Search Results (82)

In this paper, we propose a fuzzy formulation of the classic Frankot–Chellappa algorithm by which surfaces can be reconstructed using normal vectors. In the fuzzy formulation, the surface normal vectors may be uncertain or ambiguous, yielding a fuzzy Poisson partial differential equation that requires appropriate definitions of fuzzy derivatives. The solution of the resulting fuzzy model is approached by adopting a fuzzy variant of the discrete sine transform, which results in a fast and robust algorithm for surface reconstruction. An adaptive defuzzification strategy is also introduced to improve noise handling in highly uncertain regions. In experiments, we demonstrate that our fuzzy Frankot–Chellappa algorithm achieves accuracy on par with the classic approach for smooth surfaces and offers improved robustness in the presence of noisy normal data. We also show that it can naturally handle missing data (such as gaps) in the normal field by filling them using neighboring information. Full article

This study proposes the PHD-YOLO model as a means to enhance the precision of passion fruit detection in intricate orchard settings. The model has been meticulously engineered to circumvent salient challenges, including branch and leaf occlusion, variances in illumination, and fruit overlap. This study introduces a pioneering partial convolution module (ParConv), which employs a channel grouping and independent processing strategy to mitigate computational complexity. The module under consideration has been demonstrated to enhance the efficacy of local feature extraction in dense fruit regions by integrating sub-group feature-independent convolution and channel concatenation mechanisms. Secondly, deep separable convolution (DWConv) is adopted to replace standard convolution. The proposed method involves decoupling spatial convolution and channel convolution, a strategy that enables the retention of multi-scale feature expression capabilities while achieving a substantial reduction in model computation. The integration of the HSV Attentional Fusion (HSVAF) module within the backbone network facilitates the fusion of HSV color space characteristics with an adaptive attention mechanism, thereby enhancing feature discriminability under dynamic lighting conditions. The experiment was conducted on a dataset of 1212 original images collected from a planting base in Yunnan, China, covering multiple periods and angles. The dataset was constructed using enhancement strategies, including rotation and noise injection, and contains 2910 samples. The experimental results demonstrate that the improved model achieves a detection accuracy of 95.4%, a recall rate of 85.0%, mAP@0.5 of 91.5%, and an F1 score of 90.0% on the test set, which are 0.7%, 3.5%, 1.3%, and 2. The model demonstrated a 4% increase in accuracy compared to the baseline model YOLOv11n, with a single-frame inference time of 0.6 milliseconds. The model exhibited significant robustness in scenarios with dense fruits, leaf occlusion, and backlighting, validating the synergistic enhancement of staged convolution optimization and hybrid attention mechanisms. This solution offers a means to automate the monitoring of orchards, achieving a balance between accuracy and real-time performance. Full article

As an essential part of terrestrial ecosystems, forests are key to sustaining ecological balance, supporting the carbon cycle, and offering various ecosystem services. In recent years, forests in Southwest China have experienced notable greening. However, the rising occurrence and severity of droughts present a significant threat to the stability of forest ecosystems in this region. This study adopted the near-infrared reflectance of vegetation (NIRv) and the lag-1 autocorrelation of NIRv as indicators to assess the dynamics and resilience of forests in Southwest China. We identified a progressive decline in forest resilience since 2008 despite a dominant greening trend in Southwest China’s forests during the last 20 years. By developing the eXtreme Gradient Boosting (XGBoost) model and Shapley additive explanation framework (SHAP), we classified forests in Southwest China into coniferous and broadleaf types to evaluate the driving factors influencing changes in forest resilience and mapped the spatial distribution of dominant drivers. The results showed that the resilience of coniferous forests was mainly driven by variations in elevation and land surface temperature (LST), with mean absolute SHAP values of 0.045 and 0.038, respectively. In contrast, the resilience of broadleaf forests was primarily influenced by changes in photosynthetically active radiation (PAR) and soil moisture (SM), with mean absolute SHAP values of 0.032 and 0.028, respectively. Regions where elevation and LST were identified as dominant drivers were mainly distributed in coniferous forest areas across central, eastern, and northern Yunnan Province as well as western Sichuan Province, accounting for 32.9% and 20.0% of the coniferous forest area, respectively. Meanwhile, areas where PAR and SM were dominant drivers were mainly located in broadleaf forest regions in Sichuan and eastern Guizhou, accounting for 29.9% and 27.7% of the broadleaf forest area, respectively. Our study revealed that the forest greening does not necessarily accompany an enhancement in resilience in Southwest China, identifying the driving factors behind the decline in forest resilience and highlighting the necessity of differentiated restoration strategies for forest ecosystems in this region. Full article

In distribution networks, energy storage serves as a crucial means to mitigate power fluctuations from renewable energy sources. However, due to its high cost, energy storage remains a resource whose large-scale adoption in power systems faces significant challenges. In recent years, the emergence of shared energy storage business models has provided new opportunities for the efficient operation of multi-distribution networks. Nevertheless, distribution network operators and shared energy storage operators belong to different stakeholders, and traditional centralized scheduling strategies suffer from issues such as privacy leakage and overly conservative decision-making. To address these challenges, this paper proposes a Nash bargaining game-based optimal energy management and trading strategy for multi-distribution networks with shared energy storage. First, we establish optimal scheduling models for active distribution networks (ADNs) and shared energy storage operators, respectively, and then develop a cooperative scheduling model aimed at maximizing collaborative benefits. The interactive variables—power exchange and electricity prices between distribution networks and shared energy storage operators—are iteratively solved using the Alternating Direction Method of Multipliers (ADMM). Finally, case studies based on modified IEEE-33 test systems validate the effectiveness and feasibility of the proposed method. The results demonstrate that the presented approach significantly outperforms conventional centralized optimization and distributed robust techniques, achieving a maximum improvement of 3.6% in renewable energy utilization efficiency and an 11.2% reduction in operational expenses. While maintaining computational performance on par with centralized methods, it effectively addresses data privacy concerns. Furthermore, the proposed strategy enables a substantial decrease in load curtailment, with reductions reaching as high as 63.7%. Full article

Photosynthetically Active Radiation (PAR) is critical for sustaining plant growth in the ground and on building surfaces, but how to accurately predict PAR availability in a complex urban environment can be a challenge. Using an advanced ray-tracing software (Radiance 4.0) and local weather data, this study presents a dynamic analysis of the effects of layout, façade orientation and height on PAR availability in four high density residential areas in Shanghai city, China. A metric system was also adopted using three light level requirements of outdoor plants (low, medium, high light levels). Key findings included: (1) the urban layout with the highest ratio of building height to north–south facing adjacent building separation achieved the higher levels of PAR availability for low/medium light level plants and the lower levels of PAR availability for high-light plants for middle and low façades and the ground, while high façades in all layouts could see similar PAR availability for all plants. (2) The PAR availability for low/medium-light plants decreased with the increasing façade height, while the PAR availability for high-light plants showed the opposite trend. (3) The north façade and its ground had higher levels of PAR availability for low/medium-light plants and lower levels of PAR availability for high-light plants than other façades. (4) All layouts offered more opportunities to apply high-light and medium-light plants at façades and the ground. Full article

Photosynthetically active radiation (PAR) is crucial for plant growth, influencing photosynthesis efficiency and crop yield. The increasing adoption of controlled-environment agriculture (CEA) necessitates precise PAR monitoring. The high cost of commercial PAR sensors, however, limits their accessibility and widespread use, creating a growing need for a low-cost alternative capable of reliable deployment in diverse agricultural environments. Building on recent advancements in PAR sensing using multi-channel spectral sensors such as the AS7341 and AS7265, this study develops the electronics for an AS7341-based, open-source, cost-effective (~USD 50) PAR sensor validated across a broad PPFD range and conditions, ensuring reliability and ease of replication. It uses a relatively simple multi-linear regression that offers real-time applications without energy intensive machine learning. The developed sensor is calibrated against the industry-standard Apogee SQ-500SS PAR sensor in four distinct farming environments: (i) horizontal grow lights, (ii) vertical agrotunnel lighting, (iii) agrivoltaics, and (iv) in greenhouses. A mean error ranging from 1 to 5% indicates its suitability for controlled environment farming and continuous data logging. The open-source hardware design and systematic installation guidelines enable users to replicate, calibrate, and integrate the sensor with minimal background in electronics and optics. Full article

Chronic kidney disease (CKD) remains a significant global health burden, often diagnosed at advanced stages due to the limitations of traditional biomarkers such as serum creatinine and estimated glomerular filtration rate (eGFR). This review aims to critically evaluate recent advancements in novel biomarkers, multi-omics technologies, and artificial intelligence (AI)-driven diagnostic strategies, specifically addressing existing gaps in early CKD detection and personalized patient management. We specifically explore key advancements in CKD diagnostics, focusing on emerging biomarkers—including neutrophil gelatinase-associated lipocalin (NGAL), kidney injury molecule-1 (KIM-1), soluble urokinase plasminogen activator receptor (suPAR), and cystatin C—and their clinical applications. Additionally, multi-omics approaches integrating genomics, proteomics, metabolomics, and transcriptomics are reshaping disease classification and prognosis. Artificial intelligence (AI)-driven predictive models further enhance diagnostic accuracy, enabling real-time risk assessment and treatment optimization. Despite these innovations, challenges remain in biomarker standardization, large-scale validation, and integration into clinical practice. Future research should focus on refining multi-biomarker panels, improving assay standardization, and facilitating the clinical adoption of precision-driven diagnostics. By leveraging these advancements, CKD diagnostics can transition toward earlier intervention, individualized therapy, and improved patient outcomes. Full article

Habitat suitability assessment for forest and grassland ecosystems is a critical component of ecological restoration and land use planning in the Loess Plateau, aiming to advance soil and water conservation and foster sustainable ecological environment development. Despite progress in vegetation restoration, systematic evaluations of habitat suitability in complex geomorphic regions like the Loess Plateau remain scarce, particularly in balancing hydrological and ecological trade-offs. The Yanhe River Basin (7725 km²), a sediment-prone tributary of the Yellow River, exemplifies the challenges of soil erosion and semi-arid climatic constraints, making it a critical case for evaluating restoration strategies. This study employed a comprehensive approach utilizing Analytic Hierarchy Process (AHP), Geographic Detector, mathematical statistics, and other methods. An evaluation indicator system and methodology were established to assess the suitability of forest and grassland habitats in the Yanhe River Basin, evaluating the suitability and quality improvement potential under the current land use conditions. The results indicate: (1) The dominant factors influencing the suitable distribution of forests include photosynthetically active radiation (PAR), soil total phosphorus content, annual precipitation, and elevation. For grasslands, the dominant factors include photosynthetically active radiation, annual average temperature, elevation, and annual precipitation. (2) In the watershed, forestland and grassland areas classified as moderately suitable or higher cover 1064.9 km² and 4196.9 km², accounting for 91.9% and 94.7% of their total respective areas, indicating a generally rational spatial allocation of forest and grassland ecosystems. (3) The improvable area for forests measures 366 km² (34.4% of moderately or higher suitability zones), with most already meeting coverage thresholds. In contrast, grasslands have an improvable area of 2491.6 km² (59.4% of moderately or higher suitability zones), where over half of the area remains below coverage thresholds corresponding to their habitat conditions. (4) Forests can adopt natural restoration-focused low-intensity interventions through strengthened closure management, while grasslands require spatially tailored measures—such as precipitation interception and enhanced stewardship—targeting suitability-based potential grades, collectively achieving overall improvement in grassland vegetation coverage. This study represents the first systematic evaluation of forest–grassland habitat suitability in the Yanhe River Basin, elucidating its spatial distribution patterns and providing critical insights for watershed-scale ecological restoration. Full article

This paper proposes ParDP, an algorithm and concrete tool for unsupervised clustering, which belongs to the class of density peaks-based clustering methods. Such methods rely on the observation that cluster representative points (centroids) are points of higher local density surrounded by points of lesser density. Candidate centroids, though, are to be far from each other. A key factor of ParDP is adopting a k-Nearest Neighbors (kNN) technique for estimating the density of points. Complete clustering depends on densities and distances among points. ParDP uses principal component analysis to cope with high-dimensional data points. The current implementation relies on Java parallel streams and the built-in lock-free fork/join mechanism, enabling the exploitation of the computing power of commodity multi/many-core machines. This paper demonstrates ParDP’s clustering capabilities by applying it to several benchmark and real-world datasets. ParDP’s operation can either be directed to observe the number of clusters in a dataset or to finalize clustering with an assigned number of clusters. Different internal and external measures can be used to assess the accuracy of a resultant clustering solution. Full article

To investigate the light and temperature environmental parameters of photovoltaic greenhouses in tropical areas, this study adopted experimental measurement and simulation methods to test and simulate the photosynthetically active radiation (PAR), relative temperature and humidity, and other environmental parameters inside and outside two types of serrated photovoltaic greenhouses in Langheng Village, Yangpu, Hainan. The study aimed to explore the distribution laws of PAR, light transmission rates, and relative humidity and temperature inside and outside double-slope and single-slope photovoltaic greenhouses. The ridges of both types of greenhouses run east to west, with photovoltaic panels arranged on the south-facing slopes, covering 57% of the area. The results show the following: (1) The trends of PAR inside and outside both types of photovoltaic greenhouses were consistent across all seasons, with the annual average values were 164.98 μmol/(m²·s) for double-slope and 127.59 μmol/(m²·s) for single-slope; (2) The annual average light transmission rates were 23.91% for double-slope and 19.17% for single-slope; (3) The average indoor temperatures in both types of greenhouses were higher than outside in all seasons, with a temperature difference ranging between 1 and 3 °C; (4) The indoor relative humidity in both types of greenhouses was higher than outside, with the difference reaching up to 6% during summer and autumn; (5) The annual light transmission rates for both types of greenhouses were simulated using Design Builder. The simulation results were generally consistent with the measured values, with the simulated values being higher overall than the measured ones by an average difference within 5%. In summary, the average light transmission rate of the double-slope photovoltaic greenhouse was 4.74% higher that of the single-slope photovoltaic greenhouse and the PAR was 37.39 μmol/(m²·s) higher than the single-slope. Additionally, the average temperature in the double-slope greenhouse was slightly higher and the relative humidity was slightly lower than that in the single-slope greenhouse. Both types of greenhouses could meet the light, temperature, and humidity requirements for cultivating leafy vegetables in tropical areas. Except for the temperature parameters in summer, the performance of the double-slope photovoltaic greenhouse was also better. The Design Builder simulation results showed little difference to the actual measurements and their trends were also consistent. The light transmission rate of photovoltaic greenhouses can be simulated by setting the overall light transmission coefficient of the light-transmitting roofing materials. Full article

In order to solve the problem of large-scale offshore wind power consumption, the development of an offshore wind power hydrogen supply chain has become one of the trends. In this study, 10 feasible options are proposed to investigate the economics of an offshore wind hydrogen supply chain for offshore hydrogen refueling station consumption from three aspects: offshore wind hydrogen production, storage and transportation, and application. The study adopts a levelized cost analysis method to measure the current and future costs of the hydrogen supply chain. It analyses the suitable transport modes for delivering hydrogen to offshore hydrogen refueling stations at different scales and distances, as well as the profitability of offshore hydrogen refueling stations. The study draws the following key conclusions: (1) the current centralised wind power hydrogen production method is economically superior to the distributed method; (2) gas-hydrogen storage and transportation is still the most economical method at the current time, with a cost of CNY 32.14/kg, which decreases to CNY 13.52/kg in 2037, on a par with the cost of coal-based hydrogen production using carbon capture technology; and (3) at the boundaries of an operating load factor of 70% and a selling price of CNY 25/kg, the offshore hydrogen refueling station. The internal rate of return (IRR) is 21%, showing good profitability; (4) In terms of the choice of transport mode for supplying hydrogen to the offshore hydrogen refueling station, gas-hydrogen ships and pipeline transport will mainly be used in the near future, while liquid organic hydrogen carriers and synthetic ammonia ships can be considered in the medium to long term. Full article

The global electric vehicle (EV) market is experiencing exponential growth, driven by technological advancements, environmental awareness, and government incentives. As EV adoption accelerates, it introduces opportunities and challenges for power systems worldwide due to the large battery capacity, uncertain charging behaviors of EV users, and seasonal variations. This could result in significant peak–valley differences in load in featured time slots, particularly during winter periods when EVs’ heating systems use increases. This paper proposes three future charging strategies, namely the Overnight, Workplace/Other Charging Sites, and Overnight Workplace/Other Charging Sites, to reduce overall charging in peak periods. The charging strategies are based on predicted load utilizing a hybrid machine learning (ML) approach to reduce overall charging in peak periods. The hybrid ML method combines similar day selection, complete ensemble empirical mode decomposition with adaptive noise, and deep neural networks. The dataset utilized in this study was gathered from 1000 EVs across nine provinces in Canada between 2017 and 2019, encompassing charging loads for thirty-five vehicle models, and charging locations and levels. The analysis revealed that the aggregated charging power of EV fleets aligns and overlaps with the peak periods of residential buildings energy consumption. The proposed Overnight Workplace/Other Charging Sites strategy can significantly reduce the Peak-to-Average Ratio (PAR) and energy cost during the day by leveraging predictions made three days in advance. It showed that the PAR values were approximately half those on the predicted load profile (50% and 51%), while charging costs were reduced by 54% and 56% in spring and winter, respectively. The proposed strategies can be implemented using incentive programs to motivate EV owners to charge in the workplace and at home during off-peak times. Full article

Skin sensitisation is a critical adverse effect assessed to ensure the safety of compounds and materials exposed to the skin. Alongside the development of new approach methodologies (NAMs), defined approaches (DAs) have been established to promote skin sensitisation potency assessment by adopting and integrating standardised in vitro, in chemico, and in silico methods with specified data analysis procedures to achieve reliable and reproducible predictions. The incorporation of additional NAMs could help increase accessibility and flexibility. Using superior algorithms may help improve the accuracy of hazard and potency assessment and build confidence in the results. Here, we introduce two new DA models, with the aim to build DAs on freely available software and the newly developed kDPRA for covalent binding of a chemical to skin peptides and proteins. The new DA models are built on an existing Bayesian network (BN) modelling approach and expand on it. The new DA models include kDPRA data as one of the in vitro parameters and utilise in silico inputs from open-source QSAR models. Both approaches perform at least on par with the existing BN DA and show 63% and 68% accuracy when predicting four LLNA potency classes, respectively. We demonstrate the value of the Bayesian network’s confidence indications for predictions, as they provide a measure for differentiating between highly accurate and reliable predictions (accuracies up to 87%) in contrast to low-reliability predictions associated with inaccurate predictions. Full article

Particle-based Variational Inference (ParVI) methods have been widely adopted in deep Bayesian inference tasks such as Bayesian neural networks or Gaussian Processes, owing to their efficiency in generating high-quality samples given the score of the target distribution. Typically, ParVI methods evolve a weighted-particle system by approximating the first-order Wasserstein gradient flow to reduce the dissimilarity between the particle system’s empirical distribution and the target distribution. Recent advancements in ParVI have explored sophisticated gradient flows to obtain refined particle systems with either accelerated position updates or dynamic weight adjustments. In this paper, we introduce the semi-Hamiltonian gradient flow on a novel Information–Fisher–Rao space, known as the SHIFR flow, and propose the first ParVI framework that possesses both accelerated position update and dynamical weight adjustment simultaneously, named the General Accelerated Dynamic-Weight Particle-based Variational Inference (GAD-PVI) framework. GAD-PVI is compatible with different dissimilarities between the empirical distribution and the target distribution, as well as different approximation approaches to gradient flow. Moreover, when the appropriate dissimilarity is selected, GAD-PVI is also suitable for obtaining high-quality samples even when analytical scores cannot be obtained. Experiments conducted under both the score-based tasks and sample-based tasks demonstrate the faster convergence and reduced approximation error of GAD-PVI methods over the state-of-the-art. Full article

The superpixel usually serves as a region-level feature in various image processing tasks, and is known for segmentation accuracy, spatial compactness and running efficiency. However, since these properties are intrinsically incompatible, there is still a compromise within the overall performance of existing superpixel algorithms. In this work, the property constraint in superpixels is relaxed by in-depth understanding of the image content, and a novel two-stage superpixel generation framework is proposed to produce content-aware superpixels. In the global processing stage, a diffusion-based online average clustering framework is introduced to efficiently aggregate image pixels into multiple superpixel candidates according to color and spatial information. During this process, a centroid relocation strategy is established to dynamically guide the region updating. According to the area feature in manifold space, several superpixel centroids are then split or merged to optimize the regional representation of image content. Subsequently, local updating is adopted on pixels in those superpixel regions to further improve the performance. As a result, the dynamic centroid relocating strategy offers online averaging clustering the property of content awareness through coarse-to-fine label updating. Extensive experiments verify that the produced superpixels achieve desirable and comprehensive performance on boundary adherence, visual satisfactory and time consumption. The quantitative results are on par with existing state-of-the-art algorithms in terms with several common property metrics. Full article