Search Results (14,452)

In agricultural production, the nitrogen content of sugarcane is assessed with precision and the economy, which is crucial for balancing fertilizer application, reducing resource waste, and minimizing environmental pollution. As an important economic crop, the productivity of sugarcane is significantly influenced by various environmental factors, especially nitrogen supply. Traditional methods based on manually extracted image features are not only costly but are also limited in accuracy and generalization ability. To address these issues, a novel regression prediction model for estimating the nitrogen content of sugarcane, named SC-ResNeXt (Enhanced with Self-Attention, Spatial Attention, and Channel Attention for ResNeXt), has been proposed in this study. The Self-Attention (SA) mechanism and Convolutional Block Attention Module (CBAM) have been incorporated into the ResNeXt101 model to enhance the model’s focus on key image features and its information extraction capability. It was demonstrated that the SC-ResNeXt model achieved a test R² value of 93.49% in predicting the nitrogen content of sugarcane leaves. After introducing the SA and CBAM attention mechanisms, the prediction accuracy of the model improved by 4.02%. Compared with four classical deep learning algorithms, SC-ResNeXt exhibited superior regression prediction performance. This study utilized images captured by smartphones combined with automatic feature extraction and deep learning technologies, achieving precise and economical predictions of the nitrogen content in sugarcane compared to traditional laboratory chemical analysis methods. This approach offers an affordable technical solution for small farmers to optimize nitrogen management for sugarcane plants, potentially leading to yield improvements. Additionally, it supports the development of more intelligent farming practices by providing precise nitrogen content predictions. Full article

Driven by the growing demands for plant-based protein in Europe and attempts of soybean breeding programs to improve the productivity of created varieties, this study aimed to enhance genetic resource utilization efficiency by providing information relevant to well-focused breeding targets. A set of 90 accessions was subjected to a comprehensive assessment of genetic diversity in a soybean working collection using three marker types: morphological descriptors, agronomic traits, and SSRs. Genotype grouping patterns varied among the markers, displaying the best congruence with pedigree data and maturity for SSRs and agronomic traits, respectively. The clear origin-related grouping pattern was not observed for any of the marker types. For the diversity assessed by morphological descriptors, Homogeneity Analysis by Means of Alternating Least Squares (HOMALS) yielded the most efficient classification by identifying the traits with the highest discriminative power and separating the genotypes into homogeneous groups. According to genetic distances (GDs), the highest diversity was found for morphological descriptors (GD = 517), followed by SSRs (GD = 0.317) and agronomic traits (GD = 0.244). The analysis of molecular variance (AMOVA) revealed a weak differentiation between geographic groups (Φ_ST = 0.061), emphasizing the highest differentiation for Canadian genotypes (Φ_ST = 0.148 **). A low correlation was found between molecular and morphological, i.e., agronomic trait-based matrices (0.061 *, i.e., –0.027, respectively). The overall assessed diversity highlighted the importance of introducing new sources of variation to promote long-term improvement in soybean breeding. Full article

In this study, a general description of geothermal power plants is provided, and the optimization methods used are summarized. Following the review of these optimization methods, the advantages of heuristic methods and the success of the developed models are demonstrated. The challenges in optimizing geothermal systems, including the limitations due to their complexity and the use of multiple parameters, are discussed. Heuristic methods, particularly the widely used artificial neural networks and genetic algorithms, are explained in general terms. Recent studies highlight that the combined use of artificial neural networks and genetic algorithms can produce faster and more consistent results. This demonstrates the benefits of using advanced methods for geothermal resource utilization and power plant optimization. An innovative optimization method has been developed using the operational data of an ORC geothermal power plant in the city of Izmir. The computational method, using genetic algorithms with artificial neural networks as the fitness function, has identified the optimal operating conditions, achieving a 39.41% increase in net power output. The plant’s gross power generation has increased from 4943 kW to 6624 kW. Full article

The mining and processing of coal resources generate substantial coal-based solid wastes, such as coal gangue and slag, which pose environmental challenges, occupy land, and are difficult to manage. However, utilizing these wastes for the stabilization and solidification (S/S) of municipal sludge containing chromium (Cr) and nickel (Ni) offers an effective solution for mitigating environmental and groundwater pollution while enabling sustainable waste treatment and resource utilization. This study applied an alkali-activated coal gangue–S95 granulated blast furnace slag-based binder (CGS) to the S/S treatment of municipal sludge. The effects of the liquid-to-solid ratio, alkali activator dosage, sludge content, and incineration on compressive strength and the leaching of Cr and Ni were analyzed. The results showed that compressive strength decreased with increases in the sludge content and liquid-to-solid ratio, while incinerated sludge (ESA) samples exhibited better strength than raw sludge (ES). Incineration decomposed the calcite (CaCO₃) into CaO, which facilitated the oxidation of Cr(III) to Cr(VI) and increased Cr leaching in the ESA. However, the ESA samples demonstrated superior heavy metal stabilization, as CGS reduced Cr(VI) to Cr(III) and immobilized it through the formation of chromite phases. Using ESA as a binder in CGS provides a safe, efficient approach for resource recovery and heavy metal stabilization, offering a novel solution for the environmental management and utilization of coal-based solid wastes. Full article

Agricultural land resources are essential for food production, and thus it is vital to examine the spatiotemporal changes in these resources and their impacts on land suitability to optimize resource allocation. In this study, we investigated the spatial evolution of cropland resources through land use change analysis by utilizing four periods of land use data from 1990 to 2020 in the black soil region of northeast China (BSRNC). Employing niche theory, we developed a cultivability evaluation model tailored to the BSRNC, which was used to assess the impact of the spatial changes in cropland patterns over the past 30 years on land suitability. Our key findings are as follows: (1) Cropland resources have generally tended to expand in the BSRNC, with an increase of 7.16 × 10³ km² in the cultivated area and a northeastward shift in the cropland center by 52.94 km, indicating significant changes in the spatial configuration of the land. (2) The region’s cultivable land resources were substantial, covering 694.06 × 10³ km², or 55.78% of the total area, with notable spatial variability, influenced by the regional climate and topography. (3) The land cultivability has slightly improved, as shown by a 0.10 increase in the cultivability index, but a significant declining trend in the cultivability of cropland was observed after 2000. Our findings provide valuable insights to help accurately assess land productivity in the BSRNC and facilitate the sustainable use and conservation of black soil. Full article

With the continuous development of animal husbandry, the harmless handling and resource utilization of livestock manure has gradually become a bottleneck problem in sustainable agriculture and livestock production in China. This study evaluates the policies related to manure handling and utilization in different economic development periods in China. The decreased pollutant discharge from livestock manure indicates the effectiveness of the strategy aiming to encourage the construction of manure treatment facilities and resource utilization in cropland and to establish a sound legal system for pollutant discharge. New policies and measures should be introduced to promote the coupling of intensive livestock breeding and crop planting, with the direction of nutrient management planning and the incorporation of a service platform for the resource utilization of manure. Technological innovation in green livestock breeding should be supported by policies to achieve source reduction in pollutants in breeding waste. Full article

Recently, convolutional neural networks (CNNs) have received a massive amount of interest due to their ability to achieve high accuracy in various artificial intelligence tasks. With the development of complex CNN models, a significant drawback is their high computational burden and memory requirements. The performance of a typical CNN model can be enhanced by the improvement of hardware accelerators. Practical implementations on field-programmable gate arrays (FPGA) have the potential to reduce resource utilization while maintaining low power consumption. Nevertheless, when implementing complex CNN models on FPGAs, these may may require further computational and memory capacities, exceeding the available capacity provided by many current FPGAs. An effective solution to this issue is to use quantized neural network (QNN) models to remove the burden of full-precision weights and activations. This article proposes an accelerator design framework for FPGAs, called FPGA-QNN, with a particular value in reducing high computational burden and memory requirements when implementing CNNs. To approach this goal, FPGA-QNN exploits the basics of quantized neural network (QNN) models by converting the high burden of full-precision weights and activations into integer operations. The FPGA-QNN framework comes up with 12 accelerators based on multi-layer perceptron (MLP) and LeNet CNN models, each of which is associated with a specific combination of quantization and folding. The outputs from the performance evaluations on Xilinx PYNQ Z1 development board proved the superiority of FPGA-QNN in terms of resource utilization and energy efficiency in comparison to several recent approaches. The proposed MLP model classified the FashionMNIST dataset at a speed of 953 kFPS with 1019 GOPs while consuming 2.05 W. Full article

Manual labeling of lesions in medical image analysis presents a significant challenge due to its labor-intensive and inefficient nature, which ultimately strains essential medical resources and impedes the advancement of computer-aided diagnosis. This paper introduces a novel medical image-segmentation framework named Efficient Generative-Adversarial U-Net (EGAUNet), designed to facilitate rapid and accurate multi-organ labeling. To enhance the model’s capability to comprehend spatial information, we propose the Global Spatial-Channel Attention Mechanism (GSCA). This mechanism enables the model to concentrate more effectively on regions of interest. Additionally, we have integrated Efficient Mapping Convolutional Blocks (EMCB) into the feature-learning process, allowing for the extraction of multi-scale spatial information and the adjustment of feature map channels through optimized weight values. Moreover, the proposed framework progressively enhances its performance by utilizing a generative-adversarial learning strategy, which contributes to improvements in segmentation accuracy. Consequently, EGAUNet demonstrates exemplary segmentation performance on public multi-organ datasets while maintaining high efficiency. For instance, in evaluations on the CHAOS T2SPIR dataset, EGAUNet achieves approximately $2\%$ higher performance on the Jaccard metric, $1\%$ higher on the Dice metric, and nearly $3\%$ higher on the precision metric in comparison to advanced networks such as Swin-Unet and TransUnet. Full article

Northeast China (NEC) is a major spring maize (Zea mays L.) growing belt, and the outputs substantially influence national grain production. However, the maize grain yield per unit area has little changes in recent years, partially due to the lack of elite germplasm resources and innovation. Therefore, this study aimed to determine the performance of diverse populations in NEC to propose appropriate strategies for the utilization of elite germplasm to broaden the genetic base of Chinese germplasm. Fifteen diverse maize populations from the International Maize and Wheat Improvement Center (CIMMYT) and the U.S. were crossed to two local tester lines, representing Chinese heterotic groups Reid and Lancaster, for evaluating the combining ability and heterosis in three locations (Gongzhuling, Jilin Province, and Harbin and Suihua, Heilongjiang Province) in NEC over two years. The U.S. (BS13(S)C7 and BS31) and Chinese (Ji Syn A) populations exhibited more favorable alleles for high yield potential in all locations tested. Furthermore, the PH6WC × BS31 and PH6WC × Ji Syn A crosses had higher grain yields, and an appropriate number of days to silking, ear height, and resistance to lodging at Gongzhuling and Harbin in NEC. The best strategies for utilizing these diverse germplasms may be to develop new inbred lines from the existing elite populations or improve the grain yield and resistance to lodging of the elite line PH4CV for broadening the genetic base of the Chinese group Lancaster in NEC. Full article

Against the backdrop of the global goal of “carbon neutrality”, the advancement of electric vehicles (EVs) holds substantial importance for diminishing the reliance on fossil fuels, mitigating vehicular emissions, and fostering the transition of the automotive sector towards a sustainable, low-carbon paradigm. The wide application of electric vehicles not only reduces the dependence on non-renewable resources such as oil, but also concurrently effectuates a substantial reduction in carbon emissions within the transportation sector. In the realm of electric vehicles, ternary lithium batteries (NCM) and lithium iron phosphate batteries (LFP) are two widely used batteries. This study examines the resource utilization and environmental repercussions associated with the production of 1 kW ternary lithium batteries and lithium iron phosphate batteries, employing a life cycle assessment (LCA) framework. The importance of clean energy in reducing environmental pollution and global warming potential is revealed by introducing five different power generation types and the regional power generation structure in China into the power battery production process. The findings of the investigation indicate that lithium iron phosphate batteries exhibit pronounced superiority in terms of environmental sustainability, while ternary lithium batteries are more advantageous in terms of performance. The mitigation of environmental pollution associated with battery production can be significantly achieved by the holistic integration of clean energy sources and the systematic optimization of manufacturing processes. Specific interventions encompass enhancing the energy efficiency of the production process, incorporating renewable energy sources for power generation, and minimizing the utilization of hazardous materials. By implementing these strategies, the battery sector can advance towards a more environmentally benign and sustainable trajectory. Full article

This study deeply examines the livable environment in high-density cities like Macau, focusing on urban green spaces. The study introduces the “urban spatial naturalness degree” indicator, exploring its application with urban population growth and green space expansion. The research utilizes the planning indicator of “urban spatial naturalness degree”, and then explores the application paradigm of matching increments between urban population growth and green open space and a bottom-line planning indicator suitable for Macau. Among them, the “USND” indicator is defined as “the visual perception rate of blue and green natural elements in the three-dimensional space of urban land”, which is specifically expressed as “the average function of the occupation rate of urban green open space and the visibility rate of blue–green space of main street scenes”. Based on this, this paper estimates the incremental planning indicators of green open space in Macau and various urban areas during the implementation of the Master Plan of Macau (2020–2040). The results show the following: (1) The study found that the land increment in green open space in Macau basically matches the potential of reserve resources. (2) For Class I and Class II urban areas in Macau, the USND value is estimated to be 42.96% and 32.62% in 2040, respectively. These values are expected to reach the international excellent level. (3) For Class III and Class IV urban areas, the USND values could reach 20.14% and 15.14%, respectively, which are considered to be at the international middle level in 2040. Full article

The automotive industry is under increasing pressure to develop cleaner and more efficient technologies in response to stringent emission regulations. Hydrogen-powered internal combustion engines represent a promising alternative, offering the potential to reduce carbon-based emissions while improving efficiency. However, the accurate estimation of in-cylinder pressure is crucial for optimizing the performance and emissions of these engines. While traditional simulation tools such as GT-POWER are widely utilized for these purposes, recent advancements in artificial intelligence provide new opportunities for achieving faster and more accurate predictions. This study presents a comparative evaluation of the predictive capabilities of GT-POWER and an artificial neural network model in estimating in-cylinder pressure, with a particular focus on improvements in computational efficiency. Additionally, the artificial neural network is employed to predict the equivalent flame radius, thereby obviating the need for repeated tests using dedicated high-speed cameras in optical access research engines, due to the resource-intensive nature of data acquisition and post-processing. Experiments were conducted on a single-cylinder research engine operating at low-speed and low-load conditions, across three distinct relative air–fuel ratio values with a range of ignition timing settings applied for each air excess coefficient. The findings demonstrate that the artificial neural network model surpasses GT-POWER in predicting in-cylinder pressure with higher accuracy, achieving an RMSE consistently below 0.44% across various conditions. In comparison, GT-POWER exhibits an RMSE ranging from 0.92% to 1.57%. Additionally, the neural network effectively estimates the equivalent flame radius, maintaining an RMSE of less than 3%, ranging from 2.21% to 2.90%. This underscores the potential of artificial neural network-based approaches to not only significantly reduce computational time but also enhance predictive precision. Furthermore, this methodology could subsequently be applied to conventional road engines exhibiting characteristics and performance similar to those of a specific optical engine used as the basis for the machine learning analysis, offering a practical advantage in real-time diagnostics. Full article

The detection of highly toxic chemicals such as phosgene is crucial for addressing the severe threats to human health and public safety posed by terrorist attacks and industrial mishaps. However, timely and precise monitoring of phosgene at a low cost remains a significant challenge. This work is the first to report a novel fluorescent system based on the Intramolecular Charge Transfer (ICT) effect, which can rapidly detect phosgene in both solution and gas phases with high sensitivity by integrating a benzo[1,2-b:6,5-b’]dithiophene-4,5-diamine (BDTA) probe. Among existing detecting methods, this fluorescent system stands out as it can respond to phosgene within a mere 30 s and has a detection limit as low as 0.16 μM in solution. Furthermore, the sensing mechanism was rigorously validated through high-resolution mass spectrometry (HRMS) and density functional theory (DFT) calculations. As a result, this fluorescent probing system for phosgene can be effectively adapted for real-time, high-sensitivity sensing and used as a test strip for visual monitoring without the need for specific equipment, which will also provide a new strategy for the fluorescent detection of other toxic materials. Full article

Digital twin (DT) technology has become a cornerstone in the simulation and analysis of real-world systems, offering unparalleled insights into the lifecycle management of physical assets. By providing a real-time synchronized replica of the physical entity, DTs enable predictive maintenance, performance optimization, and lifecycle extension, which are pivotal for industries aiming for digital transformation. This paper presents a comprehensive comparative study of DT development of a robotic arm using two prominent simulation platforms: Unity and Gazebo. Unity, with its roots in the gaming industry, offers robust real-time rendering and a user-friendly interface, making it a versatile choice for various industries. Gazebo, traditionally used in robotics, provides detailed physics simulations and sensor data emulation, which is ideal for precise engineering applications. We explored the performance of both platforms in creating accurate and dynamic digital replicas. Through qualitative and quantitative analyses, this study evaluates each platform’s strengths and limitations. The study assesses these platforms across key performance metrics such as accuracy, latency, graphic quality, and integration with the Robot Operating System (ROS). The DTs were developed using a consistent physical setup and communication layer to ensure fair comparisons. The results indicate that Unity performed better in terms of accurately mimicking the robotic arm with lower latency, making it ideal for applications requiring high-fidelity visualizations and real-time responsiveness. However, Gazebo excels in its ease of ROS integration and cost-effectiveness, making it a suitable choice for smaller robotics and automation projects. This study conducts an empirical comparison of these platforms in terms of their performance in creating DTs of robotic arms which is not readily available. This paper aims to guide developers and organizations in selecting the appropriate platform for their DT initiatives, ensuring efficient resource utilization and optimal outcomes. Full article

Background: Obstructive Sleep Apnea (OSA) is a prevalent sleep disorder characterized by intermittent upper airway obstruction, leading to significant health consequences. Traditional diagnostic methods, such as polysomnography, are time-consuming and resource-intensive. Objectives: This study explores the potential of proton-transfer-reaction mass spectrometry (PTR-MS) in identifying volatile organic compound (VOC) biomarkers for the non-invasive detection of OSA. Methods: Breath samples from 89 participants, including 49 OSA patients and 40 controls, were analyzed using PTR-MS. Significance analysis was performed between OSA patients and controls to identify potential biomarkers for OSA. To as-sess the differences in VOC concentrations between OSA patients and control subjects,the Wilcoxon rank-sum test was employed. partial least squares discriminant analysis (PLS-DA) analysis and heatmap plot was conducted to visualize the differentiation between OSA patients and control subjects based on their VOC profiles.In order to further investigate the correlation between identified biomarkers and the severity of OSA measured by Apnea–Hypopnea Index (AHI), regression analysis was conducted between biomarkers and AHI Index. Results: The results identified specific VOCs, including m045 (acetaldehyde), m095.950, and m097.071, which showed significant differences between OSA patients and controls. Advanced statistical analyses, including PLS-DA and correlation mapping, highlighted the robustness of these biomarkers, with m045 (acetaldehyde) specifically emerging as a potential biomarker associated with the AHI Index. Conclusions: This study underscores the potential of VOCs as biomarkers for identifying patients with severe AHI levels. The analysis of VOCs using PTR-MS presents a rapid, non-invasive, and cost-effective method that could be seamlessly integrated into clinical practice, allowing clinicians to better stratify patients based on their need for polysomnography and prioritize those requiring earlier testing. Future studies are necessary to validate these findings in larger cohorts and to explore the integration of PTR-MS with other diagnostic modalities for improved accuracy and clinical utility. Full article