Search Results (8,733)

Climate change and human activities profoundly impact forest biodiversity, with effects projected to intensify. The Symplocos genus, a diverse assemblage of flowering plants prevalent in the subtropical and tropical forests of the Yangtze River in China, holds substantial economic and medicinal value. However, the impacts of climate change and human activities on the habitat ranges of Symplocos species in China remain unclear. This study employed an optimized Maxent model to predict potential habitats for four key Symplocos species—Symplocos setchuensis, Symplocos chinensis, Symplocos groffii, and Symplocos sumuntia under current and multiple future climate scenarios (SSP1-2.6 and SSP5-8.5 during the 2070s and 2090s). Moreover, we assessed the relative importance of various predictors, including climatic, topographic, soil, and anthropogenic factors, in shaping their habitat range patterns. Currently, the habitat ranges of the four Symplocos species are mainly concentrated in southern China, exhibiting notable differences in areas of high habitat suitability. Furthermore, the habitat ranges of S. setchuensis, S. chinensis, S. groffii, and S. sumuntia were primarily influenced by the mean temperature of the driest quarter (bio9), the minimum temperature of the coldest month (bio6), the temperature annual range (bio7), and precipitation seasonality (bio15), respectively. Notably, the habitat suitability of S. setchuensis, and S. sumuntia increased at a progressively slower rate with human footprint. Under future climate scenarios, S. groffii and S. sumuntia are projected to expand their ranges significantly northward, while S. chinensis is expected to maintain stable habitat, and S. setchuensis may face considerable contractions. Our results underscore the importance of climate and human activities in shaping the habitat ranges of Symplocos species, revealing distinct adaptive responses among the four species under future climate change. Full article

Underwater Optical Camera Communication (UOCC) has emerged as a promising paradigm for short-range, high-bandwidth, and secure data exchange in autonomous underwater vehicles (AUVs). UOCC performance strongly depends on exposure time and International Standards Organization (ISO) sensitivity—two parameters that govern photon capture, contrast, and bit detection fidelity. However, optical propagation in aquatic environments is highly susceptible to turbidity, scattering, and illumination variability, which severely degrade image clarity and signal-to-noise ratio (SNR). Conventional systems with fixed imaging settings cannot adapt to time-varying conditions, limiting communication reliability. While validating the feasibility of deep learning for exposure prediction, this baseline lacked environmental awareness and generalization to dynamic scenarios. To overcome these limitations, we introduce a Real-to-Sim-to-Deployment framework that couples a physically calibrated emulation platform with a Hybrid CNN-MLP Model (HCMM). By fusing optical images, environmental states, and camera configurations, the HCMM achieves substantially improved parameter prediction accuracy, reducing RMSE to 0.23–0.33. When deployed on embedded hardware, it enables real-time adaptive reconfiguration and delivers up to 8.5 dB SNR gain, surpassing both static-parameter systems and the prior CNN baseline. These results demonstrate that environment-aware multimodal learning, supported by reproducible optical channel emulation, provides a scalable and robust solution for practical UOCC deployment in positioning, inspection, and laser-based underwater communication. Full article

The trajectory-tracking capability of autonomous mining trucks is critical for accomplishing transportation tasks efficiently. However, due to the diverse road surfaces and rugged terrains in open-pit mines, the existing vehicle dynamics models struggle to accurately capture the complex tire–ground interactions. As a result, conventional trajectory-tracking control methods that rely on linear vehicle dynamics models suffer from degraded tracking performance. To this end, this paper proposes a novel trajectory-tracking control framework that integrates model predictive control (MPC) with model-free adaptive control (MFAC). A warm-start strategy is employed to improve the computational efficiency of MPC, while MFAC is utilized to provide real-time compensation for the control deviations generated by MPC during the trajectory-tracking process. To validate the effectiveness of the proposed trajectory-tracking control method, co-simulations were conducted on the CarSim and MATLAB/Simulink platforms under various road conditions and driving scenarios. Simulation results demonstrate that the proposed method can effectively enhance the trajectory-tracking performance of autonomous mining trucks. For instance, under the S-condition with Class E road elevation, the proposed method achieves improvements of approximately 90.83%, 15.05%, and 71.93% in the mean error, maximum error, and root mean square error (RMSE), respectively, compared with the conventional LQR-based trajectory-tracking control method. In addition, the computation time of MPC is only 2 ms, which significantly improves the overall performance of the trajectory-tracking controller. Full article

Facility agriculture cultivation is the main production form of the vegetable industry in the world. As an important vegetable crop, hot peppers are easily threatened by many diseases in a facility microclimate environment. Traditional disease detection methods are time-consuming and allow the disease to proliferate, so timely detection and inhibition of disease development have become the focus of global agricultural practice. This article proposed a generalizable and explainable machine learning model for hot pepper damping-off in intensive seedling production under the condition of ensuring the high accuracy of the model. Through Kalman filter smoothing, SMOTE-ENN unbalanced sample processing, feature selection and other data preprocessing methods, 19 baseline models were developed for prediction in this article. After statistical testing of the results, Bayesian Optimization algorithm was used to perform hyperparameter tuning for the best five models with performance, and the Extreme Random Trees model (ET) most suitable for this research scenario was determined. The F₁-score of this model is 0.9734, and the AUC value is 0.9969 for predicting the severity of hot pepper damping-off, and the explainable analysis is carried out by SHAP (SHapley Additive exPlanations). According to the results, the hierarchical management strategies under different severities are interpreted. Combined with the front-end visualization interface deployed by the model, it is helpful for farmers to know the development trend of the disease in advance and accurately regulate the environmental factors of seedling raising, and this is of great significance for disease prevention and control and to reduce the impact of diseases on hot pepper growth and development. Full article

This paper presents an optimized hybrid deep learning model for power load forecasting—QR-FMD-CNN-BiGRU-Attention—that integrates similar day selection, load decomposition, and deep learning to address the nonlinearity and volatility of power load data. Firstly, the original data are classified using Gaussian Mixture Clustering optimized by ICPO (ICPO-GMM), and similar day samples consistent with the predicted day category are selected. Secondly, the load data are decomposed into multi-scale components (IMFs) using feature mode decomposition optimized by ICPO (ICPO-FMD). Then, with the IMFs as targets, the quantile interval forecasting is trained using the CNN-BiGRU-Attention model optimized by ICPO. Subsequently, the forecasting model is applied to the features of the predicted day to generate interval forecasting results. Finally, the model’s performance is validated through comparative evaluation metrics, sensitivity analysis, and interpretability analysis. The experimental results show that compared with the comparative algorithm presented in this paper, the improved model has improved RMSE by at least 39.84%, MAE by 26.12%, MAPE by 45.28%, PICP and MPIW indicators by at least 3.80% and 2.27%, indicating that the model not only outperforms the comparative model in accuracy, but also exhibits stronger adaptability and robustness in complex load fluctuation scenarios. Full article

An integrated approach for enhancing microparticle separation efficiency in acoustofluidic lab-on-a-chip systems is presented, combining numerical modeling in COMSOL 6.2 Multiphysics^® with reinforcement learning techniques implemented in Python 3.10.14. The proposed method addresses the limitations of traditional parameter tuning, which is time-consuming and computationally intensive. A simulation framework based on LiveLink™ for COMSOL–Python integration enables the automatic generation, execution, and evaluation of particle separation scenarios. Reinforcement learning algorithms, trained on both successful and failed experiments, are employed to optimize control parameters such as flow velocity and acoustic frequency. Experimental data from over 100 numerical simulations were used to train a neural network, which demonstrated the ability to accurately predict and improve sorting efficiency. The results confirm that incorporating failed outcomes into the reward structure significantly improves learning convergence and model accuracy. This work contributes to the development of intelligent microfluidic systems capable of autonomous adaptation and optimization for biomedical and analytical applications, such as label-free separation of microplastics from biological fluids, selective sorting of soot and ash particles for environmental monitoring, and high-precision manipulation of cells or extracellular vesicles for diagnostic assays. Full article

Student engagement analysis is closely linked with learning outcomes, and its precise identification paves the way for targeted instruction and personalized learning. Current student engagement methods, reliant on either head pose estimation with facial landmarks or eye-trackers, are hardly generalized to authentic classroom teaching environments with high occlusion and non-intrusive requirements. Based on empirical observations that student body orientation and head pose exhibit a high degree of consistency in classroom settings, we propose a novel student engagement analysis algorithm incorporating human body orientation estimation. To better suit classroom settings, we develop a one-stage and end-to-end trainable framework for multi-person body orientation estimation, named JointBDOE. The proposed JointBDOE integrates human bounding box prediction and body orientation into a unified embedding space, enabling the simultaneous and precise estimation of human positions and orientations in multi-person scenarios. Extensive experimental results using the MEBOW dataset demonstrate the superior performance of JointBDOE over the state-of-the-art methods, with an MAE reduced to 10.63° and orientation accuracy exceeding 91% at 22.5°. With the more challenging reconstructed MEBOW dataset, JointBDOE maintains strong robustness with an MAE of 16.07° and an orientation accuracy of 88.3% at 30°. Further analysis of classroom teaching videos validates the reliability and practical value of body orientation as a robust metric for engagement assessment. This research showcases the potential of artificial intelligence in intelligent classroom analysis and provides an extensible solution for body orientation estimation technology in related fields, advancing the practical application of intelligent educational tools. Full article

Background: Exposure therapy is an established intervention for treating specific phobias. This study evaluates a Virtual Exposure Therapist (VET), a virtual reality (VR)-based system enhanced with artificial intelligence (AI), designed to reduce spider fear symptoms. Methods: The VET system delivers three progressive exposure scenarios involving interactive 3D spider models and features an adaptive relaxation mode triggered when physiological stress exceeds preset thresholds. AI integration is rule-based, enabling real-time adjustments based on session duration, head movement (degrees/sec), and average heart rate (bpm). Fifty-five participants (aged 18–35) with self-reported moderate to high fear of spiders completed seven sessions using the VET system. Participants were not clinically diagnosed, which limits the generalizability of findings to clinical populations. Ethical approval was obtained, and informed consent was secured. Behavioral responses were analyzed using AR(p)–GARCH (1,1) models to account for intra-session volatility in anxiety-related indicators. The presence of ARCH effects was confirmed through the Lagrange Multiplier test, validating the model choice. Results: Results demonstrated a 21.4% reduction in completion time and a 16.7% decrease in average heart rate across sessions. Head movement variability declined, indicating increased user composure. These changes suggest a trend toward reduced phobic response over repeated exposures. Conclusions: While findings support the potential of AI-assisted VR exposure therapy, they remain preliminary due to the non-clinical sample and absence of a control group. Findings indicate expected symptom improvement across sessions; additionally, within-session volatility metrics (persistence/half-life) provided incremental predictive information about later change beyond session means, with results replicated using simple volatility proxies. These process measures are offered as complements to standard analyses, not replacements. Full article

This study focuses on the impact of wastewater discharges from the Besòs treatment plant on the coastal water quality of Barcelona, particularly under adverse weather conditions. A simplified mathematical model was developed to predict, in real time, the concentration of bacterial indicators (Enterococci and E. coli) along nearby beaches. This model aims to quickly detect contamination events and trigger alerts to evacuate swimming areas before water quality tests are completed. The simulator uses meteorological data—such as wind direction and speed, rainfall intensity, and solar irradiance, among others—to anticipate pollution levels without requiring immediate water sampling. The model was tested against real-world scenarios and validated with historical meteorological and bacteriological data collected over six years. The results show that bacterial pollution occurs mainly during intense rainfall events combined with specific wind conditions, particularly when winds blow from the southeast (SE) or east–southeast (ESE) at moderate to high speeds. These wind patterns carry under-treated wastewater toward the coast. Conversely, winds from the north or northwest tend to disperse the contaminants offshore, posing little to no risk to swimmers. This study confirms that pollution events are relatively rare—about two per year—but pose significant health risks when they do occur. The simulator proved reliable, accurately predicting contamination episodes without producing false alarms. Minor variables such as water temperature or suspended solids showed limited influence, with wind and sunlight being the most critical factors. The model’s rapid response capability allows public authorities to take swift action, significantly reducing the risk to beachgoers. This system enhances current water quality monitoring by offering a predictive, cost-effective, and preventive tool for beach management in urban coastal environments. Full article

Virtual commands serve as the essential framework for establishing interaction between the virtual pilot and the MCP in autopilot scenarios. Conventional proportional-integral-derivative (PID) controllers are insufficient to ensure accurate flight trajectories due to system hysteresis. To overcome this limitation, a quaternary correlation prediction compensation PID (QCPC-PID) approach is introduced for computing virtual heading commands in autopilot tasks. The method integrates multi-feature statistics, entropy-based predictive compensation, and quaternary correlations. First, flight trajectory error statistics are dynamically calculated using signed error distances to assess deviation levels. Second, a predictive structure based on information entropy is applied to enhance PID compensation. Third, quaternary correlation dependence is established to generate virtual heading commands. The findings confirm the effectiveness of the method in improving flight convergence. The incorporation of predictive structures and quaternary correlations is critical for achieving predictive compensation during PID tuning, thereby reducing flight trajectory deviations. The quaternary correlation prediction compensation method ensures superior performance of PID control in modeling heading adjustment behavior under autopilot conditions. Full article

As the world is shifting toward cleaner energy sources, accurate forecasting of solar radiation is critical for optimizing the performance and integration of solar energy systems. In this study, we explore eight machine learning models, namely, Random Forest Regressor, Linear Regression Model, Artificial Neural Network, k-Nearest Neighbors, Support Vector Regression, Gradient Boosting Regressor, Gaussian Process Regression, and Deep Learning, as to their use in forecasting direct solar radiation across six climatically diverse regions in the Kingdom of Saudi Arabia. The models were evaluated using eight statistical metrics along with time-series and absolute error analyses. A key contribution of this work is the introduction of Trigonometric Cyclical Encoding, which has significantly improved temporal representation learning. Comparative SHAP-based feature-importance analysis revealed that Trigonometric Cyclical Encoding enhanced the explanatory power of temporal features by 49.26% for monthly cycles and 53.30% for daily cycles. The findings show that Deep Learning achieved the lowest root mean square error, as well as the highest coefficient of determination, while Artificial Neural Network demonstrated consistently high accuracy across the sites. Support Vector Regression performed optimally but was less reliable in some regions. Error and time-series analyses reveal that Artificial Neural Network and Deep Learning maintained stable prediction accuracy throughout high solar radiation seasons, whereas Linear Regression, Random Forest Regressor, and k-Nearest Neighbors showed greater fluctuations. The proposed Trigonometric Cyclical Encoding technique further enhanced model performance by maintaining the overall fitness of the models, which ranged between 81.79% and 94.36% in all scenarios. This paper supports the effective planning of solar energy and integration in challenging climatic conditions. Full article

The global pursuit of sustainable development amplifies renewable energy’s strategic importance, positioning wind power as a vital modern grid component. Accurate wind forecasting is essential to counter inherent volatility, enabling robust grid operations, security protocols, and optimization strategies. Such predictive precision directly governs wind energy systems’ stability and sustainability. This research introduces a novel spatio-temporal hybrid model integrating convolutional neural networks (CNN), bidirectional long short-term memory (BiLSTM), and graph convolutional networks (GCN) to extract temporal patterns and meteorological dynamics (wind speed, direction, temperature) across 134 wind turbines. Building upon conventional methods, our architecture captures turbine spatio-temporal correlations while assimilating multivariate meteorological characteristics. Addressing data integrity compromises from equipment failures and extreme weather-which undermine data-driven models-we implement Wasserstein GAN (WGAN) for generative missing-value interpolation. Validation across severe data loss scenarios (30–90% missing values) demonstrates the model’s enhanced predictive capacity. Rigorous benchmarking confirms significant accuracy improvements and reduced forecasting errors. Full article

It is widely recognized that benthic sediment plumes generated by deep-sea mining may pose significant potential risks to ecosystems, yet their dispersion behavior remains difficult to predict with accuracy. In this study, we combined laboratory experiments with three-dimensional numerical simulations using the Environmental Fluid Dynamics Code (EFDC) to investigate the dispersion of sediment plumes composed of particles of different sizes. Laboratory experiments were conducted with deep-sea clay samples from the western Pacific under varying conditions for plume dispersion. Experimental data were used to capture horizontal diffusion and vertical entrainment through a Gaussian plume model, and the results served for parameter calibration in large-scale plume simulations. The results show that ambient current velocity and discharge height are the primary factors regulating plume dispersion distance, particularly for fine particles, while discharge rate and sediment concentration mainly control plume duration and the extent of dispersion in the horizontal direction. Although the duration of a single-source release is short, continuous mining activities may sustain broad dispersion and result in thicker sediment deposits, thereby intensifying ecological risks. This study provides the first comprehensive numerical assessment of deep-sea mining plumes across a range of particle sizes with clay from the western Pacific. The findings establish a mechanistic framework for predicting plume behavior under different operational scenarios and contribute to defining threshold values for discharge-induced plumes based on scientific evidence. By integrating experimental, theoretical, and numerical approaches, this work offers quantitative thresholds that can inform environmentally responsible strategies for deep-sea resource exploitation. Full article

The integration of renewable energy systems and electrified transportation requires advanced energy storage solutions capable of providing both high energy density and fast dynamic response. Hybrid energy storage systems offer a promising approach by combining complementary battery chemistries, exploiting their respective strengths while mitigating individual limitations. This study presents the design, modeling, and optimization of a hybrid energy storage system composed of two high-energy lithium nickel manganese cobalt batteries and one high-power lithium titanate oxide battery, interconnected through a triple dual-active multi-port converter. A nonlinear model predictive control strategy was employed to optimally distribute battery currents while respecting constraints such as state of charge limits, current bounds, and converter efficiency. Equivalent circuit models were used for real-time state of charge estimation, and converter losses were explicitly included in the optimization. The main contributions of this work are threefold: (i) verification of the model predictive control strategy in diverse applications, including residential renewable energy systems with photovoltaic generation and electric vehicles following the World Harmonized Light-duty Vehicle Test Procedure driving cycle; (ii) explicit inclusion of the power converter model in the system dynamics, enabling realistic coordination between batteries and power electronics; and (iii) incorporation of converter efficiency into the cost function, allowing for simultaneous optimization of energy losses, battery stress, and operational constraints. Simulation results demonstrate that the proposed model predictive control strategy effectively balances power demand, extends system lifetime by prioritizing lithium titanate oxide battery during transient peaks, and preserves lithium nickel manganese cobalt cell health through smoother operation. Overall, the results confirm that the proposed hybrid energy storage system architecture and control strategy enables flexible, reliable, and efficient operation across diverse real-world scenarios, providing a pathway toward more sustainable and durable energy storage solutions. Full article

Block-based hybrid video coders typically use inter-prediction and bidirectionally coded (B) frames to improve compression efficiency. For this purpose, they employ look-ahead buffers, perform out-of-sequence frame coding, and implement similarity search-based general-purpose algorithms for motion estimation. While effective, these methods increase computational complexity and may not suit delay-sensitive practical applications such as real-time drone video transmission. If future motion can be predicted from external metadata, encoding can be optimized with lower complexity. In this study, a mathematical model for predicting motion vectors in drone video using only flight parameters is proposed. A remote-controlled drone with a fixed downward-facing camera recorded 4K video at 50 fps during autonomous flights over a marked terrain. Four flight parameters were varied independently, altitude, horizontal speed, vertical speed, and rotational rate. OpenCV was used to detect ground markers and compute motion vectors for temporal distances of 5 and 25 frames. Polynomial surface fitting was applied to derive motion models for translational, rotational, and elevational motion, which were later combined. The model was validated using complex motion scenarios (e.g., circular, ramp, helix), yielding worst-case prediction errors of approximately −1 ± 3 and −6 ± 14 pixels at 5 and 25 frames, respectively. The results suggest that flight-aware modeling enables accurate and low-complexity motion vector prediction for drone video coding. Full article