Search Results (2,517)

The accurate monitoring of crop water status is critical for optimizing irrigation strategies in winter wheat. Compared with satellite remote sensing, unmanned aerial vehicle (UAV) technology offers superior spatial resolution, temporal flexibility, and controllable data acquisition, making it an ideal choice for the small-scale monitoring of crop water status. During 2023–2025, field experiments were conducted to predict crop water status using UAV images in the North China Plain (NCP). Thirteen vegetation indices were calculated and their correlations with observed crop water content (CWC) and equivalent water thickness (EWT) were analyzed. Four machine learning (ML) models, namely, random forest (RF), decision tree (DT), LightGBM, and CatBoost, were evaluated for their inversion accuracy with regard to CWC and EWT in the 2024–2025 growing season of winter wheat. The results show that the ratio vegetation index (RVI, NIR/R) exhibited the strongest correlation with CWC (R = 0.97) during critical growth stages. Among the ML models, CatBoost demonstrated superior performance, achieving R² values of 0.992 (CWC) and 0.962 (EWT) in training datasets, with corresponding RMSE values of 0.012% and 0.1907 g cm⁻², respectively. The model maintained robust performance in testing (R² = 0.893 for CWC, and R² = 0.961 for EWT), outperforming conventional approaches like RF and DT. High-resolution (5 cm) inversion maps successfully identified spatial variability in crop water status across experimental plots. The CatBoost-RVI framework proved particularly effective during the booting and flowering stages, providing reliable references for precision irrigation management in the NCP. Full article

The diameter of the sunflower flower head and the thickness of its margins are important crop phenotypic parameters. Traditional, single-dimensional two-dimensional imaging methods often struggle to balance precision with computational efficiency. This paper addresses the limitations of the YOLOv11n-seg model in the instance segmentation of floral disk fine structures by proposing the MBLA-YOLO instance segmentation model, achieving both lightweight efficiency and high accuracy. Building upon this foundation, a non-contact measurement method is proposed that combines an improved model with three-dimensional point cloud analysis to precisely extract key structural parameters of the flower head. First, image annotation is employed to eliminate interference from petals and sepals, whilst instance segmentation models are used to delineate the target region; The segmentation results for the disc surface (front) and edges (sides) are then mapped onto the three-dimensional point cloud space. Target regions are extracted, and following processing, separate models are constructed for the disc surface and edges. Finally, with regard to the differences between the surface and edge structures, targeted methods are employed for their respective calculations. Whilst maintaining lightweight characteristics, the proposed MBLA-YOLO model achieves simultaneous improvements in accuracy and efficiency compared to the baseline YOLOv11n-seg. The introduced CKMB backbone module enhances feature modelling capabilities for complex structural details, whilst the LADH detection head improves small object recognition and boundary segmentation accuracy. Specifically, the CKMB module integrates MBConv and channel attention to strengthen multi-scale feature extraction and representation, while the LADH module adopts a tri-branch design for classification, regression, and IoU prediction, structurally improving detection precision and boundary recognition. This research not only demonstrates superior accuracy and robustness but also significantly reduces computational overhead, thereby achieving an excellent balance between model efficiency and measurement precision. This method avoids the need for three-dimensional reconstruction of the entire plant and multi-view point cloud registration, thereby reducing data redundancy and computational resource expenditure. Full article

The construction industry is responsible for a significant amount of greenhouse gas emissions. Therefore, buildings have the potential to play a central role in climate change mitigation. It is also known that building projects are unique and complex, which is why a high degree of process automation is necessary. Two key methods can be employed to calculate the environmental impacts of a construction process: Building Information Modeling (BIM) and Life Cycle Assessment (LCA). Currently, both methods are being considered as a part of advanced building projects. Database (BIM) models can be used as a precise inventory of materials and as an input for LCA. This study aims to (1) review the current status of published BIM-LCA workflows, (2) use a common case study among participants from various countries to compare the individual workflows and the calculated results, (3) identify potential sources of errors in all workflows on the common case study, and (4) provide recommendations and suggestions for developing BIM-LCA models based on the example of the common case study. The outcomes show that the main sources of differences emerge from not including all materials or from the inconsistencies in the exported material lists of the bill of quantities. The reasons for the missing materials stem primarily from the inadequate decomposition of composite materials, oversight of certain materials, and exclusion of thin materials such as foils. Inconsistencies arise from the incorrect handling of composite materials, the grouping of similar materials, and rounding inaccuracies. These issues highlight that errors occur early in the life cycle inventory phase, which forms the foundation of subsequent LCA phases, thereby impacting the final results and potentially leading to inaccurate assessments of environmental impacts. Ensuring accuracy at this stage is therefore critical for supporting reliable sustainability assessments. Consequently, recommendations are proposed to mitigate errors across various stages of the process to enhance the accuracy of LCA outcomes. Full article

Against the backdrop of global energy transition, geothermal energy has emerged as a critical renewable resource, yet its exploration remains challenging due to uneven subsurface distribution and complex surface conditions. This study pioneers a novel framework integrating the Normalized Shaded Vegetation Index (NSVI) with radiative transfer-based land surface temperature inversion to detect geothermal anomalies in the Gonghe Basin, Qinghai Province. Using multi-source remote sensing data (GF5 B AHSI, ZY1–02D/E AHSI, and Landsat 9 TIRS), we first constructed NSVI, achieving 97.74% classification accuracy for shadowed vegetation/water bodies (Kappa = 0.9656). This effectively resolved spectral mixing issues in oblique terrain, enhancing emissivity calculations for land surface temperature retrieval. The radiative transfer equation method combined with NSVI-derived parameters yielded high-precision land surface temperature estimates (RMSE = 2.91 °C; R² = 0.963 against Landsat 9 products), revealing distinct thermal stratification: bright vegetation (41.31 °C) > shadowed vegetation (38.43 °C) > water (33.56 °C). Geothermal anomalies were identified by integrating temperature thresholds (>45.80 °C), 7 km fault buffers, and concealed Triassic granite constraints, pinpointing high-potential zones covering 0.12% of the basin. These zones are concentrated in central Gonghe, northern Guinan, and central-northern Guide counties. The framework provides a replicable solution for geothermal prospecting in topographically complex regions, with implications for optimizing exploration across the Gonghe Basin. Full article

As a key form of deep foundation in civil engineering, the concrete pouring quality of cast-in-place piles directly determines the integrity and long-term bearing performance of the pile body. Accurate monitoring of the pouring interface is critical to preventing defects such as mud inclusion and pile breakage. To address the limitations of existing monitoring methods for concrete pouring interfaces, this paper proposes a full-pulse acoustic monitoring method for the concrete pouring interface of cast-in-place piles. Firstly, by constructing a hardware system platform consisting of “multi-level in-borehole sound sources + interface acoustic wave sensors + orifice full-pulse receivers + ground processors”, differential capture of signals propagating at different depths is achieved through multi-frequency excitation. Subsequently, a waveform data processing method is proposed to realize denoising, enhancement, and frequency discrimination of different signals, and a target feature recognition model that integrates cross-correlation functions and signal similarity analysis is established. Finally, by leveraging the differential characteristics of measurement signals at different depths, a near-field measurement mode and a far-field measurement mode are developed, thereby establishing a calculation model for the elevation position of the pouring interface under different scenarios. Meanwhile, the feasibility of the proposed method is verified through practical engineering cases. The results indicate that the proposed full pulse acoustic monitoring method can achieve non-destructive, real-time, and high-precision monitoring of the pouring interface, providing an effective technical approach for quality control in pile foundation construction and exhibiting broad application prospects. Full article

This paper presents an electromagnetic levitation system that stabilizes a magnetic body using an array of electromagnets controlled by a Hall-effect sensor array and TinyML-based position detection. Departing from conventional optical tracking methods, the proposed design combines finite-element-optimized electromagnets with a microcontroller-optimized neural network that processes sensor data to predict the levitated object’s position with 0.0263–0.0381 mm mean absolute error. The system employs both quantized and full-precision implementations of a supervised multi-output regression model trained on spatially sampled data (40 × 40 × 15 mm volume at 5 mm intervals). Comprehensive benchmarking demonstrates stable operation at 850–1000 Hz control frequencies, matching optical systems’ performance while eliminating their cost and complexity. The integrated solution performs real-time position detection and current calculation entirely on-board, requiring no external tracking devices or high-performance computing. By achieving sub 30 μm accuracy with standard microcontrollers and minimal hardware, this work validates machine learning as a viable alternative to optical position detection in magnetic levitation systems, reducing implementation barriers for research and industrial applications. The complete system design, including electromagnetic array characterization, neural network architecture selection, and real-time implementation challenges, is presented alongside performance comparisons with conventional approaches. Full article

With the rapid advancement of mobile edge computing and Internet of Things (IoT) technologies, device-to-device (D2D) cooperative computing has garnered significant attention due to its low latency and high resource utilization efficiency. However, workflow task scheduling in D2D networks poses considerable challenges, such as severe heterogeneity in device resources and complex inter-task dependencies, which may result in low resource utilization and inefficient scheduling, ultimately breaking the computational symmetry—a balanced state of computational resource allocation among terminal devices and load balance across the network. To address these challenges and restore system-level symmetry, a novel workflow task scheduling method tailored for D2D cooperative environments is proposed. First, a Non-dominated Sorting Genetic Algorithm (NSGA) is employed to optimize the allocation of computational resources across terminal devices, maximizing the overall computing capacity while achieving a symmetrical and balanced resource distribution. A scoring mechanism and a normalization strategy are introduced to accurately assess the compatibility between tasks and processors, thereby enhancing resource utilization during scheduling. Subsequently, task priorities are determined based on the calculation of each task’s Shapley value, ensuring that critical tasks are scheduled preferentially. Finally, a hybrid algorithm integrating Q-learning with Asynchronous Advantage Actor–Critic (A3C) is developed to perform precise and adaptive task scheduling, improving system load balancing and execution efficiency. Extensive simulation results demonstrate that the proposed method outperforms state-of-art methods in both energy consumption and response time, with improvements of 26.34% and 29.98%, respectively, underscoring the robustness and superiority of the proposed method. Full article

The water retention and permeability characteristics of loess are core factors governing geological disaster prevention and engineering stability in the loess regions of northwest China. This study focuses on Yangling loess, systematically conducting soil water characteristic curve (SWCC) measurements and saturated permeability tests under different initial compaction degrees and water contents using a pressure plate apparatus and a TST-55 permeameter. By combining fitting analyses of the Gardner, Fredlund–Xing, and Van Genuchten SWCC models, the study reveals the influence mechanism of initial conditions on the water retention properties of Yangling loess. Furthermore, the unsaturated hydraulic conductivity of loess was predicted using the Van Genuchten–Mualem model. Finally, a quantitative relationship model between hydraulic conductivity and multiple factors (initial compaction degree, water content, and matric suction) was constructed using the response surface methodology. The results indicate the following: (1) A higher initial compaction degree and water content lead to a higher air entry value of loess, resulting in stronger water retention capacity. Among the three models, the Van Genuchten model exhibits the optimal fitting effect for the SWCC of Yangling loess. Its parameter a (related to the air entry value) decreases significantly with increasing compaction degree, while parameter n (pore size distribution index) increases linearly. The SWCC model, considering compaction degree, established based on these findings, can accurately predict the water retention characteristics in the high suction range (0~1200 kPa). This model’s precision in the high-suction segment is particularly valuable, as it addresses a critical range for engineering applications where soil behavior transitions from near-saturated to highly unsaturated states. (2) When loess transitions from a saturated to an unsaturated state, the hydraulic conductivity decreases up to 10⁴ times. Both increased initial compaction degree and water content lead to a significant reduction in hydraulic conductivity. This drastic reduction highlights the sensitivity of loess permeability to saturation changes, which is attributed to the rapid reduction in interconnected pore channels as soil suction increases and pore spaces are filled or compressed under higher compaction. (3) The response surface prediction model quantitatively reveals the influence weights of various factors on hydraulic conductivity in the order of matric suction > initial compaction degree > initial water content. The model exhibits a high coefficient of determination (R² = 0.9861), enabling rapid and accurate prediction of the hydraulic conductivity of Yangling loess. This high precision confirms that the model effectively captures the complex interactions between the factors, providing a reliable tool for practical engineering calculations. This study provides a new model and experimental basis for the accurate prediction of unsaturated loess hydraulic properties. The proposed SWCC model, considering compaction degree and the response surface model for hydraulic conductivity, offers practical tools for engineers and researchers, facilitating more precise design and risk assessment in collapsible loess areas. Full article

This study develops an innovative unmanned aerial vehicle (UAV)-based intelligent system for winter wheat yield prediction, addressing the inefficiencies of traditional manual counting methods (with approximately 15% error rate) and enabling quantitative analysis of water–fertilizer interactions. By integrating an enhanced Faster Region-Based Convolutional Neural Network (Faster R-CNN) architecture with multi-source data fusion and machine learning, the system significantly improves both spike detection accuracy and yield forecasting performance. Field experiments during the 2022–2023 growing season captured high-resolution multispectral imagery for varied irrigation regimes and fertilization treatments. The optimized detection model incorporates ResNet-50 as the backbone feature extraction network, with residual connections and channel attention mechanisms, achieving a mean average precision (mAP) of 91.2% (calculated at IoU threshold 0.5) and 88.72% recall while reducing computational complexity. The model outperformed YOLOv8 by a statistically significant 2.1% margin (p < 0.05). Using model-generated spike counts as input, the random forest (RF) model regressor demonstrated superior yield prediction performance (R² = 0.82, RMSE = 324.42 kg·ha⁻¹), exceeding the Partial Least Squares Regression (PLSR) (R² +46%, RMSE-44.3%), Least Squares Support Vector Machine (LSSVM) (R² + 32.3%, RMSE-32.4%), Support Vector Regression (SVR) (R² + 30.2%, RMSE-29.6%), and Backpropagation (BP) Neural Network (R²+22.4%, RMSE-24.4%) models. Analysis of different water–fertilizer treatments revealed that while organic fertilizer under full irrigation (750 m³ ha⁻¹) conditions achieved maximum yield benefit (13,679.26 CNY·ha⁻¹), it showed relatively low water productivity (WP = 7.43 kg·m⁻³). Conversely, under deficit irrigation (450 m³ ha⁻¹) conditions, the 3:7 organic/inorganic fertilizer treatment achieved optimal WP (11.65 kg m⁻³) and WUE (20.16 kg∙ha⁻¹∙mm⁻¹) while increasing yield benefit by 25.46% compared to organic fertilizer alone. This research establishes an integrated technical framework for high-throughput spike monitoring and yield estimation, providing actionable insights for synergistic water–fertilizer management strategies in sustainable precision agriculture. Full article

High-precision angular contact ball bearings (ACBBs) are critical components in advanced manufacturing equipment, where rotation accuracy directly determines system performance and stability. Considering error superposition and equipment processing capability comprehensively, this study establishes an error analysis and control model of the ACBBs, studies the error transmission law, and puts forward a rotation accuracy control strategy for batch manufacturing of precision ACBBs. The ACBBs 7020C/P4, 7020AC/P4, 7020A/P4, and 7020B/P4 (four conventional contact angles of 15°, 25°, 30°, 40°) were taken as examples to verify the experiment. The error of the calculation compared with actual test results was not more than 7.5%, which had good accuracy and practicability. The research shows that the roundness error of bearing raceway, the thickness difference in bearing ring wall, and the parallelism error of raceway to end face were the main influencing factors of bearing rotation accuracy Kia, Sia, Kea, and Sea. The influence coefficient of raceway roundness error on the axial runout of bearing (Sia, Sea) decreased rapidly with the increase in contact angle, while the influence coefficient on radial runout (Kia, Kea) remained constant. The rotation accuracy error of the outer ring was always greater than that of the inner ring, and this law was not affected by the contact angle. Moreover, with the increase in contact angle, the radial runout of the inner and outer rings of the bearing increased. During actual machining, bearings with larger contact angle place lower demands on the equipment process capability index (Cp), particularly on the parameter Cer. This reduction in required capability is equivalent to an effective Cp improvement of about 30%. Full article

Background: Accurate prediction of postoperative care requirements is critical for patient safety and resource allocation. Although numerous approaches involving artificial intelligence (AI) and machine learning (ML) have been proposed to support such predictions, their implementation in practice has so far been insufficiently successful. One reason for this is that the performance of the algorithms is difficult to assess in practical use, as the accuracy of clinical decisions has not yet been systematically quantified. As a result, models are often assessed purely from a technical perspective, neglecting the socio-technical context. Methods: We conducted a retrospective, single-center observational study at the University Hospital Augsburg, including 35,488 elective surgical cases documented between August 2023 and January 2025. For each case, preoperative care-level predictions by surgical and anesthesiology teams were compared with the actual postoperative care provided. Predictive performance was evaluated using accuracy and sensitivity. Since this is a highly imbalanced dataset, in addition to sensitivity and specificity, the balanced accuracy and the $F_{\beta }$-score were also calculated. The results were contrasted with published Machine-Learning (ML)-based approaches. Results: Overall prediction accuracy was high (surgery: 91.2%; anesthesiology: 87.1%). However, sensitivity for identifying patients requiring postoperative intensive care was markedly lower than reported for ML models in the literature, with the largest discrepancies observed in patients ultimately admitted to the ICU (surgery: 38.05%; anesthesiology: 56.84%; ML: 70%). Nevertheless, clinical judgment demonstrated a superior $F_1$-score, indicating a more balanced performance between sensitivity and precision (surgery: 0.527; anesthesiology: 0.551; ML: 0.28). Conclusions: This study provides the first real-world benchmark of clinical expertise in postoperative care prediction and shows a way in which modern ML approaches must be evaluated in a specific sociotechnical context. By quantifying the predictive performance of surgeons and anesthesiologists, it enables an evaluation of existing ML approaches. Thus the strength of our work is the provision of a real-world benchmark against which all ML methods for preoperative prediction of ICU demand can be systematically evaluated. This enables, for the first time, a comparison of different approaches on a common, practice-oriented basis and thus significantly facilitates translation into clinical practice, thereby closing the translational gap. Furthermore it offers a data-driven framework to support the integration of ML into preoperative decision-making. Full article

The exponential growth of space objects in near-Earth and geostationary orbits has posed severe threats to space environment safety, with debris clouds from spacecraft breakup events being a critical concern. Debris cloud tracing, as a key technology for locating breakup points, faces dual challenges of insufficient precision in analytical methods and excessive computational load in numerical methods. To balance traceability accuracy with computational efficiency, this paper proposes a breakup time determination method integrating a clustering algorithm and the minimization of average relative distance. The method first calculates the average relative distance between fragment pairs and preliminarily estimates the breakup epoch using a golden section step-size optimization strategy. Subsequently, the density peak clustering (DPC) algorithm is introduced to eliminate abnormal fragments. The breakup epoch is then refined based on the cleansed fragment dataset, achieving high-precision localization. Validation through simulations of real breakup events demonstrates that this method significantly improves localization accuracy. It establishes a highly reliable temporal benchmark for space collision tracing, debris diffusion prediction, and orbital safety management. Full article

The paper presents a hybrid intelligent expert diagnostic system (HIESD) of power transformer (PT) subsystems realized on the basis of integration of measuring and computing hardware and software complexes into a single functional architecture. HIESD performs online diagnostics of four main subsystems of PT: 1—insulating (liquid and solid insulation); 2—electromagnetic (windings, magnetic conductor); 3—voltage regulation; and 4—high-voltage inputs. Computational complexes and modules of the system are connected with the real object of power grids, 110/10 kV substation, which interact with each other and contain a relational database of retrospective offline data of the PT “life cycle” (including test and measurement results), supplemented by online monitoring data of the main subsystems, corrected by high-precision test measurements; analytical complex, in which the work of calculation modules of the operational state of PT subsystems is supplemented by predictive analytics and machine learning modules; and a knowledge base, sections of which are regularly updated and supplemented. The system architecture is tested at industrial facilities in terms of online transformer diagnostics based on dissolved gas analysis (DGA) data. Additionally, a theoretical model of diagnostics based on the electromagnetic characteristics of the transformer, which takes into account distorted and nonlinear modes of its operation, is presented. The scientific significance of the work consists of the presentation of the following new provisions: Methodology and algorithm for diagnostics of electromagnetic parameters of ST, taking into account nonlinearity and non-sinusoidality of winding currents and voltages; formation of optimal client–service architecture of training models of hybrid system based on the processes of data storage and management; and modification of the moth–flame algorithm to optimize the smoothing coefficient in the process of training a probabilistic neural network Full article

YKL-40 is a glycoprotein that may be present at elevated levels in many cancers and neurodegenerative diseases. It has been investigated in numerous studies as a potential biomarker for several conditions, including Alzheimer’s Disease (AD). In this study, a biosensor with Surface Plasmon Resonance imaging (SPRi) detection, sensitive to YKL-40, was constructed for the detection of this analyte in the blood plasma of AD patients. Extensive validation of the biosensor was performed. This included the determination of analytical parameters such as the biosensor’s response characteristics, detection and quantification limits, precision, accuracy, repeatability, selectivity, stability, and performance in natural samples. Validation parameters were primarily tested using standard solutions, while natural samples were employed to evaluate repeatability, stability, and assay accuracy in three groups of samples from different patients. A YKL-40-specific antibody was used as the receptor layer, immobilized on a gold plate using the EDC/NHS protocol on thiol 11-MUA. The biosensor exhibited a wide operating range (1–200 ng/mL), a low detection limit (LOD) of 2 pg/mL, and a quantification limit (LOQ) of 7 pg/mL. High precision and accuracy were confirmed by the calculated standard deviations (SD) and coefficients of variation (CV), which ranged from 0.0009 to 7.02 ng/mL and from 0.12% to 9.24%, respectively. The sensor also demonstrated good repeatability (CV = 4.995%) and was capable of detecting the analyte of interest in complex biological matrices. Its applicability was confirmed in a study using plasma from AD patients and two selected control groups: plasma from smokers and patients with prostatitis. This allowed the assessment of YKL-40 levels across different groups. The results were consistent with literature values, and statistical analysis confirmed the significance of concentration differences between groups. Furthermore, ROC curve analysis confirmed the diagnostic usefulness of the constructed YKL-40 test in the context of Alzheimer’s disease. Full article

The daily milk yield (DMY) is defined as the sum of milk produced during morning, midday, and evening milkings. This metric is the key parameter for quantifying a cow’s absolute production level and serves as the foundation for calculating economic traits such as 305-day total milk yield, fat yield, and protein yield, making it essential for evaluating lactation performance. Based on the data cleaning pipeline, 2992 valid records were retained from 3332 initial records through rigorous quality-control screening, this study systematically evaluated three critical lactation traits—daily milk yield and its milk components (milk fat percentage and milk protein percentage)—using complete lactation records from Huaxi cows and estimated their phenotypic and genetic parameters. Non-genetic factors (parity, season, and mature body weight) were corrected via the MIXED procedure coupled with a multi-trait animal model. The results showed that all considered non-genetic factors significantly influenced the lactation traits (p < 0.05), while daily milk yield (DMY), milk fat percentage (FP), and milk protein percentage (PP) all exhibited moderate to high heritability (0.29–0.38) (p < 0.01). Genetic evaluation of DMY and its milk components provides quantitative evidence for precision selection and optimized mating decisions in the Huaxi dairy population, thereby accelerating genetic progress in milk production, improving herd profitability, and promoting the development of the regional dairy industry. Full article