Search Results (3,263)

Land surface temperature (LST) is a core physical parameter that characterizes land surface processes and surface-atmosphere energy exchange. As the demand for high-accuracy LST products intensifies across diverse research domains—including climate science, hydrology, and ecosystem modeling—the systematic quantification of pixel-level retrieval uncertainties has become essential for generating long-term, consistent Climate Data Records (CDRs). However, existing studies predominantly emphasize algorithmic development or localized validation, with limited attention to systematic cross-site and long-term uncertainty assessments. This gap impedes a comprehensive understanding of the compositional structure and spatiotemporal variability of LST retrieval uncertainties under heterogeneous surface and atmospheric conditions. In this study, based on the improved generalized split-window (GSW) algorithm and error propagation theory, the total uncertainty (U_total) and its four primary components—algorithm uncertainty (U_a), land surface emissivity uncertainty (U_e), noise equivalent delta temperature uncertainty (U_n), and atmospheric water vapor uncertainty (U_w)—at the pixel level over long time series and across multiple sites are quantified. Our analysis spans a 21-year period (2003–2023) and encompasses multiple geographically distributed sites, utilizing high-quality Moderate Resolution Imaging Spectroradiometer (MODIS) thermal infrared data—specifically MYD11_L2 and MOD11_L2 products—collocated at the locations of 15 globally distributed ground-based reference sites. These sites are used to represent diverse climatic regimes and land-cover conditions, rather than to provide point-scale “true” LST values for residual-based validation. Results show that the interquartile range (IQR) of U_total is consistently concentrated between 1.0 and 1.2 K, demonstrating long-term stability. Systematic differences in U_total are identified across sensor platforms and diurnal cycles: U_total for Aqua/MYD data (1.13–1.25 K) is marginally higher than that for Terra/MOD data (1.05–1.17 K); similarly, daytime U_total (1.08–1.23 K) is generally slightly elevated relative to nighttime U_total (1.05–1.18 K). The contributions of individual uncertainty components to U_total exhibit substantial variation, with mean relative contributions of 81.97%, 11.32%, 4.46%, and 2.25% for U_e, U_a, U_n, and U_w, respectively. The dominant drivers of U_total differ markedly across climatic regions: in arid regions, U_total is predominantly governed by U_e, termed “emissivity-dominated,” accounting for over 85% of the total; conversely, humid tropical regions exhibit a “surface-atmosphere co-influenced” regime, characterized by a reduced contribution from U_e and correspondingly enhanced contributions from U_a and U_w. Furthermore, U_total decreases with increasing total column water vapor (TCWV) (Pearson correlation coefficient r = −0.498; linear slope k = −0.0425 K/(g/cm²)), and increases with increasing viewing zenith angle (VZA) (r = 0.208; k = 0.0022 K/degree). While U_a, U_n, and U_w all increase with TCWV, U_e decreases. Full article

In order to describe the heavy ion collision dynamics which implies the formation of hot and very dense nuclear matter in the overlapping region of the two colliding nuclei, we used simulated numerical calculations for FAIR available energies. We used the anti-$k_T$ jet-detection algorithm for highlighting the main directions of flow in Au-Au collisions at CBM energies, thus obtaining structures of the events depending on the number of flow streams. The jet-finder algorithm identified domains in the y-$\psi$ (rapidity-azimuthal angle) plane, where the number of charged particles, momenta and energy take higher values compared to other areas of this plane. The anisotropic flow coefficients $v_n$ may offer information about the pressure gradients in the early stages of the collision and about the high-density nuclear matter properties. The observation of $K^{+}$ mesons in heavy ion collisions is of interest since $K^{+}$ mesons, due to their strangeness, have a mean free path that exceeds the dimensions of the “fireball”. In the numerical calculations the interval of rapidity $0<y<0.8$ is highlighted, for which the fluctuations of the antiparticle to particle ratio excitation functions show non-monotonic behavior in the 10–13 A GeV energy interval. Full article

Electroencephalography (EEG) offers a non-invasive and cost-effective means of probing brain activity during language processing; however, prior EEG-based language studies have been limited by small datasets, a predominant focus on native-speaker or speech-unit recognition rather than direct language detection, evaluation on only a small number of experimental settings, and frequent reliance on computationally intensive deep learning models with limited interpretability. The proposed feature engineering models classifies EEG segments by language and task mode. The languages are Arabic and Turkish. The modes are reading and listening. In this study, a signal refers to one fixed-length multi-channel EEG segment (14 channels × 15 s at 128 Hz). A channel refers to one electrode time series within that segment. To address these gaps, we curated a new EEG language detection dataset from 346 participants (98 Arabic and 248 Turkish) recorded in reading and listening modes, yielding 6364 EEG segments. Using this dataset, we proposed DiagPat, an explainable feature engineering (XFE) model that extracts transition table-based features from both EEG channels and signals through diagonal pattern analysis. The model combines DiagPat feature extraction with iterative neighborhood component analysis (INCA) for feature selection, at algorithm-based k-nearest neighbors (tkNN) classifier for prediction, and the Directed Lobish (DLob) symbolic language for explainability. We evaluated the framework across nine classification cases covering language detection, mode detection, and mixed multi-class settings. The proposed DiagPat-driven XFE model achieved more than 90% accuracy in all cases, with accuracies ranging from 92.14% to 99.35%, and generated case-specific cortical connectome diagrams that supported the interpretable characterization of language- and mode-related brain activity. Subject-independent results were also reported using leave-one-subject-out cross-validation (LOSO CV), where LOSO accuracies ranged from 29.75% to 83.50%. Thus, the 10-fold CV results show segment-level performance, whereas the LOSO results show subject-level generalization. Balanced accuracy and macro-F1 are also reported. These findings indicate that DiagPat provides an accurate, lightweight, and explainable framework for EEG-based language detection. Full article

Efficient and precise control of district heating (DH) networks is a critical pathway for achieving energy optimization and carbon emission reduction. This study proposes a systematic approach integrating data augmentation, hybrid model forecasting, and cost optimization. First, a Generative Adversarial Network (GAN) is employed to generate scenarios from limited meteorological and operational data, constructing an expanded dataset. Based on this, a personalized load forecasting model utilizing a dynamically weighted LSTM–Prophet combination is developed. This model assigns personalized weights to each heating station to accommodate the operational requirements of different functional zones. Validated using a district heating network in Tianjin, the results indicate that with an optimal weight of w = 0.9, the average relative error for load forecasting at Heating Station566 is −0.65%. Furthermore, the K-means algorithm is used to cluster the scenario database. The resulting typical scenarios are input into the LSTM–Prophet model to obtain real-time loads for each station, and a cost optimization model based on the APSO algorithm is subsequently constructed. Evaluated using a representative day, the optimized system achieves a reduction in distribution-stage cost of approximately 270,600 RMB, with a saving rate of 38%. Full article

With the advancement of carbon peaking and carbon neutrality goals, the increasing penetration of renewable energy sources such as wind and photovoltaic power poses severe challenges to the power supply reliability of AC/DC hybrid distribution networks due to their fluctuating, intermittent, and stochastic outputs. This paper proposes a reliability assessment method for AC/DC hybrid distribution networks under large-scale renewable energy integration based on clustering of typical operating scenarios. The net load duration curve is adopted as the feature variable to characterize typical operating scenarios. An improved t-distributed Stochastic Neighbor Embedding (t-SNE) nonlinear dimensionality reduction method with Kullback–Leibler (KL) divergence elbow correction is proposed for effective reduction of high-dimensional time-series data. An adaptive Density-Based Spatial Clustering of Applications with Noise (DBSCAN) parameter optimization method based on the k-nearest-neighbor curve and a secondary K-means clustering method based on entropy-weighted multi-objective optimization are further developed, forming a hybrid t-SNE-DBSCAN–K-means clustering algorithm. The power supply reliability is then assessed based on the clustered typical operating scenarios. A typical AC/DC hybrid distribution network is used as the test system. Results show that the DB index of the proposed clustering method improves by at least 22% compared with conventional methods, the maximum relative error between the typical-day-based and full time-series simulation results is less than 6%, and the computational efficiency improves by about 8.8 times, achieving a good balance between accuracy and efficiency. Full article

This study investigates the mechanical performance of resistance spot-welded titanium lap joints made of Grade 1 and Grade 5 alloys. Experimental tests were combined with artificial neural network modeling to predict joint load-bearing capacity based on welding current and welding time. Three models were developed for Grade 1/Grade 1, Grade 1/Grade 5, and Grade 5/Grade 5 joints. The mixed Grade 1/Grade 5 joint achieved the highest predictive accuracy, with an R² value of 0.9289. Statistical evaluation confirmed high model reliability, with mean relative errors between four and six percent. The most accurate model was optimized using a genetic algorithm. The algorithm identified an optimal parameter set consisting of a welding current of 2.89 kA and a welding time of five pulses. This configuration produced a predicted load-bearing capacity of 3.2 kN, which meets the required threshold of three kilonewtons. Contour maps showed that the optimal point lies near the boundary of the high-strength region and corresponds to the lowest welding current and shortest welding time that still ensure sufficient joint quality. The results demonstrate that combining neural network modeling with evolutionary optimization is an effective approach for designing efficient welding processes for dissimilar titanium joints. Full article

Manual counting of surgical tools, known as surgical counting, is a time-consuming and error-prone task that increases the risk of retained surgical instruments and extends operating room (OR) time. Presently, in hospitals around the world, surgical counting is often performed manually with paper or tablet checklists, often leading to delays, increased infection risk, and financial cost. RFID, barcode-based, and computer vision solutions exist but are expensive and have challenges with sterilization and signal interference. This paper presents ToolSafe, a low-cost, portable system that classifies surgical tools by their acoustic signatures when dropped into a detection box. A pilot dataset of 4004 audio samples from four tool types (n = 996, tissue forceps; n = 1005, iris scissors; n = 1006, scalpel handle; n = 997, testing needle) was collected using ToolSafe. A convolutional neural network (CNN) was evaluated using stratified five-fold cross-validation on the laboratory dataset, with a k-nearest neighbors (KNN) classifier implemented as a control model. In each fold, both models were trained on 80% of the data and tested on the remaining 20%, ensuring that all samples were used for both training and evaluation. The CNN achieved a mean (±standard deviation) classification accuracy of 99.55% (±0.19%) across the validation folds, outperforming the KNN model, which achieved a mean accuracy of 97.28% (±0.50%). The difference was statistically significant according to a paired t-test across folds (p = 0.0003), indicating CNN’s superior performance on the dataset. For a run of 100 additional samples using the Raspberry Pi-based system, spectrogram generation averaged 0.121 s (±0.025 s), CNN inference averaged 0.180 s (±0.033 s), and total end-to-end latency averaged 1.851 s (±0.253 s) per tool. This pilot study proposes a possible technological solution for surgical counting that reduces human error and enhances patient safety. ToolSafe may be subsequently improved by increasing the number of surgical tools used in the training dataset, testing under more robust OR-like environments, and comparing to other classification algorithms. Further refinement and incorporation of ToolSafe in operating room workflows have the potential to reduce patient risks from extended surgical times and retained surgical instruments. Full article

Optimizing fertilizer management is crucial for increasing crop yields while reducing environmental impact. However, traditional methods rely on extensive field trials, which are costly and limit their scalability. To overcome these limitations, this study developed data-driven yield prediction models (YPM) for wheat, rice, and maize by integrating multiple feature selection and machine learning algorithms with explainable ensemble learning, namely stacking regression (SR) and voting mean (VM). The optimal YPM was subsequently combined with the hybrid optimization strategy to construct an intelligent fertilization decision model (IFDM), and the economic–environmental benefits were subsequently evaluated. The best-performing models were SHAP-SR for wheat and rice and GBM-SR for maize, achieving R² values of 0.79, 0.69, and 0.67, and RMSEs of 681.69, 725.35, and 1091.49 kg ha⁻¹, respectively. Based on the IFDM, the recommended application ranges for nitrogen (N), phosphorus (P₂O₅), and potassium (K₂O) were as follows: for wheat, 122.1–256.3, 45.4–98.2, and 30.6–60.7 kg ha⁻¹; for rice, 170.8–261.2, 55.1–91.4, and 40.6–98.5 kg ha⁻¹; and for maize, 157.5–293.4, 84.2–156.4, and 30.1–62.7 kg ha⁻¹. Simulation-based evaluation suggested that adopting these recommendations could potentially increase average yields by 9.2–12.4% and enhance economic–environmental benefits by 32.86–97.73% across the three crops. This study indicates that coupling interpretable ensemble learning with a hybrid optimization strategy can support efficient decision-making for field-scale fertilization and provides a data-driven and cost-effective approach for precision fertilization, with potential applicability to arid agricultural regions under similar agro-ecological conditions. Full article

To boost the net power output of proton exchange membrane (PEM) fuel cell systems under variable operating conditions, this study proposes an adaptive neural network (NN) control strategy that integrates parameter optimization. The air supply subsystem is the primary focus, as its performance is crucial to the overall net power. First, a comprehensive model of the air supply subsystem is developed, along with a detailed analysis of cathode pressure, oxygen excess ratio (OER), and net power output. Then, a two-dimensional particle swarm optimization (TDPSO) algorithm is used to optimize the reference signals for cathode pressure and OER, thereby maximizing net power. By applying input–output linearization techniques, the originally coupled nonlinear multi-input multi-output (MIMO) system is decoupled and transformed into a canonical form. Based on this transformation, an adaptive NN controller is designed to regulate the pressure valve and compressor. A series of hardware-in-loop (HIL) tests confirm that the proposed control strategy effectively optimizes net power across diverse operating scenarios. Quantitative results show that the proposed method achieves a net power output of 28.6 kW to 42.1 kW over the tested current range of 100–300 A. Meanwhile, the comparisons show that the proposed controller achieves OER tracking with root mean square error (RMSE) of 0.1221 and cathode pressure with RMSE of 0.0033. In comparison, the fuzzy logic controller (FLC) achieves OER with RMSE of 0.1453 and pressure with RMSE of 0.0044, while proportional–integral–derivative (PID) controller achieves OER with RMSE of 0.2133 and pressure with RMSE of 0.0109. Full article

The indoor environmental quality of primary and secondary school classrooms is crucial for students’ health and learning efficiency, yet enhancing comfort often leads to high energy consumption. Efficiently balancing the complex relationship between daylighting, visual comfort, and energy consumption during the early design stage presents a significant challenge for architects. To address the design optimization of standard classrooms in primary and secondary schools in the cold region of Zhengzhou, this paper proposes an efficient multi-objective optimization method based on metamodels. This method integrates physical performance simulation (EnergyPlus and Radiance), Latin Hypercube Sampling (LHS), an artificial neural network (ANN) metamodel, and the Non-Dominated Sorting Genetic Algorithm II (NSGA-II). Using Useful Daylight Illuminance (UDI), Discomfort Glare Index (DGI), and Cooling Energy Use Intensity (cEUI) as optimization objectives, ten design parameters, including classroom spatial form and envelope structure, were optimized. The aim is to replace time-consuming traditional simulation calculations and rapidly generate a Pareto optimal solution set. A case study of a typical south-facing classroom in Zhengzhou demonstrates that this method can substantially improve daylighting performance while moderately reducing cooling energy. Compared to the baseline model, the optimized schemes show an average increase in UDI of 42.9% (maximum 50.5%), an average reduction in DGI of 8.4% (maximum 9.6%), and an average reduction in cEUI of 4.7% (maximum 7.7%). Because the study focuses on summer cooling energy only, the reported cEUI improvement should not be interpreted as an annual energy reduction. Through K-means clustering and sensitivity analysis, the study further identifies different design strategies from the Pareto solution set and clarifies the key design variables affecting each performance indicator. This provides an evidence-based reference and preliminary design guidelines for the early-stage design of primary and secondary school classrooms in the region. Full article

In factory workshops, wearing safety helmets is vital for worker safety. However, current deep learning-based detection methods are often hindered by large model parameters and high computational demands, limiting their deployment in resource-constrained settings. This article introduces YOLO-AFL, a novel lightweight model designed to solve these problems. The algorithm introduces several key optimizations to improve performance without increasing computational load. Firstly, the K-Means++ algorithm is applied during the anchor box preprocessing stage, along with a new distance metric (1 − AIoU), which enhances anchor box size estimation and boosts performance without additional overhead. Secondly, by introducing a lightweight PConv operation into the C3 module, the complexity of the model is significantly reduced. Finally, a dual attention network (LDA-GC) is designed to compensate for any accuracy loss caused by the model’s simplifications. Experimental results on a custom dataset show that the proposed algorithm achieves an mAP50 of 94.1%. Compared to the baseline model, it reduces the number of parameters by 19.1% and decreases computational complexity by 16.9%, demonstrating its superior performance and efficiency in safety helmet wearing detection. Full article

Todos Santos Bay, Mexico, features several wave-focusing areas driven by its complex bathymetry, making it an ideal real-world test case for wave energy converter (WEC) park optimization. This study quantifies the influence of submarine cable costs and bathymetry-dependent mooring costs on the proposed park layout (hereafter the star-layout) and the levelized cost of energy (LCOE) of a 10-device WEC park, using a multi-state operational wave climatology of $N=179$ representative sea states from a 2008–2018 SNL-SWAN hindcast (covering 97.20% of the annual time). A binary genetic algorithm combined with K-means clustering analysis was used to minimize LCOE under three cost scenarios: baseline, cable-only, and cable plus bathymetry-dependent mooring. Both infrastructure cost components contribute substantially: cable costs add 52.2% to the baseline LCOE, and bathymetry-dependent mooring costs add a further 16.0% at this site, with cable approximately three times more impactful. These quantitative magnitudes are conditioned on the moderate depth-gradient setting of Todos Santos Bay; the qualitative cost-component hierarchy is expected to generalize, but the relative weights will depend on the bathymetric and wave-climate characteristics of each candidate site. The mooring contribution is nontrivial both economically and spatially (the centroid of the park shifts by approximately 151 m between the cable-only and cable-plus-depth scenarios). K-means clustering identified 2–4 layout families per scenario (K $=4\to 3\to 2$ as cost components are added), indicating that infrastructure constraints reduce the viable solution space. These results support the central hypothesis of this work: WEC park optimization studies that adopt flat-bathymetry simplifications, the prevailing assumption in much of the prior literature, risk substantial underestimation of LCOE at sites with nontrivial depth variation. We recommend that bathymetry-dependent mooring costs be included alongside cable costs in any early-stage techno-economic assessment of WEC parks at sites with complex bathymetry. Full article

Real-time tracking of high-speed targets in autonomous systems requires detection and decision-making pipelines that can operate within sub-millisecond time budgets. Single Photon Avalanche Diode (SPAD) sensors are well suited for this task, offering 10 kHz Time-of-Flight (ToF) measurements with picosecond timing precision. However, processing such high-frequency time-series data with conventional deep learning models introduces computational bottlenecks that are difficult to handle on resource-constrained embedded hardware. This paper presents an ultra-lightweight, dual-head architecture built on the MiniRocket transformation algorithm, where a single shared feature extractor simultaneously feeds two independent decision pathways: one for multi-class target classification and one for 3-parameter kinematic regression covering velocity, pitch, and yaw. As a single-pixel sensor, the device provides only 1D range information; lateral 3D spatial localization is outside the scope of this work. To the best of the authors’ knowledge, this is the first application of MiniRocket to continuous kinematic estimation from high-frequency sensor data. Since collecting labeled physical flight data at these speeds is largely infeasible, a physics-based ray-casting simulation was developed to generate a 55,440-sample dataset across four 3D CAD target models under varying speed (100–450 m/s), orientation, and noise conditions. The proposed architecture achieves 98.6% classification accuracy and a velocity Mean Absolute Error (MAE) of 0.26 m/s, with orientation estimation yielding a pitch MAE of 3.47° and a yaw MAE of 2.46°—values consistent across all five cross-validation folds, indicating that the orientation performance floor is governed by the sensor’s physical angular resolution rather than by model capacity. With approximately 27,000 trainable parameters, the system completes full dual-task inference in 0.56 ms on a 16-core CPU (1785 Frames Per Second-FPS), satisfying the 1 ms real-time constraint of a 10 kHz sensor without GPU acceleration. It should be noted that the single-pixel SPAD architecture provides only 1D range-along-beam information; full 3D spatial localization is physically not extractable from a single sensor and is not addressed in this study. Full article

Alzheimer’s disease (AD) is a serious neurodegenerative disorder that can severely affect behavior and thinking patterns, and is accompanied by frequent memory loss. The early diagnosis of AD is essential, as this can benefit the patient, but detecting AD is a complex process due to the nature of its associated clinical data. Electroencephalography (EEG) serves as a promising and cost-effective technique for analyzing AD-related brain activity patterns. In this work, a consolidated framework for detecting AD using EEG signals and hybrid models is proposed that uses a dataset that is available online. For the feature extraction module, five efficient techniques—Principal Component Analysis (PCA), Kernel Partial Least Squares (KPLS), Kriging Model, Isomap, and K-means clustering—are used. For feature selection, with the help of biomimetics-based concepts, three efficient algorithms are used: hybrid Cuckoo Search Optimization–Rat Swarm Optimization (CSO-RSO), Zebra Optimization (ZOA), and hybrid Gravitational Search Algorithm–Particle Swarm Optimization (GSA-PSO). Four interesting hybrid classifiers are utilized here to detect AD using EEG signals—hybrid Extreme Learning Machine–Adaboost (ELM–Adaboost), hybrid Classification and Regression Trees–Adaboost (CART–Adaboost), and hybrid weighted broad learning system-based Adaboost (HWBLSA), followed by a hybrid machine learning classification model with a soft voting technique—and, finally, these are compared with other standard machine learning classifiers. The highest classification accuracy of 98.71% is found when the Kriging Model feature extraction concept is combined with the hybrid GSA-PSO feature selection method and classified with the ELM–Adaboost classifier. Full article

Because high-precision DEMs are costly to obtain, while low-precision DEMs often fail to meet accuracy requirements for watershed flood simulation, this study proposes a multi-source DEM fusion method based on the Random Forest algorithm. This method combines K-Means slope clustering and Optuna hyperparameter optimization to realize adaptive weight allocation across eight slope zones. After multi-source DEM fusion, the fused DEM is applied to the flood simulation model of the Wei River Basin to simulate the catastrophic flood event in July 2021. The results show that the Mean Absolute Error (MAE) of the fused DEM ranges from 0.9855 to 1.7218, the Root Mean Square Error (RMSE) ranges from 1.0902 to 2.3953, and the Mean Error (ME) is close to 0 with no significant systematic bias. Compared with single-source DEM, the fused DEM reduces MAE by 21.32–85.32% and RMSE by 7.63–82.03%. In flood simulation, the peak discharge error based on the fused DEM is controlled within 0.013–0.059, and the coefficient of determination (R²) is not less than 0.9808. The simulated errors of inundation area and flood detention volume in flood detention areas are significantly lower than those using a single-source DEM. The proposed multi-source DEM fusion method can effectively improve terrain accuracy and the reliability of flood routing simulation, providing technical support for flood control scheduling in the Wei River Basin and watershed hydrological and flood simulation in data-scarce regions. Full article