Search Results (61,124)

Accurate and timely estimation of soybean emergence at the plot scale using unmanned aerial vehicle (UAV) remote sensing imagery is essential for germplasm evaluation in breeding programs, where breeders prioritize overall plot-scale emergence rates over subimage-based counts. This study proposes PlotCounter, a deep learning regression model based on the TasselNetV2++ architecture, designed for plot-scale soybean seedling counting. It employs a patch-based training strategy combined with full-plot validation to achieve reliable performance with limited breeding plot data. To incorporate additional agronomic information, PlotCounter is extended into a multitask learning framework (MTL-PlotCounter) that integrates sowing metadata such as variety, number of seeds per hole, and sowing density as auxiliary classification tasks. RGB images of 54 breeding plots were captured in 2023 using a DJI Mavic 2 Pro UAV and processed into an orthomosaic for model development and evaluation, showing effective performance. PlotCounter achieves a root mean square error (RMSE) of 6.98 and a relative RMSE (rRMSE) of 6.93%. The variety-integrated MTL-PlotCounter, V-MTL-PlotCounter, performs the best, with relative reductions of 8.74% in RMSE and 3.03% in rRMSE compared to PlotCounter, and outperforms representative YOLO-based models. Additionally, both PlotCounter and V-MTL-PlotCounter are deployed on a web-based platform, enabling users to upload images via an interactive interface, automatically count seedlings, and analyze plot-scale emergence, powered by a multimodal large language model. This study highlights the potential of integrating UAV remote sensing, agronomic metadata, specialized deep learning models, and multimodal large language models for advanced crop monitoring. Full article

The synthesis of “green ammonia” from “green hydrogen” represents a critical pathway for renewable energy integration and industrial decarbonization. This study investigates the green ammonia synthesis process using an axial–radial fixed-bed reactor equipped with three catalyst layers. A simplified two-dimensional physical model was developed, and a multiscale simulation approach combining computational fluid dynamics (CFD) with physics-informed neural networks (PINNs) employed. The simulation results demonstrate that the majority of fluid flows axially through the catalyst beds, leading to significantly higher temperatures in the upper bed regions. The reactor exhibits excellent heat exchange performance, ensuring effective preheating of the feed gas. High-pressure zones are concentrated near the top and bottom gas outlets, while the ammonia mole fraction approaches 100% near the bottom outlet, confirming superior conversion efficiency. By integrating PINNs, the prediction accuracy was substantially improved, with flow field errors in the catalyst beds below 4.5% and ammonia concentration prediction accuracy above 97.2%. Key reaction kinetic parameters (pre-exponential factor k₀ and activation energy Ea) were successfully inverted with errors within 7%, while computational efficiency increased by 200 times compared to traditional CFD. The proposed CFD–PINN integrated framework provides a high-fidelity and computationally efficient simulation tool for green ammonia reactor design, particularly suitable for scenarios with fluctuating hydrogen supply. The reactor design reduces energy per unit ammonia and improves conversion efficiency. Its radial flow configuration enhances operational stability by damping feed fluctuations, thereby accelerating green hydrogen adoption. By reducing fossil fuel dependence, it promotes industrial decarbonization. Full article

With the diversification of information retrieval methods, news retrieval tasks have gradually evolved towards multimodal retrieval. Existing methods often encounter issues such as inaccurate alignment and unstable feature matching when handling cross-modal data like text and images, limiting retrieval performance. To address this, this paper proposes an innovative multimodal news retrieval method by introducing the Learnable Alignment Module (LAM), which establishes a learnable alignment relationship between text and images to improve the accuracy and stability of cross-modal retrieval. Specifically, the LAM, through trainable label embeddings (TLEs), enables the text encoder to dynamically adjust category information during training, thereby enhancing the alignment capability of text and images in the shared embedding space. Additionally, we propose three key alignment strategies: logits calibration, parameter consistency, and semantic feature matching, to further optimize the model’s multimodal learning ability. Extensive experiments conducted on four public datasets—Visual News, MMED, N24News, and EDIS—demonstrate that the proposed method outperforms existing state-of-the-art approaches in both text and image retrieval tasks. Notably, the method achieves significant improvements in low-recall scenarios (R@1): for text retrieval, R@1 reaches 47.34, 44.94, 16.47, and 19.23, respectively; for image retrieval, R@1 achieves 40.30, 38.49, 9.86, and 17.95, validating the effectiveness and robustness of the proposed method in multimodal news retrieval. Full article

For mineral exploration, an increasing number of geophysical instruments have adopted unmanned aerial vehicles (UAVs) as their carrier platforms. The effective fusion of multi-modal geophysical information will be conducive to further enhancing the reliability of exploration results. However, the integration degree of UAVs and geophysical equipment is still low, and the advantages of UAVs as robots have not been fully exploited. In addition, the existing fusion methods are still difficult to use to establish the spatial distribution model of ore-bearing rock. Therefore, we reviewed the development status of UAVs and the geophysical instruments. We believe that only by integrating the system, designing the observation plan in accordance with the requirements of the fusion method, and treating the hardware part as an external extension of the algorithm, can high-matching data be provided for fusion. Subsequently, we analyzed the progress of the fusion methods, leading us to believe that the cross-dimensional and cross-abstract-level issues are major challenges in the algorithm aspect. Meanwhile, the fusion should be carried out simultaneously with the generation of the ore-bearing rock model, that is, to establish an integrated system of fusion and generation. It is hoped that this research can promote the development of UAV-borne multi-modal observation technology. Full article

Accurate prediction of airport delays under convective weather conditions is essential for effective traffic coordination and improving overall airport efficiency. Traditional methods mainly rely on numerical weather and traffic indicators, but they often fail to capture the spatial distribution of traffic flows within the terminal area. To address this limitation, we propose a novel image-based representation named Multi-Channel Traffic and Weather Scene Image (MTWSI), which maps both meteorological and traffic information onto a two-dimensional airspace grid, thereby preserving spatial relationships. Based on the MTWSI, we develop a delay prediction model named ADLCNN. This model first uses a convolutional neural network to extract deep spatial features from the scene images and then classifies each sample into a delay level. Using real operational data from Guangzhou Baiyun Airport, this paper shows that ADLCNN achieves significantly higher prediction accuracy compared to traditional machine learning methods. The results confirm that MTWSI provides a more accurate representation of real traffic conditions under convective weather. Full article

Knowledge-graph-based recommendation aims to provide personalized recommendation services to users based on their historical interaction information, which is of great significance for shopping transaction rates and other aspects. With the rapid growth of online shopping, the knowledge graph constructed from users’ historical interaction data now incorporates multiattribute information, including timestamps, images, and textual content. The information of multiple modalities is difficult to effectively utilize due to their different representation structures and spaces. The existing methods attempt to utilize the above information through simple embedding representation and aggregation, but ignore targeted representation learning for information with different attributes and learning effective weights for aggregation. In addition, existing methods are not sufficient for effectively modeling temporal information. In this article, we propose MTR, a knowledge graph recommendation framework based on mixture of experts network. To achieve this goal, we use a mixture-of-experts network to learn targeted representations and weights of different product attributes for effective modeling and utilization. In addition, we effectively model the temporal information during the user shopping process. A thorough experimental study on popular benchmarks validates that MTR can achieve competitive results. Full article

In intelligent vehicular networks, the accuracy of semantic segmentation in road scenes is crucial for vehicle-mounted artificial intelligence to achieve environmental perception, decision support, and safety control. Although deep learning methods have made significant progress, two main challenges remain: first, the difficulty in balancing global and local features leads to blurred object boundaries and misclassification; second, conventional convolutions have limited ability to perceive irregular objects, causing information loss and affecting segmentation accuracy. To address these issues, this paper proposes a global–local collaborative attention module and a spider web convolution module. The former enhances feature representation through bidirectional feature interaction and dynamic weight allocation, reducing false positives and missed detections. The latter introduces an asymmetric sampling topology and six-directional receptive field paths to effectively improve the recognition of irregular objects. Experiments on the Cityscapes, CamVid, and BDD100K datasets, collected using vehicle-mounted cameras, demonstrate that the proposed method performs excellently across multiple evaluation metrics, including mIoU, mRecall, mPrecision, and mAccuracy. Comparative experiments with classical segmentation networks, attention mechanisms, and convolution modules validate the effectiveness of the proposed approach. The proposed method demonstrates outstanding performance in sensor-based semantic segmentation tasks and is well-suited for environmental perception systems in autonomous driving. Full article

The use of informal language on social media and the sheer volume of information make it difficult for a computer system to analyse it automatically. The aim of this work is to design a new group decision-making method that applies two new consensus methods based on sentiment analysis. This method is designed for application in the analysis of texts on social media. To test the method, we will use posts from the so called social network X. The proposed model differs from previous work in this field by defining a new degree of subjectivity and a new degree of reliability associated with user opinions. This work also presents two new consensus measures, one focused on measuring the number of words classified as positive and negative and the other on analysing the percentage of occurrence of those words. Our method allows us to automatically extract preferences from the transcription of the texts used in the debate, avoiding the need for users to explicitly indicate their preferences. The application to a real case of public investment demonstrates the effectiveness of the approach in collaborative contexts that used natural language. Full article

This paper presents the multi-triangular ring and self-routing protocol (MTRSRP), which is a new decentralized strategy designed to boost throughput and network efficiency in multiring scatternets. MTRSRP comprises two primary phases: leader election and scatternet formation, which collaborate to establish an effective multi-triangular ring topology. In the leader election phase, nodes exchange broadcast messages to gather neighbor information and elect coordinators through a competitive process. The scatternet formation phase determines the optimal number of rings based on the coordinator’s collected node information and predefined rules. The master nodes then send unicast connection requests to establish piconets within the scatternet, following a predefined role table. Intra- and inter-bridge nodes were activated to interconnect the piconets, creating a cohesive multi-triangular ring scatternet. Additionally, MTRSRP incorporates a self-routing addressing scheme within the triangular ring architecture, optimizing packet transmission paths and reducing overhead by utilizing master/slave relationships established during scatternet formation. Simulation results indicate that MTRSRP with dual-bridge connectivity outperforms the cluster-based on-demand routing protocol and Bluetooth low-energy mesh schemes in key network transmission performance metrics such as the transmission rate, packet delay, and delivery ratio. In summary, MTRSRP significantly enhances throughput, optimizes routing paths, and improves network efficiency in multi-ring scatternets through its multi-triangular ring topology and self-routing capabilities. Full article

Virginia’s coastal location and abundant marine resources make its seafood industry a vital contributor to the state’s economy, supporting both local communities and tourism. This study applied input–output models and updates the economic contributions of the Virginia seafood industry using 2023 data, building on models developed for 2019 that capture both direct effects and broader economic ripple effects. In 2023, the industry generated USD 1.27 billion in total economic output and supported over 6500 jobs—including watermen, aquaculture farmers, processors, and distributors—resulting in USD 238.3 million in labor income. Contributions to state GDP totaled USD 976.7 million, and tax revenues exceeded USD 390.4 million. The study also evaluates the economic role of Virginia seafood products sold in retail stores and restaurants, based on secondary data sources. In 2023, these sectors generated USD 458 million in economic output, supported more than 3600 jobs, produced USD 136.7 million in labor income, and USD 280.8 million in value-added. Combined tax contributions surpassed USD 74 million. Importantly, the analysis results for the Virginia seafood products from retail and restaurant should not be summed to the seafood industry totals to avoid double-counting, as seafood products move as output from one sector as an input to another. These results provide evidence-based insights to guide decision-making, inform stakeholders, and support continued investment in Virginia’s seafood supply chain and related economic activities. Full article

According to the United Nations Environment Programme reports, buildings are responsible for nearly 40% of energy-related emissions; therefore, energy-optimized building design is crucial to reduce the reliance on non-renewable energy sources as well as greenhouse gas emissions. The OECD reports indicate the use of Building Information Modelling (BIM) as one of the effective strategies for decarbonization of buildings, since a 3D digital representation of both physical and functional characteristics of a building can help to design a more efficient infrastructure. An efficient integration of solar energy in building design can be vital for the enhancement of energy performance in terms of heating, cooling, and lighting demand. This paper presents results of an analysis of how factors related to the use of daylight, such as automatic control of artificial lighting, external shading, or the visual absorptance of internal surfaces, influence the energy efficiency within an example room in two different climatic zones. The simulation was conducted using Design Builder software, with predefined occupancy schedules and internal heat gains, and standard EPW weather files for Warsaw and Genua climate zones. The study indicates that for the examined room, when no automatic sunshades or a lighting control system is utilized, most of the final energy demand is for cooling purposes (45–54%), followed by lighting (42–43%), with only 3–12% for heating purposes. The introduction of sunshades and/or the use of daylight allowed for a reduction of the total demand by up to half. Moreover, it was pointed out that often neglected factors, like the colour of the internal surfaces, can have a significant effect on the final energy consumption. In variants with light interior, the total energy consumption was lower by about 3–4% of the baseline demand, compared to their corresponding ones with dark surfaces. These results are consistent with previous studies on daylighting strategies and highlight the importance of considering both visual and thermal impacts when evaluating energy performance. Similarly, possible side effects of certain actions were highlighted, such as an increase in heat demand resulting from a reduced need for artificial lighting. The results of the analysis highlight the potential of a simulation-based design approach in optimizing daylight use, contributing to the broader goals of building decarbonization. Full article

This essay provides a fine-grained analysis of selected passages of Giulio Aleni (艾儒略 1582–1649)’s translation of Catholic liturgy into classical Chinese in late imperial China. It focuses on the hitherto underexplored relationships between Aleni’s resort to medieval Aristotelianism and Thomism, as well as his translation-based introduction of Catholic Eucharistic theology into China. The case studies here revolve around Aleni’s Chinese translation of Aristotelian-Thomistic hylomorphism, with a focus on his interpretation of “anima” (i.e., the soul, which corresponds largely to linghun 靈魂 in Chinese), which is a multifaceted Western concept that pertains simultaneously to Aristotelian-Thomistic philosophy and Eucharistic theology. It is argued that in his overarching project of introducing Western learnings (i.e., 西學) to sixteenth- and seventeenth-century China, Aleni’s attention is centered primarily on the body-soul and form-matter relationship. This is, as understood here, motivated to a great extent by his scholarly awareness that properly informing Chinese Catholics of the Aristotelian-Thomistic underpinning of Western metaphysics enacts an indispensable role in introducing Catholic liturgy into China, notably the mystery of the Eucharist and Transubstantiation that would not have been effectively introduced to China without having the Western philosophical underpinnings already made available to Chinese intellectuals. Aleni’s use of medieval European cultural legacy thus requires more in-depth analysis vis-à-vis his translational poetics in China. Accordingly, the intellectual and liturgical knowledge in Aleni’s Chinese œuvres shall be investigated associatively, and the medievalism embodied by Aleni offers a valid entry point and productive critical prism. Full article

Croatian agricultural legislation acknowledges the significance of radionuclides as pollutants in agricultural lands; however, it lacks specific thresholds or reference values for contamination levels, in contrast to other contaminants. This absence highlights the necessity for a comprehensive assessment of radionuclides across various agricultural systems in Croatia. This study investigates the transfer of radionuclides ¹³⁷Cs and ⁴⁰K from soil to agricultural crops throughout Croatia and estimates the consequent annual ingestion dose for the population. The samples collected comprised food crops and animal feed, with corresponding soil samples analyzed to calculate transfer factors. Activity concentrations of ¹³⁷Cs exhibited regional and crop-type variability, reflecting the uneven distribution of fallout and differing soil properties. Transfer factors were found to range from 0.003 to 0.06 for ¹³⁷Cs and from 0.15 to 3.1 for ⁴⁰K, with the highest uptake occurring in kidney beans. The total estimated annual effective ingestion dose was calculated to be a maximum of 0.748 mSv/year for children aged 2–7, predominantly attributable to ⁴⁰K. Given the homeostatic regulation of potassium in the human body, the dose associated with ¹³⁷Cs poses a more significant radiological concern. These findings underscore the need for radionuclide-specific agricultural legislation in Croatia and offer a baseline for recommending reference values and informing future regulations regarding agricultural soil contamination. Full article

Daphnis nerii cypovirus-23 (DnCPV-23) is a new type of cypovirus that has a lethal effect on many species of Sphingidae pests. DnCPV-23 can replicate in Spodoptera frugiperda Sf9 cells, but the replication characteristics of the virus in this cell line are still unclear. To determine the replication characteristics of DnCPV-23 in Sf9 cells, uninfected Sf9 cells and Sf9 cells at 24 and 72 h after DnCPV-23 infection were collected for transcriptome analysis. Compared to uninfected Sf9 cells, a total of 188 and 595 differentially expressed genes (DEGs) were identified in Sf9 cells collected at 24 hpi and 72 h, respectively. KEGG analyses revealed that 139 common DEGs in two treatment groups were related to nutrition and energy metabolism-related processes, cell membrane integrity and function-related pathways, detoxification-related pathways, growth and development-related pathways, and so on. We speculated that these cellular processes might be manipulated by viruses to promote replication. This study provides an important basis for further in-depth research on the mechanism of interaction between viruses and hosts. It provides additional basic information for the future exploitation of DnCPV-23 as a biological insecticide. Full article

We need to educate students and the public about addressing natural resource challenges to maintain civilization moving into a sustainable future. Because US mineral and energy resources are found in its continental crust and sedimentary basins, introductory geology students need to be well-informed about US crust and basins. We think that creating effective videos about these topics is the best way to engage students to want to learn more. In preparation for making these videos, we researched what introductory geology students are taught and what they learn about these topics. Student interviews informed us about learned curriculum, and taught curriculum was analyzed using a novel keyword-counting method applied to textbook indices. We found that geophysics is stressed twice as much as geology, radiometric dating, and sedimentary basins. We expected that students would have learned more about geophysics and less about the other topics; however, this was not the case. Students knew more about geology, and less about geophysics, radiometric dating, and sedimentary basins. To make effective videos on these topics, we need to explain the following threshold concepts: seismic refraction to scaffold student understanding of crustal geophysics, as well as radiometric dating and deep time to understand crustal geology and the economic importance of sedimentary basins. Full article