Multi-level Network Research Articles

Ag-S coordination strategy for high recovery driving stress in recyclable shape memory polymers

To address the issue of low strength and recovery stress in recyclable shape memory polymer (SMP) materials with dynamic covalent bonds in practical applications, we propose a method based on Ag-S coordination interactions to improve dynamic covalent bonds, thereby preparing recyclable SMP with high recovery stress and large recovery strain. The introduction of in situ reduced silver nanoparticles (AgNPs) in the SMP system play multiple roles, serving as additional physical crosslinking points at the microscale and coordinating with disulfide bonds in the system to construct a multi-level dynamic network structure. This endows the material with exceptional mechanical properties (tensile strength of 25.93 MPa and fracture strain of 1466.83 %) and recovery driving stress (5.59 MPa), while maintaining more than 99 % shape recovery and fixity rate. Furthermore, due to the outstanding photothermal performance of AgNPs, the composite material has acquired remote photothermal driving capabilities. The proposed Ag-S coordination enhancement offers a new approach for SMP materials that achieve both large actuation distance and high recovery stress, holding significant potential for applications in soft robotics and actuators.

Multi-Temporal Snow-Covered Remote Sensing Image Matching via Image Transformation and Multi-Level Feature Extraction

To address the challenge of image matching posed by significant modal differences in remote sensing images influenced by snow cover, this paper proposes an innovative image transformation-based matching method. Initially, the Pix2Pix-GAN conversion network is employed to transform remote sensing images with snow cover into images without snow cover, reducing the feature disparity between the images. This conversion facilitates the extraction of more discernible features for matching by transforming the problem from snow-covered to snow-free images. Subsequently, a multi-level feature extraction network is utilized to extract multi-level feature descriptors from the transformed images. Keypoints are derived from these descriptors, enabling effective feature matching. Finally, the matching results are mapped back onto the original snow-covered remote sensing images. The proposed method was compared to well-established techniques such as SIFT, RIFT2, R2D2, and ReDFeat and demonstrated outstanding performance. In terms of NCM, MP, Rep, Recall, and F1-measure, our method outperformed the state of the art by 177, 0.29, 0.22, 0.21, and 0.25, respectively. In addition, the algorithm shows robustness over a range of image rotation angles from −40° to 40°. This innovative approach offers a new perspective on the task of matching multi-temporal snow-covered remote sensing images.

Frequency aware high-quality computer-generated holography via multilevel wavelet learning and channel attention.

Deep learning-based computer-generated holography offers significant advantages for real-time holographic displays. Most existing methods typically utilize convolutional neural networks (CNNs) as the basic framework for encoding phase-only holograms (POHs). However, recent studies have shown that CNNs suffer from spectral bias, resulting in insufficient learning of high-frequency components. Here, we propose a novel, to our knowledge, frequency aware network for generating high-quality POHs. A multilevel wavelet-based channel attention network (MW-CANet) is designed to address spectral bias. By employing multi-scale wavelet transformations, MW-CANet effectively captures both low- and high-frequency features independently, thus facilitating an enhanced representation of high-frequency information crucial for accurate phase inference. Furthermore, MW-CANet utilizes an attention mechanism to discern and allocate additional focus to critical high-frequency components. Simulations and optical experiments confirm the validity and feasibility of our method.

Stepwise Corrected Attention Registration Network for Preoperative and Follow-Up Magnetic Resonance Imaging of Glioma Patients.

The registration of preoperative and follow-up brain MRI, which is crucial in illustrating patients' responses to treatments and providing guidance for postoperative therapy, presents significant challenges. These challenges stem from the considerable deformation of brain tissue and the areas of non-correspondence due to surgical intervention and postoperative changes. We propose a stepwise corrected attention registration network grounded in convolutional neural networks (CNNs). This methodology leverages preoperative and follow-up MRI scans as fixed images and moving images, respectively, and employs a multi-level registration strategy that establishes a precise and holistic correspondence between images, from coarse to fine. Furthermore, our model introduces a corrected attention module into the multi-level registration network that can generate an attention map at the local level through the deformation fields of the upper-level registration network and pathological areas of preoperative images segmented by a mature algorithm in BraTS, serving to strengthen the registration accuracy of non-correspondence areas. A comparison between our scheme and the leading approach identified in the MICCAI's BraTS-Reg challenge indicates a 7.5% enhancement in the target registration error (TRE) metric and improved visualization of non-correspondence areas. These results illustrate the better performance of our stepwise corrected attention registration network in not only enhancing the registration accuracy but also achieving a more logical representation of non-correspondence areas. Thus, this work contributes significantly to the optimization of the registration of brain MRI between preoperative and follow-up scans.

Synthesising a network of evidence on a seabird bycatch mitigation measure

AbstractRobust estimates of the relative efficacies of alternative management interventions are essential for developing evidence‐informed fisheries bycatch policy. Bycatch is a major threat to the conservation of albatrosses and other pelagic seabirds. Branchline weighting is one approach prescribed by regional fisheries management organisations and the Agreement on the Conservation of Albatrosses and Petrels to reduce seabird bycatch in pelagic longline fisheries. We used a Bayesian multilevel network meta‐regression modelling approach to conduct the first synthesis of available evidence to assess the relative efficacies at mitigating seabird bycatch of alternative pelagic longline weighting designs. Unlike conventional pairwise meta‐analysis, network meta‐analysis enables the simultaneous comparison of multiple interventions within a coherent modelling framework. There was a > 97% probability that all weighting designs significantly reduced seabird bycatch compared to a reference design with no weight within 5 m of the hook. Nonetheless, some weighting designs were significantly more effective at reducing seabird bycatch than others—for instance, the 2 designs with weights >60 g and >1 m from the hook performed the best with >93% probability that those 2 designs performed significantly better than 2 more commonly used designs with less weight but attached closer to the hook. These two best performing designs reduced seabird bycatch by ca 89% relative to the reference design. These relative efficacies and rankings, when combined with other performance criteria such as costs to commercial viability and crew safety, support robust evaluations of alternative bycatch management strategies.

Process and mechanism of termite impact on soil and plant.

Termites, as a kind of nesting social insects, are often confused as worldwide "pests" because some of their groups have great destructive effects. The vast majority of termites can regulate ecosystem functions and ser-vices by participating in biogeochemical cycles, known as "ecosystem engineers". We reviewed studies on the effects of termites on the physical, chemical and biological characteristics of mound soil ecosystems and the composition and diversity of plant communities. Termites could form unique soil "biogenic aggregates" and "resource heterogeneity patches", which affect microbial community structure, extracellular enzyme activity, physicochemical property and greenhouse gas emission, thereby affecting plant growth, community composition and structure, and vegetation productivity. However, this effect significantly differed among termite groups and functional groups, and was dependent on regional soil environment and microclimate conditions. Meanwhile, termite-mound could effectively improve ecosystem adaptation or resistance to environmental stress through the above process. Future research should focus on the following directions: 1) studying the trophic cascading effect of termite-centered soil multilevel biological network and the potential effect on biogeochemical cycle from microscale (aggregate level) to macroscale (landscape level); 2) exploring the potential of termite mound soil as a fertility amendment in tropical regions, and mining beneficial microbial functional genes to develop related products for termite control.

Comparing the efficacy of cipaglucosidase alfa plus miglustat with other enzyme replacement therapies for late-onset Pompe disease: a network meta-analysis utilizing patient-level and aggregate data.

Aim: Late-onset Pompe disease is characterized by progressive loss of muscular and respiratory function. Until recently, standard of care was enzyme replacement therapy (ERT) with alglucosidase alfa. Second-generation ERTs avalglucosidase alfa (aval) and cipaglucosidase alfa with miglustat (cipa+mig) are now available. Without head-to-head trials comparing aval with cipa+mig, an indirect treatment comparison is informative and timely for understanding potential clinical differentiation. Materials & methods: A systematic literature review was performed to identify relevant studies on cipa+mig and aval. Using patient-level and aggregate published data from randomized controlled trials (RCTs) and phase I/II and open-label extension (OLE) trials, a multi-level network meta-regression was conducted, adjusting for various baseline covariates, including previous ERT duration, to obtain relative effect estimates on 6-minute walk distance (6MWD, meters [m]) and forced vital capacity (FVC, %predicted [pp]). Analyses of two networks were conducted: Network A, including only RCTs, and network B, additionally including single-arm OLE and phase I/II studies. Results: Network B (full evidence analysis) showed that cipa+mig was associated with a relative increase in 6MWD (mean difference 28.93m, 95% credible interval [8.26-50.11m]; Bayesian probability 99.7%) and FVC (2.88pp [1.07-4.71pp]; >99.9%) compared with aval. The comparison between cipa+mig and aval became more favorable for cipa+mig with increasing previous ERT duration for both end points. Analysis of network A showed that cipa+mig was associated with a relative decrease in 6MWD (-10.02m [-23.62 to4.00m]; 91.8%) and FVC (-1.45pp [-3.01 to0.07pp]; 96.8%) compared with aval. Conclusion: Cipa+mig showed a favorable effect versus aval when all available evidence was used in the analysis.

Strategic Enhancement and Differential Governance: China’s Partnership Diplomacy in Latin America

This paper studies China’s partnership diplomacy and its practice in Latin America and the Caribbean (LAC). China has constructed an all-round, multi-level, and three-dimensional partnership network in LAC through three stages: strategic exploration, development, and improvement. China has implemented differential governance towards its partners, which enables active shaping and dynamic management of the partnership network. This paper categorizes the 15 partner countries into three types: pivot countries, link countries, and node countries based on their political friendliness with China, geopolitical influence, and potential for economic and trade cooperation. China’s partnerships in LAC are vital support for implementing its diplomatic strategy in the region. However, challenges to this strategy’s development include insufficient mutual support from other diplomatic means, doubts and misinterpretations of the China-Latin America partnership by some Latin American countries, and the political and identity shifts within these countries. To enhance the role of partnerships in maintaining state relations and promoting the implementation of diplomatic strategies, China has introduced new content to its partnership diplomacy in LAC.

Research on Multi-Layer Defense against DDoS Attacks in Intelligent Distribution Networks

With the continuous development of new power systems, the intelligence of distribution networks has been increasingly enhanced. However, network security issues, especially distributed denial-of-service (DDoS) attacks, pose a significant threat to the safe operation of distribution networks. This paper proposes a novel DDoS attack defense mechanism based on software-defined network (SDN) architecture, combining Rényi entropy and multi-level convolutional neural networks, and performs fine-grained analysis and screening of traffic data according to the amount of calculation to improve the accuracy of attack detection and response speed. Experimental verification shows that the proposed method excels in various metrics such as accuracy, precision, recall, and F1-score. It demonstrates significant advantages in dealing with different intensities of DDoS attacks, effectively enhancing the network security of user-side devices in power distribution networks.

MLFA-Net: multi-level feature-aggregated network for semantic change detection in remote sensing images

ABSTRACT The rapid advancement in Earth observation technologies has improved the acquisition of precise data on terrestrial changes. However, traditional binary change detection (BCD) fails to satisfy the complex demands of contemporary applications. In contrast, semantic change detection (SCD) can identify changed areas and further detect the types of changes in ground objects. Nonetheless, current SCD approaches pose significant challenges, including the inadequate extraction and utilization of multi-level features and limited synergistic integration of related tasks. This paper proposes a multi-level feature-aggregated network (MLFA-Net), which decomposes the SCD task into two related subtasks: ground object classification and BCD of bi-temporal images. To optimize the classification performance, MLFA-Net incorporates feature alignment and cross-level feature aggregation modules that operate between the encoders and decoders, achieving effective extraction, aggregation, and utilization of multi-level image features. MLFA-Net also integrates symmetric transform feature aggregation modules between classification and BCD branches, leveraging prior knowledge to facilitate cross-task transmission of multi-level information and further optimize SCD results. MLFA-Net achieved Scores of 0.6214 and 0.3581 on Landsat-SCD and SECOND datasets, respectively, with improvements of at least 0.0402 and 0.0035 compared to other methods. Quantitative and qualitative experiments validate the efficacy and superiority of the proposed MLFA-Net in SCD tasks.

Coarse-to-Fine Structure and Semantic Learning for Single-Sample SAR Image Generation

Synthetic Aperture Radar (SAR) enables the acquisition of high-resolution imagery even under severe meteorological and illumination conditions. Its utility is evident across a spectrum of applications, particularly in automatic target recognition (ATR). Since SAR samples are often scarce in practical ATR applications, there is an urgent need to develop sample-efficient augmentation techniques to augment the SAR images. However, most of the existing generative approaches require an excessive amount of training samples for effective modeling of the SAR imaging characteristics. Additionally, they show limitations in augmenting the interesting target samples while maintaining image recognizability. In this study, we introduce an innovative single-sample image generation approach tailored to SAR data augmentation. To closely approximate the target distribution across both the spatial layout and local texture, a multi-level Generative Adversarial Network (GAN) architecture is constructed. It comprises three distinct GANs that independently model the structural, semantic, and texture patterns. Furthermore, we introduce multiple constraints including prior-regularized noise sampling and perceptual loss optimization to enhance the fidelity and stability of the generation process. Comparative evaluations against the state-of-the-art generative methods demonstrate the superior performance of the proposed method in terms of generation diversity, recognizability, and stability. In particular, its advantages over the baseline method are up to 0.2 and 0.22 in the SIFID and SSIM, respectively. It also exhibits stronger robustness in the generation of images across varying spatial sizes.

Maritime transportation risk assessment: A multilevel node relationship-based fuzzy bayesian network

Maritime transportation safety has encountered unprecedented challenges arising from abrupt changes in various risk attributes in recent years, including natural weather and non-traditional security threats. This study presents a novel two-phase framework for assessing the maritime transportation risk. Firstly, a fuzzy Bayesian network considering multi-level node relationships was constructed to more accurately assess the transportation risk in various sea areas. In the second phase, RF-Shapley was developed to identify crucial risk nodes that exert substantial influence on transportation risk within individual sea areas. The results showed that transportation risk was the lowest in the South Asian and the highest in the Middle East waters. Critical risk nodes were different for each sea area, such as pirate attack node in Southeast Asian waters, extreme weather node in Northeast Asia, changing these nodes would be more helpful in improving transportation safety. Moreover, the contribution of critical risk nodes exhibited variations, such as combating terrorism and piracy were more conducive to reducing transportation risk in Middle Eastern waters, while ship accidents node be low contribution. These results offer valuable insights for evaluating transportation risk in uncertain environments and can serve as a reference for stakeholders to devise tailored policies and action plans.

A multi-level multi-product supply chain network design of vegetables products considering costs of quality: A case study.

Effective logistics management is crucial for the distribution of perishable agricultural products to ensure they reach customers in high-quality condition. This research examines an integrated, multi-echelon supply chain for perishable agricultural goods. The supply chain consists of four stages: supply, processing, storage, and customers. This study investigates the quality-related costs associated with product perishability to maximize supply chain profitability. Key factors considered include the network design, location of processing and distribution centers, the ability to process raw products to minimize post-harvest quality degradation, the option to sell the excess produce to a secondary market due to unpredictable yields, and the decision not to fulfill demand from distant customers where significant quality loss and price drops would be involved, instead diverting those products to the aforementioned secondary market. Quantitative methods and linear mathematical programming are employed to model and validate the proposed supply chain using actual data from a real-world case study on vegetable supply chains. The main contribution of this research is the incorporation of quality costs into the objective function, which allows the supply chain to prioritize meeting nearby customers' demands with minimal quality loss over serving distant customers where high quality loss is unavoidable. Additionally, deploying a faster transportation fleet can significantly improve the overall profitability of the perishable product supply chain.

A novel pansharpening model based on two parallel network architectures

ABSTRACT Pansharpening is an important technology for obtaining high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) images and high-resolution panchromatic (PAN) images. Although many pansharpening models have emerged by taking advantage of deep learning (DL) technology, there remains a pressing need to further assess pansharpening accuracy and stability when LRMS images with complex land-cover types. What’s more, these models often overlook the exploitation of PAN images’ inherent high-frequency information. To address these issues, we propose a pansharpening model combining multi-level and multi-scale network architectures. The multi-level network architecture is used to build spatial-spectral dependence on LRMS-PAN pairs, and strengthen the network’s feature capture capability by keeping the multi-level texture details. The multi-scale architecture is subsequently used to extract the spatial structure and deep texture of the PAN images at different scales. Downsampled experiments and real experiments in four standard datasets show that the proposed model achieves a state-of-the-art performance.

Construction of urban-rural ecological networks with multi-scale nesting and composite functions based on the “red-green-blue” spatial perspective: A case study of Dali City, China

Urbanization has facilitated economic development while simultaneously resulting in various ecological issues. Constructing a multi-scale nested and composite functional urban-rural ecological network is crucial for improving ecological security. This study utilizes Dali City as a case study and employs methods including MSPA, circuit theory, and landscape connectivity index to develop the urban-rural habitat network, water green network, and recreation network, focusing on the " red-green-blue " spatial framework. An analysis of the spatial characteristics of source areas, corridors, ecological strategic points, and other spatial elements is conducted to establish a multi-level, multi-objective, and multifunctional composite urban-rural ecological network. The results show that: (1) 13 ecological source areas were identified in both the municipal and main urban areas, along with 22 ecological corridors in the municipal and 20 main urban areas. The distribution of ecological corridors was uniform across the study area. (2) The optimal width for the municipal biological corridor is 150 m, the main urban area should have a width of 90 m. The optimal width for rainwater corridors in municipal and main urban areas is 60 m. (3) The multi-scale nested ecological network identified 4 common ecological sources, 11 ecological corridors, 3 rainwater corridors, 6 wetland nodes, and 7 amusement nodes. Overall, the number of ecological nodes is limited, indicating a need for enhanced node construction. The research findings offer insights for developing ecological networks that integrate urban and rural functions, serving as a reference for ecological protection and restoration in pertinent regions.

Real-time voltage control of centralized and distributed coordination in active distribution network under multiple coupling

Abstract At present, the “source-load interaction” distribution network operation mode has gradually replaced the “source-load operation” mode. The uncertainty and volatility of the distribution system have been enhanced, the controllability has been weakened, the voltage fluctuations have been frequent, and the power quality has been decreased. Voltage regulation is crucial to fully absorbing new energy generation and improving the operation safety of the active distribution network. To solve the problem of real-time control of distribution networks, this paper proposes a distributed voltage control method of active distribution networks with global sensitivity, establishes a distributed communication mechanism, and builds a distributed forward push-back communication rule to transfer power and voltage information between nodes. The global sensitivity of voltage, active power, and reactive power is used for real-time, independent, and effective control of multiple devices at each node, and the distributed control process is simulated according to actual production conditions. Furthermore, the centralized and decentralized real-time voltage control methods are proposed, and the centralized and distributed methods are implemented in medium voltage primary distribution network (MVPN) and low voltage secondary distribution network (LVSN), respectively, to play the advantages of high computing efficiency and fast control response. Based on model predictive control (MPC), intra-day rolling time scale voltage regulation is constructed, and second-level control is used to adapt the MPC results, finally promoting the optimal scheduling and rapid response of various controllable flexible resources in the multi-level active distribution network.

Sustainable manufacturing process thermal energy environment detection and green economy development based on image classification

With a growing global focus on sustainability, manufacturing needs to ensure productivity while reducing resource consumption and environmental impact. This paper discusses the thermal energy environment detection method based on image classification in order to improve the energy efficiency monitoring in the manufacturing process and promote the development of green economy. In this study, deep learning technology was used to train convolutional neural network (CNN) to classify thermal environment data, collect thermal data images from multiple manufacturing processes, and label them. The pretreatment technology is used to improve the data quality, and the classification effect is optimized through multi-level network structure. The training and verification process of the model ensures its reliability in practical application scenarios. The experimental results show that the proposed image classification method achieves high accuracy in thermal environment detection, which is obviously superior to the traditional method. Through real-time monitoring of thermal energy status, timely identification of abnormal conditions, so as to provide effective data support for the manufacturing process, and promote the realization of energy conservation and emission reduction goals. Therefore, the thermal environment detection based on image classification provides a new technical path for the sustainable development of the manufacturing industry, and helps enterprises realize the transformation and upgrading of the green economy.

Node Role Selection and Rotation Scheme for Energy Efficiency in Multi-Level IoT-Based Heterogeneous Wireless Sensor Networks (HWSNs).

The emergence of Internet of Things (IoT)-based heterogeneous wireless sensor network (HWSN) technology has become widespread, playing a significant role in the development of diverse human-centric applications. The role of efficient resource utilisation, particularly energy, becomes further critical in IoT-based HWSNs than it was in WSNs. Researchers have proposed numerous approaches to either increase the provisioned resources on network devices or to achieve efficient utilisation of these resources during network operations. The application of a vast proportion of such methods is either limited to homogeneous networks or to a single parameter and limited-level heterogeneity. In this work, we propose a multi-parameter and multi-level heterogeneity model along with a cluster-head rotation method that balances energy and maximizes lifetime. This method achieves up to a 57% increase in throughput to the base station, owing to improved intra-cluster communication in the IoT-based HWSN. Furthermore, for inter-cluster communication, a mathematical framework is proposed that first assesses whether the single-hop or multi-hop inter-cluster communication is more energy efficient, and then computes the region where the next energy-efficient hop should occur. Finally, a relay-role rotation method is proposed among the potential next-hop nodes. Results confirm that the proposed methods achieve 57.44%, 51.75%, and 17.63% increase in throughput of the IoT-based HWSN as compared to RLEACH, CRPFCM, and EERPMS, respectively.

Dynamic traffic network representation model for improving the prediction performance of passenger flow for mass rapid transit

Accurate machine learning predictions of passenger flow data for mass rapid transit (MRT) systems can considerably improve operational efficiency by enabling better allocation of train and human resources. However, such predictions are challenging because MRT networks have complex structures with route dependence and transfer stations. Although the static state of an MRT network has been computed in previous studies, a comprehensive understanding of an MRT network requires characterizing its dynamics. Therefore, this paper proposes a dynamic traffic network representation (DTNR) model that captures station features from historical traffic flows and geographical information of MRT stations. Furthermore, a multilevel attention network (MLAN) model is proposed to predict MRT passenger flow as a downstream task following the pretraining of the DTNR model. The experimental results of this study indicate that the developed DTNR and MLAN models can accurately predict MRT passenger flow. These models are widely applicable to different MRT systems and passenger flow situations, making them a valuable tool for transportation planners and operators.

Application of Virtual Reality Technology Based on Convolutional Neural Network in Digital Media Art Creation

On the basis of the convolutional neural network based on the absolute value layer, a convolutional neural network based on multi-level parallel is proposed. This model adds shortcut connections between different convolutional layers of the convolutional neural network. The shortcut connections allow the feature map output from the shallower convolutional layers in the network to be directly used as branch information, which is similar to the deep convolutional layer. The feature maps are combined to obtain a feature map with more comprehensive information. By using the features of the shallow convolutional layer and the deep convolutional layer at the same time, the embedded traces it learns are more accurate. The final experimental results prove that the multi-level parallel convolutional neural network has a significant improvement in detection performance compared with the rich model art creation analysis algorithm, even when confronting the HILL art creation algorithm with an embedding rate of 0.4bpp.