Search Results (145)

Quick visual balance perception in layouts is essential for a positive user experience. However, existing computational models often struggle to accurately capture this key aesthetic aspect, particularly in interfaces with asymmetric elements. This paper introduces Visual Moment Equilibrium (VME), a new cognitive model that redefines visual balance as a unified perceptual force field, similar to moment equilibrium in physical systems. Based on principles from Gestalt psychology, spatial cognition, and psychophysics, we incorporate three main innovations: (1) a Measured Balance index enhanced with psychophysical transformations to enable sensitive quantification of visual imbalance; (2) a nine-grid visual weighting system combined with Manhattan distance to reflect human attentional distribution and non-Euclidean spatial reasoning; and (3) a Shape Sparsity Ratio with a piecewise compensation function that formally operationalizes the Gestalt principle of closure, especially for irregular visual elements. Validation against human perceptual benchmarks from the Analytic Hierarchy Process shows that the VME model has a strong correlation with expert judgments regarding regular interfaces (Pearson’s r = 0.942, accounting for 88.8% of the variance), outperforming the widely used model (33.9%). VME also maintains high predictive accuracy for irregular interfaces (r = 0.890), emphasizing its wide applicability across various design configurations. Full article

Background: During an apnea, oxygen depletion occurs at all tissue levels, so apnea duration is influenced by the mammalian dive reflex, which includes a bradycardia resulting in reduced cardiac oxygen consumption. This study aimed to examine the relationships between heart rate (HR), peripheral estimation of O₂ (SpO₂), deltoid and respiratory muscle oxygenation (SmO₂), and apnea duration. Methods: The study included 10 breath-hold divers (BHD), 39 ± 10 years of age, with body height of 184.3 ± 3.5 cm, body mass of 84.0 ± 9.2 kg, and 16.2 ± 9.7 years of apnea experience. The BHD performed three preparatory apneas followed by three maximal apneas with 5 min of supine rest between each apnea. During all apneas (duration, 115–323 s; involuntary breathing movements (IBMs), 7–35), SmO₂ (measured via NIRS on intercostals (respiratory) and deltoid (locomotor) muscles), heart rate, and SpO₂ (measured via forehead sensor) were obtained. Results: The smallest disagreement in oxygen levels was between intercostal SmO₂ and SpO₂ during the easy-going phase (no IBMs), whereas deltoid desaturation values were more variable. During the struggle phase, Intercostal SmO₂, moderately, and Deltoid SmO₂, strongly, differed from SpO₂. Correlations between apnea duration and O₂ saturation showed that only Intercostal SmO₂ (r = −0.71; p = 0.03) was significantly related to apnea duration. There was also a significant correlation between HR and SpO₂ in the struggle phase (r = −0.58; p = 0.05). Conclusions: These findings suggest that during the struggle phase, SpO₂ and SmO₂ are not highly connected and that local and systemic oxygen levels in the blood are depleted at different rates. Furthermore, the HR response during the struggle phase affected only SpO₂, which indicates that lowering the heart rate may help prevent more rapid deoxygenation. Lastly, the intercostal trend of deoxygenation could be interpreted as respiratory muscle work, suggesting that the increased work of respiratory muscles may prolong apnea duration. Full article

Sea surface wind speed is a crucial parameter for studying climate change and ocean dynamics. Accurate, real-time measurements are essential for meteorological and oceanographic observations. Global Navigation Satellite System Reflectometry (GNSS-R) is a key technology for sea surface wind speed retrieval. Existing wind speed retrieval models employ two primary approaches: unified modeling across the entire wind speed range and independent modeling for partitioned wind speed intervals. The former cannot effectively address physical property variations across wind speed ranges. The latter, while mitigating this issue, relies on empirical thresholds for interval partitioning that ignore actual data distribution and struggles to assign new samples to appropriate intervals during prediction. To address these limitations, this study employs the Gradient-Boosted Adaptive Multi-Objective Simulated Annealing (GAMSA) algorithm to construct a multi-objective optimization function and perform data-driven wind speed interval partitioning. Specialized XGBoost sub-models are then constructed for each partitioned interval, and their predictions are integrated through a stacking ensemble learning architecture. The experiments utilize a Cyclone Global Navigation Satellite System (CYGNSS) and ERA5 reanalysis data. The experimental results show that the proposed method reduces the root mean square error (RMSE) from 1.77 m/s to 1.43 m/s and increases the coefficient of determination (R²) from 0.6293 to 0.7770 compared with a global XGBoost model. It also exhibits enhanced accuracy under high wind speeds (>16 m/s) and, when independently validated with buoy data, achieves an RMSE of 1.52 m/s and R² of 0.79. The proposed method improves retrieval accuracy across both overall and individual wind speed intervals, avoids the sample isolation problem inherent in traditional empirical partitioning methods, and resolves the issue of assigning new samples to appropriate sub-models during application. Full article

Improving financial time series forecasting presents challenges because models often struggle to identify diverse fault patterns in unseen data. This issue is critical in fintech, where accurate and reliable forecasting of financial data is essential for effective risk management and informed investment strategies. This work addresses these challenges by initializing the weights and biases of two proposed models, Gated Recurrent Units (GRUs) and the Echo State Network (ESN), with different chaotic sequences to enhance prediction accuracy and capabilities. We compare reservoir computing (RC) and recurrent neural network (RNN) models with and without the integration of chaotic systems, utilizing standard initialization. The models are validated on six different datasets, including the 500 largest publicly traded companies in the US (S&P500), the Irish Stock Exchange Quotient (ISEQ) dataset, the XAU and USD forex pair (XAU/USD), the USD and JPY forex pair with respect to the currency exchange rate (USD/JPY), Chinese daily stock prices, and the top 100 index of UK companies (FTSE 100). The ESN model, combined with the Lorenz system, achieves the lowest error among other models, reinforcing the effectiveness of chaos-trained models for prediction. The proposed ESN model, accelerated by the Kintex-Ultrascale KCU105 FPGA board, achieves a maximum frequency of $83.5$ MHz and a power consumption of $0.677$ W. The results of the hardware simulation align with MATLAB R2025b fixed-point analysis. Full article

In modern industrial automation, optimizing the performance of Programmable Logic Controller (PLC)-based PID controllers is critical for ensuring precise process control. This study presents a novel methodology for the dynamic tuning of built-in Proportional-Integral-Derivative (PID) controllers in PLCs using a hybrid algorithm that combines Particle Swarm Optimization (PSO) and Multiple-Adaptive Neuro-Fuzzy Inference System (MANFIS). Classical PID tuning methods, such as Ziegler–Nichols and Cohen–Coon, have traditionally been employed in industrial control systems. However, these methods often struggle to address the complexities of nonlinear, time-varying, or highly dynamic processes, resulting in suboptimal performance and limited adaptability. To overcome these challenges, the proposed PSO-MANFIS hybrid algorithm leverages the global search capabilities of PSO and the adaptive learning abilities of MANFIS to optimize PID parameters in real-time dynamically. Integrating MATLAB (R2021a) with industrial automation systems via an OPC (OLE for Process Control) server utilizes advanced optimization algorithms within MATLAB to obtain the best possible parameters for the industrial PID controller, enhancing control precision and optimizing production efficiency. This MATLAB-PLC interface facilitates seamless communication, enabling real-time monitoring, data analysis, and the implementation of sophisticated computational tools in industrial environments. Experimental results demonstrate superior performance, with reductions in rise time from 93.01 s to 70.98 s, settling time from 165.28 s to 128.84 s, and overshoot eliminated from 0.0012% to 0% of the controller response compared to conventional tuning. Furthermore, the proposed approach achieves a reduction in Root Mean Square Error (RMSE) by approximately 56% to 74% when compared with the baseline performance. By integrating MATLAB’s computational capabilities with PLC-based industrial automation, this study provides a practical and innovative solution for modern industries, offering enhanced adaptability, precision, and reliability in dynamic control applications, ultimately leading to optimized production outcomes. Full article

Precise pore pressure prediction is highly essential for safe and effective drilling; however, the nonlinear and heterogeneous nature of the subsurface strata makes it extremely challenging. Conventional physics-based methods are not capable of handling this nonlinearity and variation. Recently, machine learning (ML) methods have been deployed by researchers to enhance prediction performance. These methods are often highly domain-specific and produce good results for the data they are trained for but struggle to generalize to unseen data. This study introduces a Hybrid Meta-Ensemble (HME), a meta model framework, as a novel data mining approach that applies ML methods and ensemble learning on well log data for pore pressure prediction. This proposed study first trains five baseline models including Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Deep Feedforward Neural Network (DFNN), Random Forest (RF), and Extreme Gradient Boost (XGBoost) to capture sequential and nonlinear relationships for pore pressure prediction. The stacked predictions are further improved through a meta learner that adaptively reweighs them according to subsurface heterogeneity, effectively strengthening the ability of ensembles to generalize across diverse geological settings. The experimentation is performed on well log data from four wells located in the Potwar Basin which is one of Pakistan’s principal oil- and gas-producing regions. The proposed Hybrid Meta-Ensemble (HME) has achieved an R² value of 0.93, outperforming the individual base models. Using the HME approach, the model effectively captures rock heterogeneity by learning optimal nonlinear interactions among the base models, leading to more accurate pressure predictions. Results show that integrating deep learning with robust meta learning substantially improves the accuracy of pore pressure prediction. Full article

Predicting structural loads on offshore wind turbine support structures under varying environmental conditions is a complex yet critical task, particularly for large-capacity turbines such as the 15 MW offshore wind turbine. Current prediction methods often struggle with accuracy, especially for torsional moments, due to the non-linear interactions between wind parameters and structural responses. To address this challenge, present study develops a generalized load estimation framework using multivariable polynomial regression, leveraging 10,000 numerical simulations. The framework accounts for four critical variables: Extreme Wind Speed (30 to 40 m/s), Turbulence Intensity (12% to 16%), Flow Inclination Angle (−8° to +8°), and Shear Exponent (0.1 to 0.3). The proposed equations predict six key moment components at the tower base, including the bending moments about the y-axis, torsional moments about the z-axis, bending moments in the x-y, x-z, and y-z planes, and the resultant combined moment. The framework was validated using 2000 testing data points, achieving high accuracy with R² values exceeding 0.92 for all moments. Specifically, the prediction accuracy was highest for the resultant combined moment and y-z bending moment, with average absolute errors of 5.76% and 5.97%, respectively, while x-z bending moment had a slightly higher error of 13.91%, highlighting that torsional moments are inherently more challenging to predict. Heatmap and scatter plot analyses confirmed that the predicted moments align closely with the simulated values, particularly for the torsional moment about the z-axis and y-z bending moment, with standard deviation values as low as 4.85. By optimizing polynomial degrees between 2 and 4, the framework effectively balances prediction accuracy and computational efficiency. This approach provides engineers and scientists with a reliable tool for load estimation, facilitating improved design and analysis of offshore wind turbine support structures. Full article

Flight delays during extreme weather events exhibit spatio-temporal propagation and cascading effects, posing serious challenges to the resilience of aviation systems. Existing prediction approaches often neglect dynamic dependencies across flight chains and struggle to model sparse extreme events. This study develops a data-driven framework that explicitly models delay propagation paths, incorporates historical scenario retrieval to capture rare disruption patterns, and integrates meteorological, airport operational, and flight-specific information through multi-source fusion. Using U.S. flight operations and weather records, the framework demonstrates clear advantages over established baselines in extreme-delay scenarios, achieving a MAE of 3.23 min, an RMSE of 6.25 min, and an R² of 0.92—improving by 8.8%, 26.0%, and 5.75% compared to the best benchmark. Ablation studies confirm the contribution of the propagation modeling, historical retrieval, and multi-source integration modules, while cross-airport evaluations reveal consistent accuracy at both major hubs (e.g., Atlanta, Chicago O’Hare) and regional airports (e.g., Kona, Anchorage). These findings demonstrate that the proposed framework enables reliable forecasting of delay propagation under complex weather conditions, providing valuable support for proactive departure management and enhancing the resilience of aviation operations. Full article

Hybrid PV-TEG systems can harvest both solar electrical and thermoelectric power, but their operating point drifts with irradiance, temperature gradients, partial shading, and load changes—often yielding multi-peak P-V characteristics. Conventional MPPT (e.g., P&O) and fixed-structure integer-order PID struggle to remain fast, stable, and globally optimal in these conditions. To address fast, robust tracking in these conditions, we propose an adaptive fractional-order PID (FOPID) MPPT whose parameters (K_p, K_i, K_d, λ, μ) are auto-tuned by the red-billed blue magpie optimizer (RBBMO). RBBMO is used offline to set the controller’s search ranges and weighting; the adaptive law then refines the gains online from the measured ΔV, ΔI slope error to maximize the hybrid PV-TEG output. The method is validated in MATLAB R2024b/Simulink 2024b, on a boost-converter–interfaced PV-TEG using five testbeds: (i) start-up/search, (ii) stepwise irradiance, (iii) partial shading with multiple local peaks, (iv) load steps, and (v) field-measured irradiance/temperature from Shanxi Province for spring/summer/autumn/winter. Compared with AOS, PSO, MFO, SSA, GHO, RSA, AOA, and P&O, the proposed tracker is consistently the fastest and most energy-efficient: 0.06 s to reach 95% MPP and 0.12 s settling at start-up with 1950 W·s harvested (vs. 1910 W·s AOS, 1880 W·s PSO, 200 W·s P&O). Under stepwise irradiance, it delivers 0.95–0.98 kJ at t = 1 s and under partial shading, 1.95–2.00 kJ, both with ±1% steady ripple. Daily field energies reach 0.88 × 10⁻³, 2.95 × 10⁻³, 2.90 × 10⁻³, 1.55 × 10⁻³ kWh in spring–winter, outperforming the best baselines by 3–10% and P&O by 20–30%. Robustness tests show only 2.74% power derating across 0–40 °C and low variability (Δv^max typically ≤ 1–1.5%), confirming rapid, low-ripple tracking with superior energy yield. Finally, the RBBMO-tuned adaptive FOPID offers a superior efficiency–stability trade-off and robust GMPP tracking across all five cases, with modest computational overhead. Full article

Accurate prediction of fracturing pressure is critical for operational safety and fracturing efficiency in unconventional reservoirs. Traditional physics-based models and existing deep learning architectures often struggle to capture the intense fluctuations and complex temporal dependencies observed in actual fracturing operations. To address these challenges, this paper proposes a multi-source data-driven fracturing pressure prediction model, a model integrating TCN-BiLSTM-Attention Mechanism (Temporal Convolutional Network, Bidirectional Long Short-Term Memory, Attention Mechanism), and introduces a feature selection mechanism for fracture pressure prediction. This model employs TCN to extract multi-scale local fluctuation features, BiLSTM to capture long-term dependencies, and Attention to adaptively adjust feature weights. A two-stage feature selection strategy combining correlation analysis and ablation experiments effectively eliminates redundant features and enhances model robustness. Field data from the Sichuan Basin were used for model validation. Results demonstrate that our method significantly outperforms baseline models (LSTM, BiLSTM, and TCN-BiLSTM) in mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R²), particularly under high-fluctuation conditions. When integrated with slope reversal analysis, it achieves sand blockage warnings up to 41 s in advance, offering substantial potential for real-time decision support in fracturing operations. Full article

Smart cities offer new opportunities for urban governance and sustainable development. However, at the current stage, the construction and development of smart cities generally exhibit a technology-driven tendency, neglecting real resident demand, which contradicts the “human-centric” principle. Traditional top-down methods of demand collection struggle to capture the dynamics and heterogeneity of public demand. At the same time, government service platforms, as one dimension of smart city construction, have accumulated massive amounts of user-generated data, providing new solutions for this challenge. This paper aims to construct a big data-driven analytical framework for dynamically identifying and accurately forecasting core resident demand. The study uses Xi’an City, Shaanxi Province, China, as a case study, utilising user messages from People.cn spanning 2011 to 2023. These messages cover various domains, including urban construction, healthcare, education, and transportation, as the data source. The People.cn message board is China’s most significant nationwide online political platform. Its institutionalised feedback mechanism ensures data content focuses on highly representative specific grievances, rather than the broad emotional expressions on social media. The study employs user messages from People.cn from 2011 to 2023 as its data source, encompassing urban construction, healthcare, education, and transportation. First, a large language model (LLM) was used to preprocess and clean the raw data. Subsequently, the BERTopic model was applied to identify ten core demand themes and construct their monthly time series, thereby overcoming the limitations of traditional methods in short-text semantic recognition. Finally, by integrating variational mode decomposition (VMD) with support vector machines (SVMs), a hybrid demand forecasting model was established to mitigate the risk of overfitting in deep learning when forecasting small-sample time series. The empirical results show that the proposed LLM-BERTopic-VMD-SVM framework exhibits excellent performance, with the goodness-of-fit (R2) on various demand themes ranging from 0.93 to 0.96. This study proposes an effective analytical framework for identifying and forecasting resident demand. It provides a decision-support tool for city managers to achieve proactive and fine-grained governance, thereby offering a viable empirical pathway to promote the transformation of smart cities from technology-centric to human-centric. Full article

Early warning systems on edge devices such as satellites and unmanned aerial vehicles (UAVs) are essential for effective forest fire prevention. Edge Intelligence (EI) enables deploying deep learning models on edge devices; however, traditional convolutional neural networks (CNNs)/Transformer-based models struggle to balance local-global context integration and computational efficiency in such constrained environments. To address these challenges, this paper proposes HybriDet, a novel hybrid-architecture neural network for wildfire detection. This architecture integrates the strengths of both CNNs and Transformers to effectively capture both local and global contextual information. Furthermore, we introduce efficient attention mechanisms—Windowed Attention and Coordinate-Spatial (CS) Attention—to simultaneously enhance channel-wise and spatial-wise features in high-resolution imagery, enabling long-range dependency modeling and discriminative feature extraction. Additionally, to optimize deployment efficiency, we also apply model pruning techniques to improve generalization performance and inference speed. Extensive experimental evaluations demonstrate that HybriDet achieves superior feature extraction capabilities while maintaining high computational efficiency. The optimized lightweight variant of HybriDet has a compact model size of merely 6.45 M parameters, facilitating seamless deployment on resource-constrained edge devices. Comparative evaluations on the FASDD-UAV, FASDD-RS, and VOC datasets demonstrate that HybriDet achieves superior performance over state-of-the-art models, particularly in processing highly heterogeneous remote sensing (RS) imagery. When benchmarked against YOLOv8, HybriDet demonstrates a 6.4% enhancement in mAP50 on the FASDD-RS dataset while maintaining comparable computational complexity. Meanwhile, on the VOC dataset and the FASDD-UAV dataset, our model improved by 3.6% and 0.2%, respectively, compared to the baseline model YOLOv8. These advancements highlight HybriDet’s theoretical significance as a novel hybrid EI framework for wildfire detection, with practical implications for disaster emergency response, socioeconomic security, and ecological conservation. Full article

In this study, we utilize Gaofen-2 satellite remote sensing images to optimize and enhance the extraction of feature information from rural compounds, addressing key challenges in high-resolution remote sensing analysis: traditional methods struggle to effectively capture long-distance spatial dependencies for scattered rural compounds. To this end, we implement the RS³Mamba+ deep learning model, which introduces the Mamba state space model (SSM) into its auxiliary branching—leveraging Mamba’s sequence modeling advantage to efficiently capture long-range spatial correlations of rural compounds, a critical capability for analyzing sparse rural buildings. This Mamba-assisted branch, combined with multi-directional selective scanning (SS2D) and the enhanced STEM network framework (replacing single 7 × 7 convolution with two-stage 3 × 3 convolutions to reduce information loss), works synergistically with a ResNet-based main branch for local feature extraction. We further introduce a multiscale attention feature fusion mechanism that optimizes feature extraction and fusion, enhances edge contour extraction accuracy in courtyards, and improves the recognition and differentiation of courtyards from regions with complex textures. The feature information of courtyard utilization status is finally extracted using empirical methods. A typical rural area in Weifang City, Shandong Province, is selected as the experimental sample area. Results show that the extraction accuracy reaches an average intersection over union (mIoU) of 79.64% and a Kappa coefficient of 0.7889, improving the F1 score by at least 8.12% and mIoU by 4.83% compared with models such as DeepLabv3+ and Transformer. The algorithm’s efficacy in mitigating false alarms triggered by shadows and intricate textures is particularly salient, underscoring its potential as a potent instrument for the extraction of rural vacancy rates. Full article

Snow accumulation on photovoltaic (PV) panels can cause significant energy losses in cold climates. While drone-based monitoring offers a scalable solution, real-world challenges like varying illumination can hinder accurate snow detection. We previously developed a YOLO-based drone system for snow coverage detection using a Fixed Thresholding segmentation method to discriminate snow from the solar panel; however, it struggled in challenging lighting conditions. This work addresses those limitations by presenting a reliable drone-based system to accurately estimate the Snow Coverage Percentage (SCP) over PV panels. The system combines a lightweight YOLOv11n-seg deep learning model for panel detection with an adaptive image processing algorithm for snow segmentation. We benchmarked several segmentation models, including MASK R-CNN and the state-of-the-art SAM2 segmentation model. YOLOv11n-seg was selected for its optimal balance of speed and accuracy, achieving 0.99 precision and 0.80 recall. To overcome the unreliability of static thresholding under changing lighting, various dynamic methods were evaluated. Otsu’s algorithm proved most effective, reducing the absolute error of the mean in SCP estimation to just 1.1%, a significant improvement over the 13.78% error from the previous fixed-thresholding approach. The integrated system was successfully validated for real-time performance on live drone video streams, demonstrating a highly accurate and scalable solution for autonomous snow monitoring on PV systems. Full article

A 9.4T brain MRI is the highest resolution MRI scanner in the public market. It offers submillimeter brain imaging with exceptional anatomical detail, making it one of the most powerful tools for detecting subtle structural changes associated with neurological conditions. Current segmentation models are optimized for lower-field MRI (1.5T–3T), and they struggle to perform well on 9.4T data. In this study, we present the GA-MS-UNet++, the world’s first deep learning-based model specifically designed for 9.4T brain MRI segmentation. Our model integrates multi-scale residual blocks, gated skip connections, and spatial channel attention mechanisms to improve both local and global feature extraction. The model was trained and evaluated on 12 patients in the UltraCortex 9.4T dataset and benchmarked against four leading segmentation models (Attention U-Net, Nested U-Net, VDSR, and R2UNet). The GA-MS-UNet++ achieved a state-of-the-art performance across both evaluation sets. When tested against manual, radiologist-reviewed ground truth masks, the model achieved a Dice score of 0.93. On a separate test set using SynthSeg-generated masks as the ground truth, the Dice score was 0.89. Across both evaluations, the model achieved an overall accuracy of 97.29%, precision of 90.02%, and recall of 94.00%. Statistical validation using the Wilcoxon signed-rank test (p < 1 × 10⁻⁵) and Kruskal–Wallis test (H = 26,281.98, p < 1 × 10⁻⁵) confirmed the significance of these results. Qualitative comparisons also showed a near-exact alignment with ground truth masks, particularly in areas such as the ventricles and gray–white matter interfaces. Volumetric validation further demonstrated a high correlation (R² = 0.90) between the predicted and ground truth brain volumes. Despite the limited annotated data, the GA-MS-UNet++ maintained a strong performance and has the potential for clinical use. This algorithm represents the first publicly available segmentation model for 9.4T imaging, providing a powerful tool for high-resolution brain segmentation and driving progress in automated neuroimaging analysis. Full article