting outcomes of implant-retained auricular prostheses were searched in PubMed and Scopus databases. Data were extracted on implant type, survival rates, prosthetic performance, workflow, and complications. Risk of bias was assessed using appropriate tools based on each study design. Results: A total of thirty-two studies were included, comprising fifteen case reports, fifteen case series, one cohort study, and one prospective observational study. Implant survival was consistently high across all workflow categories, with failures predominantly associated with irradiated or anatomically compromised bone. Prosthetic outcomes were favorable, showing excellent esthetics, stable retention, and high patient satisfaction irrespective of manufacturing method, although digital and navigation-assisted workflows improved reproducibility, symmetry, and planning precision. Complication rates were low and generally limited to mild peri-abutment inflammation manageable with conservative care. The clinical case confirmed these findings, showing stable osseointegration, healthy soft tissues, and uncompromised prosthetic function at 6-year follow-up. Conclusions: Implant-retained auricular prostheses show predictable long-term success, independent of whether traditional, hybrid, or fully digital workflows are employed. Digital technologies enhance surgical accuracy, minimize morbidity, and streamline prosthetic fabrication, although high-quality comparative studies remain limited. Full article

During rotary tillage operations, the draft force is jointly affected by operating parameters and soil conditions, exhibiting pronounced nonlinearity, time-varying behavior, and historical dependence, which all impose higher requirements on tractor operating parameter matching and traction performance analysis. A draft force prediction method that is based on a long short-term memory (LSTM) neural network jointly optimized by a genetic algorithm (GA) and the bald eagle search (BES) algorithm, termed GABES-LSTM, is proposed to address the limited prediction accuracy and stability of traditional empirical models and single data-driven approaches under complex field conditions. First, on the basis of the mechanical characteristics of rotary tillage operations, a time-series mathematical description of draft force is established, and the prediction problem is formulated as a multi-input single-output nonlinear temporal mapping driven by operating parameters such as travel speed, rotary speed, and tillage depth. Subsequently, an LSTM-based draft force prediction model is constructed, in which GA is employed for global hyperparameter search and BES is integrated for local fine-grained optimization, thereby improving the effectiveness of model parameter optimization. Finally, a dataset is established using measured field rotary tillage data to train and test the proposed model, and comparative analyses are conducted against LSTM, GA-LSTM, and BES-LSTM models. Experimental results indicate that the GABES-LSTM model outperforms the comparison models in terms of mean absolute percentage error, mean relative error, relative analysis error, and coefficient of determination, effectively capturing the dynamic variation characteristics of draft force during rotary tillage operations while maintaining stable prediction performance under repeated experimental conditions. This method provides effective data support for draft force prediction analysis and operating parameter adjustment during rotary tillage operations. Full article

Fuel consumption in heavy-duty off-road machinery depends on a wide range of interacting factors related to the operating environment, the technical characteristics and condition of the machine, and the behaviour, experience and state of the operator. Existing studies typically address only fragments of this relationship, focusing on vehicle parameters, selected environmental factors or individual aspects of driving style. The method proposed in this work provides a general and transferable framework for assessing fuel consumption in any type of machine or vehicle. The Integrated Fuel Consumption Assessment Model (IFCAM) combines environmental, vehicle and human domains into a coherent structured formula that can be used across different operational contexts. The model was developed using continuous short-term measurements and long-term operational data collected during real industrial work. Its universal structure makes it applicable not only to mining equipment, but also to construction machinery and transport vehicles, as well as conventional passenger cars, where it offers a systematic procedure for estimating fuel demand under variable operating conditions. The results demonstrate that integrating multi-domain data improves predictive accuracy and opens new possibilities for analysing operator influence and overall energy efficiency. Full article

In complex maritime environments, the safety of path planning for Unmanned Surface Vehicles (USVs) remains a significant challenge. Existing methods for handling dynamic obstacles often suffer from inadequate predictability and generate non-smooth trajectories. To address these issues, this paper proposes a reliable hybrid path planning approach that integrates a reinforcement learning-enhanced A* algorithm with an improved Dynamic Window Approach (DWA). Specifically, the A* algorithm is augmented by incorporating a dynamic five-neighborhood search mechanism, a reinforcement learning-based adaptive weighting strategy, and a path post-optimization procedure. These enhancements collectively shorten the path length and significantly improve trajectory smoothness. While ensuring that the global path avoids dynamic obstacles smoothly, a Kalman Filter (KF) is integrated into the Long Short-Term Memory (LSTM) network to preprocess historical data. This mechanism suppresses transient outliers and stabilizes the trajectory prediction of dynamic obstacles. Moreover, the evaluation function of the DWA is refined by incorporating the International Regulations for Preventing Collisions at Sea (COLREGs) constraints, enabling compliant navigation behaviors. Simulation results in MATLAB demonstrate that the enhanced A* algorithm better conforms to the kinematic model of the USVs. The improved DWA significantly reduces collision risks, thereby ensuring safer navigation in dynamic marine environments. Full article

Acrylamide is a heat-induced food contaminant that can be formed through the Maillard reaction between reducing sugars and asparagine in carbohydrate-rich foods. It is recognized as having carcinogenic, neurotoxic, and reproductive risks, prompting global regulatory and research attention. This review synthesizes recent advances (2013–2025) in understanding acrylamide’s formation mechanisms, detection methods, mitigation strategies, and health implications. Analytical innovations such as LC–MS/MS have enabled detection at trace levels (≤10 µg/kg), supporting process optimization and compliance monitoring. Effective mitigation strategies combine cooking adjustments, ingredient reformulation, and novel technologies, including vacuum frying, ohmic heating, and predictive modeling, which can achieve up to a 70% reduction in certain food categories. Dietary polyphenols and fibers also hold promise, lowering acrylamide formation and bioavailability through carbonyl trapping and enhanced detoxification. However, significant gaps remain in bioavailability assessment, analysis of metabolic fate (glycidamide conversion), and standardized global monitoring. This review emphasizes that a sustainable reduction in dietary acrylamide requires a multidisciplinary framework integrating mechanistic modeling, green processing, regulatory oversight, and consumer education. Bridging science, industry, and policy is essential to ensure safer food systems and minimize long-term public health risks. Full article

Camellia oleifera, a woody oil crop unique to China, plays a crucial role in alleviating the global pressure of edible oil supply and maintaining ecological security. However, it remains challenging to accurately forecast Camellia oleifera yield in complex landscapes using only remote sensing data. The aim of this study is to develop an interpretable deep learning model, namely Shapley Additive Explanations–guided Attention–long short-term memory (SALSTM), for estimating Camellia oleifera yield by integrating an improved spectral bloom index and environmental parameters. The study area is located in Hengyang City in Hunan Province. Sentinel-2 imagery, meteorological observation from 2019 to 2023, and topographic data were collected. First, an improved spectral bloom index (ISBI) was constructed as a proxy for flowering density, while average temperature, precipitation, accumulated temperature, and wind speed were selected to represent environmental regulation variables. Second, a SALSTM model was designed to capture temporal dynamics from multi-source inputs, in which the LSTM module extracts time-dependent information and an attention mechanism assigns time-step-wise weights. Feature-level importance derived from SHAP analysis was incorporated as a guiding prior to inform attention distribution across variable dimensions, thereby enhancing model transparency. Third, model performance was evaluated using root mean square error (RMSE) and coefficient of determination (R²). The result show that the constructed SALSTM model achieved strong predictive performance in predicting Camellia oleifera yield in Hengyang City (RMSE = 0.5738 t/ha, R² = 0.7943). Feature importance analysis results reveal that ISBI weight > 0.26, followed by average temperature and precipitation from flowering to fruit stages, these features are closely associated with C. oleifera yield. Spatially, high-yield zones were mainly concentrated in the central–southern hilly regions throughout 2019–2023, In contrast, low-yield zones were predominantly distributed in the northern and western mountainous areas. Temporally, yield hotspots exhibited a gradual increasing while low-yield zones showed mild fluctuations. This framework provides an effective and transferable approach for remote sensing-based yield estimation of flowering and fruit-bearing crops in complex landscapes. Full article

The dynamics of open quantum systems play a crucial role in quantum information science. However, obtaining numerically exact solutions for the Lindblad master equation is often computationally expensive. Recently, machine learning techniques have gained considerable attention for simulating open quantum system dynamics. In this paper, we propose a deep learning model based on time series prediction (TSP) to forecast the dynamical evolution of open quantum systems. We employ the positive operator-valued measure (POVM) approach to convert the density matrix of the system into a probability distribution and construct a TSP model based on Transformer neural networks. This model effectively captures the historical evolution patterns of the system and accurately predicts its future behavior. Our results show that the model achieves high-fidelity predictions of the system’s evolution trajectory in both short- and long-term scenarios, and exhibits robust generalization under varying initial states and coupling strengths. Moreover, we successfully predicted the steady-state behavior of the system, further proving the practicality and scalability of the method. Full article

Understanding the economic performance of heritage-rich towns requires a systematic evaluation of how heritage-related components collectively contribute to revenue generation. Existing studies often examine heritage assets, socio-cultural factors, physical infrastructure, and local economic conditions independently, resulting in fragmented insights that limit comprehensive planning for local economic development. This study develops and validates an integrated Cultural Heritage Economy Model that quantifies the influence of heritage resources, social, physical, and economic aspects on revenue generation in heritage contexts. The model is conceptualized through a structured synthesis of theoretical literature and domain-specific indicators, followed by construct operationalization, expert validation, and pilot-level assessment. Using Structural Equation Modelling (SEM-PLS), the study demonstrates strong reliability, convergent validity, discriminant validity, and significant structural relationships. The predictive relevance of the final model is further evaluated through PLSpredict, confirming its suitability for future estimation. The findings confirm that revenue generation is a product of the combined and mutually reinforcing effects of heritage, socio-cultural, physical, and economic dimensions, rather than just by the influence of heritage resources. By offering this novel, empirically grounded, multidimensional framework to estimate heritage-driven economic outcomes, this research establishes a foundational model that can guide evidence-based resource allocation, policy formulation, and long-term sustainable urban development planning. Full article

One of the most significant impacts of climate change is sea-level rise, which is increasingly threatening to the coastal setting, infrastructure, and socioeconomic systems. Since a change at the sea level is spatially non-uniform and highly modulated by local oceanographic and climatic events, local or regional-scale measurements are necessary—especially in semi-enclosed basins. This paper examines the long-term variability of sea levels throughout the Persian Gulf and illustrates a strong spatial variance of the trends over the past and the future. Using three decades of satellite-derived observations, regional sea-level trends were estimated from monthly sea-level anomaly (SLA) data, which were also used to generate future projections to 2100. The analysis shows that the rate of sea-level rise along the UAE–Oman stretch is 3.88 mm year⁻¹ and that of the Strait of Hormuz is 5.23 mm year⁻¹, with a mean of 4.44 mm year⁻¹ in the basin. Statistical forecasts of sea-level change were projected by a statistical forecasting scheme with high predictive ability with the optimal configuration of an average of 0.0391 m, an RMSE of 0.0492 m, and an R² of 0.80 when independent validation was conducted. It is estimated that by 2100, the average rise of the sea level in the Persian Gulf is about 0.30–0.40 m, and the peak rise in sea level is at the Strait of Hormuz. Since these projections are based on statistical extrapolation rather than physics-based climate models, they are interpreted within the uncertainty envelope defined by IPCC AR6 scenarios. This study presents a unique, regionally resolved viewpoint on sea-level rise that is relevant to coastal risk management and adaptation planning in semi-enclosed marine basins by connecting robust statistical performance with physically interpretable regional patterns. Full article

The time-scale mismatch between rapid influent fluctuations and slow biochemical responses hinders the stability of wastewater treatment plants (WWTPs). Existing models often fail to capture shock signals due to noise interference (“signal pollution”). To address this, we propose the HD-MAED-LSTM model, which employs a “decompose-and-conquer” strategy. Targeting the dynamic characteristics of different components, this study innovatively designs heterogeneous attention mechanisms: utilizing Long-term Dependency Attention to capture the global evolution of the trend component, employing Multi-scale Periodic Attention to reinforce the cyclic patterns of the seasonal component, and using Gated Anomaly Attention to keenly capture sudden shocks in the residual component. In a case study, the effectiveness of the proposed model was validated based on one year of operational data from a large-scale industrial WWTP. HD-MAED-LSTM outperformed baseline models such as Transformer and LSTM in the medium-to-long-term (10-h) prediction of COD, TN, and TP, clearly demonstrating the positive role of differentiated modeling. Notably, in the core task of shock load early warning, the model achieved an F1-Score of 0.83 (superior to Transformer’s 0.77 and LSTM’s 0.67), and a Mean Directional Accuracy (MDA) as high as 0.93. Ablation studies confirm that the specialized attention mechanism is the key performance driver, reducing the Mean Absolute Error (MAE) by 56.7%. This framework provides precise support for shifting WWTPs from passive response to proactive control. Full article

Despite widespread adoption, Electronic Medical Record (EMR) systems remain limited in providing intelligent clinical decision support, particularly for early detection of patient deterioration. We present MedROAD V2 (Medical Records Organization, Analysis, and Display), an open-source EMR that integrates AI-driven physiological analysis with comprehensive patient management. The system combines continuous vital sign monitoring and laboratory data using an ensemble of the following four complementary machine learning models: gradient boosting for supervised prediction, isolation forests for anomaly detection, autoencoders for pattern recognition, and Long Short-Term Memory networks for temporal modeling. A novel framework couples these predictions with a large language model (Claude AI) to generate explainable differential diagnoses grounded in medical literature. Validation on the MIMIC-IV database demonstrated excellent 12 h deterioration prediction. MedROAD demonstrates that combining quantitative prediction with natural language explanation can enhance clinical decision support while extending quality care to populations that would otherwise lack access. Full article

Collision avoidance between unmanned aerial vehicles (UAVs) and non-cooperative targets (e.g., off-nominal operations or birds) presents significant challenges in urban air mobility (UAM). This difficulty arises due to the highly dynamic and unpredictable flight intentions of these targets. Traditional collision-avoidance methods primarily focus on cooperative targets or non-cooperative ones with fixed behavior, rendering them ineffective when dealing with highly unpredictable flight patterns. To address this, we introduce a deep reinforcement learning-based collision-avoidance approach leveraging global and local intent prediction. Specifically, we propose a Global and Local Perception Prediction Module (GLPPM) that combines a state-space-based global intent association mechanism with a local feature extraction module, enabling accurate prediction of short- and long-term flight intents. Additionally, we propose a Fusion Sector Flight Control Module (FSFCM) that is trained with a Dueling Double Deep Q-Network (D3QN). The module integrates both predicted future and current intents into the state space and employs a specifically designed reward function, thereby ensuring safe UAV operations. Experimental results demonstrate that the proposed method significantly improves mission success rates in high-density environments, with up to 80 non-cooperative targets per square kilometer. In 1000 flight tests, the mission success rate is 15.2 percentage points higher than that of the baseline D3QN. Furthermore, the approach retains an 88.1% success rate even under extreme target densities of 120 targets per square kilometer. Finally, interpretability analysis via Deep SHAP further verifies the decision-making rationality of the algorithm. Full article

Cadmium (Cd) contamination in agricultural systems poses significant ecotoxicological risks through bioaccumulation in food chains. While lime-based amendments are widely applied for Cd immobilization, mechanistic understanding of bioavailability control pathways remains limited. This study employed a meta-analysis methodology based on 260 datasets from 55 publications to systematically investigate the mechanisms and differences in the effectiveness of calcium hydroxide, calcium carbonate, and calcium oxide in regulating Cd migration in acidic soil–plant systems. The study revealed that lime-based materials synergistically regulated Cd migration through two processes: chemical fixation and ionic competition. Results showed lime application reduced soil available Cd by 33.0%, decreased grain Cd by 44.8%, increased soil pH by 15.6%, and enhanced exchangeable Ca by 35.2%. Chemical fixation was evidenced by Cd transformation from labile to stable forms (residual Cd: +29.5%, acid-soluble Cd: −17.5%). Ionic competition was quantitatively confirmed through strong negative correlation between exchangeable Ca and grain Cd (R² = 0.704). Among the materials, Ca(OH)₂ exhibits the highest efficiency in rapid pedogenic passivation (58.7% reduction in available Cd), whereas CaCO₃ demonstrates superior long-term grain Cd attenuation (65.7% inhibition) via sustained Ca²⁺ release and rhizosphere-regulated dissolution. This study advances mechanistic understanding of Cd bioavailability control and establishes quantitative frameworks for predicting ecotoxicological outcomes, providing scientific basis for optimizing remediation strategies to minimize Cd transfer through agricultural food chains. Full article