期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到473,246篇文章
< 1 2 … 250 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Modularized Graph Convolutional Network 认领 引用
1
作者 Tiantian He Zhixuan Duan Xin Luo 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第3期737-739,共3页
Dear Editor,This letter presents a novel graph neural network, namely modularized graph convolution network(MGCN), to address the underexplored issue in graph convolution networks(GCNs), wherein the weights for neighb... Dear Editor,This letter presents a novel graph neural network, namely modularized graph convolution network(MGCN), to address the underexplored issue in graph convolution networks(GCNs), wherein the weights for neighbor aggregation are fixed, leading to the limited capability of capturing diverse relationships among nodes for representation learning. Conventional GCNs always learn node representations in the graph according to the weights computed from the graph Laplacian, consequently overlooking the similarity and group cohesiveness of node features. 展开更多
关键词 graph convolution networks gcns capturing diverse relationships nodes representation learning modularized graph convolution network neighbor aggregation graph neural network modularized graph convolution network mgcn graph convolutional network
暂未订购 下载PDF
Introduction to the Special Issue on Computer Modeling for Future Communications and Networks 认领 引用
2
作者 Wenbing Zhao Pan Wang 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第6期36-38,共3页
The next generation of global communication networks is expected to deliver a transformative leap in connectivity,transcending beyond terrestrial limitations to achieve truly ubiquitous coverage.Rather than operating ... The next generation of global communication networks is expected to deliver a transformative leap in connectivity,transcending beyond terrestrial limitations to achieve truly ubiquitous coverage.Rather than operating as fragmented regional systems,future infrastructures will leverage Satellite-Terrestrial Integrated Networks(STIN)and 6G technologies to form a unified global network. 展开更多
关键词 unified global network computer modeling networks global communication networks future communications g technologies regional systemsfuture satellite terrestrial integrated networks
暂未订购 下载PDF
Space-Terrestrial Integrated 6G Network:Architecture,Networking,and Transmission Technologies 认领 引用
3
作者 Kuang Linling Wang Jianxiu +1 位作者 Zhang Jianhua Wang Shuai 《China Communications》 SCIE EI CSCD 2026年第3期I0002-I0004,共3页
With the large-scale deployment of satellite constellations and the rapid advancement of technologies including artificial intelligence(AI)and non-terrestrial networks(NTNs),the integration of high,medium,and low Eart... With the large-scale deployment of satellite constellations and the rapid advancement of technologies including artificial intelligence(AI)and non-terrestrial networks(NTNs),the integration of high,medium,and low Earth orbit satellite networks with terrestrial networks has become a critical direction for future communication technologies.The objective is to develop a space-terrestrial integrated 6G network that ensures ubiquitous connectivity and seamless services,facilitating intelligent interconnection and collaborative symbiosis among humans,machines,and objects.This integration has become a central focus of global technological innovation. 展开更多
关键词 communication technologiesthe g network satellite constellations space terrestrial integrated g network terrestrial networks artificial intelligence ai intelligent interconnection satellite networks
暂未订购 下载PDF
Spatial Network Structure Characteristics and Resilience Evaluation of Urban Ice and Snow Activities in Cold Border Regions:A Case Study of Harbin City,China 认领 引用
4
作者 DU Wenhao LI Weilin +7 位作者 CHEN Xiaohong WANG Ying MOU Jinming CUI Yi WU Han WANG Xinyu XIE Donghong ZHANG Yujie 《Chinese Geographical Science》 SCIE CAS CSCD 2026年第4期638-654,共17页
Under the background of the diversification and increasingly frequent flow of ice and snow activities,revealing the characteristics of the spatial network of ice and snow activities and enhancing the resilience of the... Under the background of the diversification and increasingly frequent flow of ice and snow activities,revealing the characteristics of the spatial network of ice and snow activities and enhancing the resilience of the network to cope with multiple disturbances have become the core issues of the adaptive transformation and development of ice and snow tourism in cold border cities.Taking Harbin City,Heilongjiang Province,China as the research object,based on Python and Large Language Model(LLM),this paper obtained the‘O(origin)-D(destination)'space movement trajectory in Mafengwo Tourism Official Website online travel notes from 2023 to 2025.With the help of complex network analysis and scenario simulation,it analyzed the‘overall-individual'characteristics of the static ice and snow activity space network,and evaluated the resilience of the dynamic space network.The results show that:1)the spatial network nodes of ice and snow activities show the characteristics of‘overall aggregation-local dispersion',and the moving trajectory shows the radial spatial characteristics of‘center-surrounding',the network structure shows the spatial imbalance state of unipolar aggregation,and the mobility between a large number of nodes is weak.2)There are local dense areas and strong clusters in the spatial network of ice and snow activities,but the connections between nodes are‘redundant-inefficient'hierarchical connectivity,and a few hub nodes have very many connections,which combines the hub monopoly of scale-free network and the local clustering of small world network.3)The relative positions of nodes in the network are quite different.Some nodes show a significant central superposition of‘flow control-transit monopoly-network center-hub agglomeration',and the network shows a significant‘core-periphery'feature.4)The spatial network of ice and snow activities is strong and resilient when subjected to random attacks,but it shows significant vulnerability under intentional attacks,with high network crash rate and strong dependence on the connection between key nodes and the core.This study provides a scientific basis for decision-makers to accurately protect core activity nodes,cultivate secondary hubs and alternative routes,thereby reasonably promoting the continuous optimization of the spatial layout of urban activity networks. 展开更多
关键词 spatial flow network network topology characteristics network resilience complex network analysis ice and snow activities space Harbin China
暂未订购 下载PDF
Voxel event graph neural network for event-based human gait recognition 认领 引用
5
作者 Guangyuan MA Xiaolin GONG +2 位作者 Jiangtao XU Jiandong GAO Zhaoxuan GUO 《Optoelectronics Letters》 EI 2026年第3期167-173,共7页
To improve the accuracy of event-based gait recognition,a method called voxel event graph neural network(VEGNN)is proposed.This method voxelizes the event stream and selects representative voxels as vertices of the gr... To improve the accuracy of event-based gait recognition,a method called voxel event graph neural network(VEGNN)is proposed.This method voxelizes the event stream and selects representative voxels as vertices of the graph.Then the edges are constructed based on spatio-temporal distance and temporal order constraints so that the event stream is constructed as a graph structure.Finally,a lightweight feature extraction network based on graph neural networks(GNNs)is used to efficiently capture spatio-temporal information and motion cues from the event graph.To evaluate our method,an event-based gait recognition dataset called Celex-Gait is created.Experimental results show that VEGNN achieves a gait recognition accuracy of 95.8%and 93.9%on the Celex-Gait dataset and the DVS128-Gait-Day dataset,respectively.Furthermore,compared to the state-of-the-art methods,VEGNN reduces the number of model parameters by 30%.This indicates that VEGNN achieves higher recognition accuracy with lower model complexity. 展开更多
关键词 selects representative voxels voxel event graph neural network vegnn event stream lightweight feature extraction network voxel event graph neural network graph structurefinallya graph neural networks gnns gait recognitiona
暂未订购 下载PDF
Cropping alfalfa for 18 years increases importance of fungi in multi-kingdom networks in saline-alkali soils 认领 引用
6
作者 Dan ZHU Bin LI +5 位作者 Lun AO Xiaoqian LIU Mengmeng ZHANG Guangyu SUN Junnan DING Xin LI 《Pedosphere》 SCIE CAS CSCD 2026年第3期802-817,共16页
Soil salinization has become a significant global ecological and resource problem.Alfalfa cropping has been recognized as an effective method for improving soil fertility and promoting the sustainable growth of agricu... Soil salinization has become a significant global ecological and resource problem.Alfalfa cropping has been recognized as an effective method for improving soil fertility and promoting the sustainable growth of agricultural ecosystems.In this study,an 18-year-old alfalfa cultivation area within the saline-alkali Songnen Plain in Northeast China was selected to determine the contribution of the microbial network to the improvement of saline-alkali soils after alfalfa cropping.Our findings indicated that the multi-kingdom microbial network,comprising fungi,bacteria,and archaea,was more complex and stable than the single-kingdom networks.Specifically,the multi-kingdom network exhibited an increased number of nodes and connections,demonstrating higher complexity.By cultivating alfalfa in saline-alkali soils,fungal nodes in the multi-kingdom network demonstrated significantly higher degree and betweenness compared to bacterial nodes and archaeal nodes.Additionally,fungi had a higher natural connectivity,which contributed to the overall network stability.In contrast,the bacterial subset in the multi-kingdom network in bare land exhibited a higher degree,betweenness,and natural connectivity.Furthermore,changes in the topological properties of the microbial network,including its complexity and stability,were significantly correlated with environmental factors,such as soil electrical conductivity and pH.In conclusion,cultivating alfalfa stabilized the self-organization in the multi-kingdom network in saline-alkaline soils and increased the complexity and stability of the fungal network.These findings provide a foundation for further research into the role of multi-kingdom microbial communities in soil ecosystems. 展开更多
关键词 microbial community microbial co-occurrence network network stability phytoremediation single-kingdom network soil salinization Songnen Plain topological property
暂未订购 下载PDF
Recognition and classification of microseismic signals based on Bayesian-optimized CNN-LSTM neural network 认领 引用
7
作者 WU Yang LIU Jian-feng +4 位作者 WANG Chun-ping LIU Jun-jie JI Zhen-xing TIAN Cheng-yu XUE Fu-jun 《Journal of Central South University》 SCIE EI CAS CSCD 2026年第6期2762-2787,共26页
Microseismic monitoring and signal recognition constitute critical technologies for accurately assessing rockburst risks and ensuring the safe construction of underground rock engineering.This study developed a"S... Microseismic monitoring and signal recognition constitute critical technologies for accurately assessing rockburst risks and ensuring the safe construction of underground rock engineering.This study developed a"Surface+Underground"microseismic intelligent monitoring system to evaluate dynamic disaster risks during construction at the Beishan High-level Radioactive Waste Geological Disposal Laboratory in China.The datasets of four typical one-dimensional time-domain microseismic signals,including rock fracture,blasting,TBM tunneling,and drilling,were constructed,and the BO-CNN-LSTM model is developed to identify and classify these signals..Based on the classification results,the typical time-frequency domain characteristics of the four types of signals are analyzed.The classification results of BO-CNN-LSTM,CNN,LSTM and CNN-LSTM models show that the recognition accuracy of the four models is 98.0%,85.7%,66.7%and 91.0%,respectively.Among all types,the four models demonstrate the highest effectiveness in identifying rock fracture and borehole signals.The findings further confirm that the BO-CNN-LSTM model efficiently recognizes and extracts microseismic signal features,demonstrating superior performance and stability in the classification task.Finally,the study suggests several future research directions,particularly in the areas of raw signal denoising,and automation of feature extraction. 展开更多
关键词 deep ground engineering microseismic monitoring signal classification neural network Bayesian optimization convolutional neural network(CNN) long short-term memory network(LSTM) BO-CNN-LSTM model
暂未订购 下载PDF
Networked Predictive Control:A Survey 认领 引用
8
作者 Zhong-Hua Pang Tong Mu +3 位作者 Yi Yu Haibin Guo Guo-Ping Liu Qing-Long Han 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第1期3-20,共18页
Networked predictive control(NPC) has gained significant attention in recent years for its ability to effectively and actively address communication constraints in networked control systems(NCSs),such as network-induc... Networked predictive control(NPC) has gained significant attention in recent years for its ability to effectively and actively address communication constraints in networked control systems(NCSs),such as network-induced delays,packet dropouts,and packet disorders.Despite significant advancements,the increasing complexity and dynamism of network environments,along with the growing complexity of systems,pose new challenges for NPC.These challenges include difficulties in system modeling,cyber attacks,component faults,limited network bandwidth,and the necessity for distributed collaboration.This survey aims to provide a comprehensive review of NPC strategies.It begins with a summary of the primary challenges faced by NCSs,followed by an introduction to the control structure and core concepts of NPC.The survey then discusses several typical NPC schemes and examines their extensions in the areas of secure control,fault-tolerant control,distributed coordinated control,and event-triggered control.Moreover,it reviews notable works that have implemented these schemes.Finally,the survey concludes by exploring typical applications of NPC schemes and highlighting several challenging issues that could guide future research efforts. 展开更多
关键词 Communication constraints cyber attacks networked control systems networked multi-agent systems networked predictive control
暂未订购 下载PDF
Toward Future Intelligent Network:When Foundation Models Meet Digital Twin 认领 引用
9
作者 Zhou Cheng Li Mei +5 位作者 Chen Danyang Yang Hongwei Li Zhiqiang Sun Tao Lu Lu Duan Xiaodong 《China Communications》 SCIE EI CSCD 2026年第3期298-315,共18页
The increasing complexity of future networks demands intelligent,scalable,and adaptive management solutions.Digital twin network(DTN)provides a high-fidelity replica of the physical network for monitoring and optimiza... The increasing complexity of future networks demands intelligent,scalable,and adaptive management solutions.Digital twin network(DTN)provides a high-fidelity replica of the physical network for monitoring and optimization,but faces significant limitations,including complex modeling,high synchronization overhead,and limited scalability.Foundation models(large pre-trained AI models)offer powerful semantic understanding and reasoning abilities,yet suffer from high training costs,risks of generating hallucinations,and limited interpretability.To address these challenges,this paper proposes an integrated architecture that combines DTN with foundation models,leveraging their complementary strengths.DTN ensures fidelity and domain-specific modeling,and acts as a validation platform to help facilitate the training and verification of network foundation models.Foundation models enable data-driven automation,downstream model generation,and adaptive decision-making.Furthermore,we present use cases related to twin network configuration verification and protocol generation,demonstrating enhanced scalability,efficiency,and intelligence for intelligent networks by bridging foundation models and digital twin. 展开更多
关键词 digital twin network foundation models large language models network configuration verification network foundation models
暂未订购 下载PDF
A Multi-Scale Graph Neural Networks Ensemble Approach for Enhanced DDoS Detection 认领 引用
10
作者 Noor Mueen Mohammed Ali Hayder Seyed Amin Hosseini Seno +2 位作者 Hamid Noori Davood Zabihzadeh Mehdi Ebady Manaa 《Computers, Materials & Continua》 SCIE EI 2026年第4期1216-1242,共27页
Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)t... Distributed Denial of Service(DDoS)attacks are one of the severe threats to network infrastructure,sometimes bypassing traditional diagnosis algorithms because of their evolving complexity.PresentMachine Learning(ML)techniques for DDoS attack diagnosis normally apply network traffic statistical features such as packet sizes and inter-arrival times.However,such techniques sometimes fail to capture complicated relations among various traffic flows.In this paper,we present a new multi-scale ensemble strategy given the Graph Neural Networks(GNNs)for improving DDoS detection.Our technique divides traffic into macro-and micro-level elements,letting various GNN models to get the two corase-scale anomalies and subtle,stealthy attack models.Through modeling network traffic as graph-structured data,GNNs efficiently learn intricate relations among network entities.The proposed ensemble learning algorithm combines the results of several GNNs to improve generalization,robustness,and scalability.Extensive experiments on three benchmark datasets—UNSW-NB15,CICIDS2017,and CICDDoS2019—show that our approach outperforms traditional machine learning and deep learning models in detecting both high-rate and low-rate(stealthy)DDoS attacks,with significant improvements in accuracy and recall.These findings demonstrate the suggested method’s applicability and robustness for real-world implementation in contexts where several DDoS patterns coexist. 展开更多
关键词 DDoS detection graph neural networks multi-scale learning ensemble learning network security stealth attacks network graphs
暂未订购 下载PDF
An efficient and balanced feature pyramid network:Shared-FPN 认领 引用
11
作者 Sulong TIAN Longfei QIN +2 位作者 Wenchao PANG Ying GAO Dexin ZHAO 《Optoelectronics Letters》 EI 2026年第5期295-301,共7页
In the field of object detection,it is challenging to achieve a balance between neck complexity and accuracy.To address this issue,we propose an efficient and decoupled neck module called shared feature pyramid networ... In the field of object detection,it is challenging to achieve a balance between neck complexity and accuracy.To address this issue,we propose an efficient and decoupled neck module called shared feature pyramid network(Shared-FPN).Not only does Shared-FPN not increase the number of model parameters and floating point operations per second(FLOPs),but it also can be easily ported to any of the detection models.It improves on path aggregation feature pyramid network(PAFPN)by using transposed convolution with a large convolution kernel as the upsampling module,designing spatial pyramidal pooling-fast downsampling(SPPFD)based on shared pooling,and designing shared convolution as the right part module.To evaluate the performance of Shared-FPN in object detection tasks,we conducted experiments on object detection datasets.The results show that Shared-FPN achieved excellent performance across all sizes.In particular,on the VOC 2012 dataset,the Shared-FPN’s mean average precision(mAP)was improved by 11.2%compared to FPN with you only look once extended-s(YOLOX-s)as the detector.On the COCO dataset,the Shared-FPN’s mAP was improved by 7.8%compared to FPN and 7.1%compared to PAFPN with faster region-based convolutional neural network(Faster RCNN)as the detector.The Shared-FPN can be easily inserted into any of the detectors for better performance in various scenarios,such as small,medium or large objects. 展开更多
关键词 efficient feature pyramid network object detectionit shared feature pyramid network shared fpn not path aggregation feature pyramid network pafpn balanced transposed convolution floating point
暂未订购 下载PDF
WGCNet:wavelet global context network for speckle-free 4K holographic display with high-frequency preservation 认领 引用
12
作者 YINGJUN LUO KEXUAN LIU +1 位作者 ZEHAO HE LIANGCAI CAO 《Photonics Research》 SCIE EI CAS CSCD 2026年第7期2925-2935,共11页
Neural-network-based computer-generated holography(CGH)has been extensively confirmed to break the tradeoff between algorithm runtime and reconstruction quality.However,conventional U-Net-based CGH methods lose high-f... Neural-network-based computer-generated holography(CGH)has been extensively confirmed to break the tradeoff between algorithm runtime and reconstruction quality.However,conventional U-Net-based CGH methods lose high-frequency detail due to inadequate global context modeling,which constrains the enhancement of realism and immersion in holographic displays.To address these challenges,we propose WGCNet:a two-stage wavelet global context network for generating speckle-free,high-fidelity 4K phase-only holograms(POHs).This framework integrates a two-dimensional(2D)wavelet down-sampling technique to enhance the U-Net backbone network and leverages physical prior knowledge to preserve high-frequency details.A lightweight global attention module is introduced to model long-range dependencies.We demonstrate that the proposed model achieves a peak signalto-noise ratio of 38.68 dB and a structural similarity index of 0.9615 on the DIV2K dataset at 4K resolution.The method significantly reduces the speckle noise in reconstruction while effectively preserving fine details.This synergistic approach establishes an effective solution for high-resolution holographic displays,offering potential for enhancing visual realism and immersion in virtual reality(VR)and augmented reality(AR)applications. 展开更多
关键词 global context modelingwhich Neural Network Based Computer Generated Holography Wavelet Global Context Network High Frequency Preservation global context network Wavelet Down Sampling U Net Speckle Free Holographic Display
暂未订购 下载PDF
ATC-FusionNet:A Hybrid Deep Learning Ensemble for Network Intrusion Detection Systems 认领 引用
13
作者 Liping Wang Jiang Wu Liang Wang 《Computers, Materials & Continua》 SCIE EI 2026年第7期1024-1046,共23页
The rapid growth of networked systems and the increasing diversity of cyberattack behaviors have posed significant challenges to intrusion detection,particularly in scenarios characterized by high-dimensional features... The rapid growth of networked systems and the increasing diversity of cyberattack behaviors have posed significant challenges to intrusion detection,particularly in scenarios characterized by high-dimensional features and severe class imbalance.Conventional detection approaches based on handcrafted rules or shallow representations often exhibit limited robustness under such conditions.To address these issues,this paper presents a hybrid deep learning framework for network intrusion detection that integrates complementary feature learning mechanisms within a dual-branch architecture.Specifically,a Transformer branch is employed to model long-range temporal dependencies in network traffic,while a convolutional neural network branch(CNN)is used to capture localized and fine-grained feature patterns.An attention-based fusion strategy is further introduced to adaptively aggregate branch-specific representations and enhance intrusion-sensitive features.In addition,an autoencoder-based feature reconstruction module is incorporated before the dual-branch network to compress and reconstruct input features through an encoder-decoder structure,thereby preserving essential behavioral characteristics of network traffic and improving feature discriminability.To mitigate the impact of class imbalance,a Dynamic Weighted Logit-adjusted Focal Loss(DWLF)is introduced to reduce the bias toward majority classes during model optimization.Extensive experiments conducted on two public benchmark datasets demonstrate the effectiveness of the proposed approach.The proposed model achieves an overall accuracy of 90.01%on the UNSW-NB15 dataset and 97.82%on the NF-CSE-CIC-IDS2018 dataset.Experimental results indicate improved robustness under highly imbalanced data distributions,demonstrating stable performance across datasets with different traffic characteristics. 展开更多
关键词 Network intrusion detection Transformer networks convolutional neural networks autoencoder class-imbalanced
暂未订购 下载PDF
A routing strategy for non-uniform spatial network 认领 引用
14
作者 Yicong Ye Yongxiang Xia Haicheng Tu 《Chinese Physics B》 SCIE EI CAS CSCD 2026年第7期875-885,共11页
As network scales continue to expand,congestion has emerged as a critical issue in the study of complex networks,particularly in spatial networks such as transportation,aviation,and communication systems,where transmi... As network scales continue to expand,congestion has emerged as a critical issue in the study of complex networks,particularly in spatial networks such as transportation,aviation,and communication systems,where transmission is the primary function.To address this challenge,various routing strategies have been proposed to alleviate congestion by adjusting transmission paths.However,most of these strategies are based on network models that assume a uniform spatial distribution of nodes,which fails to accurately represent the non-uniform distributions observed in real-world networks.In this paper,we construct a more realistic non-uniform spatial network model and propose a novel routing strategy,termed the FH routing strategy,which integrates distance-based degree and harmonic centrality.Simulation results show that the FH strategy effectively avoids high-load nodes,promotes a more balanced load distribution,and significantly improves traffic throughput compared to traditional routing strategies.These findings provide theoretical support and practical guidance for optimizing information transmission in real-world non-uniform spatial networks. 展开更多
关键词 spatial network routing strategy network congestion complex network
暂未订购 下载PDF
Tensor Low-Rank Orthogonal Compression for Convolutional Neural Networks 认领 引用
15
作者 Yaping He Xin Luo 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第1期227-229,共3页
Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression... Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression is crucial for deploying deep neural network(DNN)models on resource-constrained embedded devices. 展开更多
关键词 model compression convolutional neural network cnn which tensor low rank orthogonal compression deep neural network dnn models embedded devices convolutional neural networks
暂未订购 下载PDF
Effects of Urbanization on Amphibian Predation Networks in Kunming 认领 引用
16
作者 Qisheng LI Pili WU +3 位作者 Yingzhi YAN Zhongping XIONG Yunfei MA Jielong ZHOU 《Asian Herpetological Research》 SCIE CAS CSCD 2026年第1期53-61,共9页
Urbanization is a significant driver of the loss of biodiversity and the disruption of ecosystems.Amphibians are especially vulnerable to the negative impact of urbanization as their life cycles and habitat requiremen... Urbanization is a significant driver of the loss of biodiversity and the disruption of ecosystems.Amphibians are especially vulnerable to the negative impact of urbanization as their life cycles and habitat requirements are complex.The present study investigated the effects of urbanization on amphibian predation networks in suburban Kunming in Yunnan,China and aimed to understand how predation network structure and stability vary with urbanization level.We constructed predation networks by analyzing the stomach contents of amphibians from 12d istinct urbanization gradients.We used the bipartite package in R to evaluate network robustness metrics such as modularity,nestedness,connectivity,and average shortest path length(ASPL).We found that urbanization level is negatively correlated with predation network connectivity(R=−0.67,Ρ=0.02),but there were no significant correlations between urbanization level and nestedness,modularity,or ASPL.Removal of the keystone species destabilized the predation networks at certain locations.The present work highlighted that maintaining prey quantity and diversity preserves predation network connectivity and stabilizes the overall network in urbanizing landscapes.It also underscored the critical role that keystone species play in sustaining network robustness.The results of this research provided insights into the ecological consequences of urbanization.They also suggested that conservation measures should protect the key species and habitats of amphibian predation networks and mitigate the negative impact of urban development on them. 展开更多
关键词 amphibian network robustness predation network urbanization
暂未订购 下载PDF
Mechanical Bonds Unlock Rapid Stress Relaxation in Covalent Adaptable Networks via Topology-preserving Chain Sliding 认领 引用
17
作者 Jun Zhao Lin Cheng +2 位作者 Zhao-Ming Zhang Wei Yu Xu-Zhou Yan 《Chinese Journal of Polymer Science》 SCIE EI CAS CSCD 2026年第7期2051-2061,共11页
Covalent adaptable networks(CANs)have emerged as versatile platforms for sustainable polymer materials,where precise control over the dissociation/exchange kinetics of dynamic covalent bonds is essential for tuning th... Covalent adaptable networks(CANs)have emerged as versatile platforms for sustainable polymer materials,where precise control over the dissociation/exchange kinetics of dynamic covalent bonds is essential for tuning their viscoelastic behaviors.Herein,we introduce a topology-preserving strategy to accelerate network relaxation by embedding slidable mechanically interlocked cross-links into vinylogous urethane-based CANs,yielding mechanically interlocked vitrimers(MIVs).The mechanically bonded junctions are constructed by incorporating kinetically stable acetoacetate-functionalized[2]pseudorotaxane cross-linkers through catalyst-free polymerization with diamines.Although exhibiting higher glass-transition temperatures than a control network with identical cross-linking density but fixed cross-links,the representative MIV-2 maintains comparable ductility while displaying greater toughness,indicating that the slidable cross-links effectively enhance chain sliding.At elevated temperatures,this chain sliding prominently accelerates stress relaxation in MIV-2,showing a substantial reduction in the apparent activation energy for vinylogous urethane exchange compared with the control(10.3 versus 21.2 kJ/mol).Unlike the control with fixed crosslinks,the chain motion enabled by mechanical bonds enhances the diffusion of dynamic covalent moieties,thereby effectively promoting bond exchange throughout the network.Owing to the associative nature of vinylogous urethane exchange,the mechanically bonded cross-links remain topologically constrained on the polymer chains during relaxation.Consequently,the accelerated stress relaxation originates from mechanical-bond-mediated chain sliding rather than defect generation,clearly distinguishing MIVs from defect-mediated dual-dynamic CANs designs commonly employed to promote relaxation.These results disclose how the mechanically interlocked structures regulate chemical reactions in cross-linked polymer networks,establishing a novel strategy of topology-engineering guided structural design for smart multidynamic polymers. 展开更多
关键词 Covalent adapable networks Dynamic covalent bonds Mechanically interlocked network Synergistic effects Stress relaxation
暂未订购 下载PDF
Personalized Differential Privacy Graph Neural Network 认领 引用
18
作者 Yanli Yuan Dian Lei +3 位作者 Chuan Zhang Zehui Xiong Chunhai Li Liehuang Zhu 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第2期498-500,共3页
Dear Editor,This letter addresses the critical challenge of preserving privacy in graph learning without compromising on data utility.Differential privacy(DP)is emerging as an effective method for privacy-preserving g... Dear Editor,This letter addresses the critical challenge of preserving privacy in graph learning without compromising on data utility.Differential privacy(DP)is emerging as an effective method for privacy-preserving graph learning.However,its application often diminishes data utility,especially for nodes with fewer neighbors in graph neural networks(GNNs). 展开更多
关键词 graph neural networks gnns personalized differential privacy graph learning privacy preservation data utility preserving privacy graph neural network
暂未订购 下载PDF
HerbGL:a network propagation and graph regularization-based framework for herb pairs prediction in traditional Chinese medicine 认领 引用
19
作者 Weixiang Liu Qian Yuan +3 位作者 Junjie Zhang Xinliang Sun Kongfa Hu Tao Yang 《Digital Chinese Medicine》 CAS CSCD 2026年第2期265-277,共13页
Objective To address the challenges of systematically identifying herb pairs in traditional Chinese medicine(TCM),we proposed HerbGL,a framework for predicting potential herb pairs that integrates network propagation ... Objective To address the challenges of systematically identifying herb pairs in traditional Chinese medicine(TCM),we proposed HerbGL,a framework for predicting potential herb pairs that integrates network propagation and graph regularization.Methods Based on the assumption that herbal actions induce subtle perturbations in biological systems,a framework named HerbGL was proposed.Random walk with restart(RWR)was first applied to the protein-protein interaction(PPI)network to reconstruct herb-specific perturbation effects and generate weighted subnetworks.Then,to quantify affinity between herb pairs,two network-proximity metrics,Closeness and PageRank,were computed from the weighted subnetworks to construct herb-pair affinity matrices.Finally,these matrices,together with known herb pairs(derived from co-occurrence analysis of TCM formulas with a threshold determined from the inflection point of the frequency distribution),were incorporated into a graph regularization model to predict potential herb pairs.Model performance was assessed through baseline comparison,ablation and robustness experiment under different ratios of positive and negative samples,using the area under the receiver operating characteristic curve(AUROC),the area under the precision-recall curve(AUPRC),accuracy,and precision as evaluation metrics.Furthermore,the predicted herb pairs were validated through both literature evidence and Gene Ontology(GO)and Kyoto Encyclopedia of Genes and Genomes(KEGG)enrichment analyses.Results The weighted subnetworks constructed by RWR provided a refined simulation of herb-specific perturbation effects,which formed the basis for subsequent affinity modeling and prediction.Analysis of herb pair co-occurrence frequencies revealed a marked change around 150,which was selected as the threshold to distinguish herb pairs from non-herb pairs.HerbGL exhibited superior predictive performance compared with baseline models(AUROC=0.9705,AUPRC=0.9555,accuracy=0.7266,precision=0.9706).Ablation results showed that removing the Closeness and PageRank metrics substantially degraded performance(AUROC=0.8191,AUPRC=0.8768),confirming their necessity.Robustness evaluation under an imbalanced positive-to-negative sample ratio of 1:5 yielded AUROC=0.9696 and AUPRC=0.8404,indicating stable predictive ability.Moreover,multiple case studies further validated the rationality of the predicted herb pairs,such as Fangfeng(Saposhnikoviae Radix)and Qingpi(Citri Reticulatae Pericarpium Viride)which are recorded in Liangpeng Huiji(《良朋汇集》,Collection of Excellent Recipes)Vol.3:Fangfeng Shengma Tang(防风升麻汤).Additionally,pathway enrichment analysis of the Renshen(Ginseng Radix et Rhizoma)and Lianqiao(Forsythiae Fructus)pair further supported the biological plausibility of their compatibility.Conclusion HerbGL offers an effective and biologically informed framework for identifying herb pairs in TCM.Beyond improving herb pair prediction,the framework also provides data support for research on herb compounds and mechanisms,thereby supporting data-driven exploration of TCM compatibility. 展开更多
关键词 Traditional Chinese medicine Herb pair Network propagation Graph regularization Network pharmacology
暂未订购 下载PDF
Deep learning-enhanced prediction of small intestinal bleeding points using long short-term memory networks 认领 引用
20
作者 Hsin-Yu Kuo Kun-Hua Lee +6 位作者 Chu-Kuang Chou Arvind Mukundan Riya Karmakar Tsung-Hsien Chen Thong-Lin Wang Ping-Hung Liu Hsiang-Chen Wang 《World Journal of Gastroenterology》 SCIE CAS 2026年第15期88-101,共14页
BACKGROUND Small intestinal bleeding(SIB)remains a significant challenge in the diagnosis of obscure gastrointestinal bleeding.While capsule endoscopy(CE)is the gold standard for visualization,manual interpretation of... BACKGROUND Small intestinal bleeding(SIB)remains a significant challenge in the diagnosis of obscure gastrointestinal bleeding.While capsule endoscopy(CE)is the gold standard for visualization,manual interpretation of the extensive video footage is labor-intensive and subject to inter-observer variability.Although convolutional neural networks(CNNs)have improved lesion detection,standard models often fail to account for temporal continuity,limiting their ability to accurately predict the specific location of bleeding points within the small bowel.AIM To develop and validate a deep learning framework integrating CNNs with long short-term memory(LSTM)networks to enhance the automated detection and precise localization of SIB.METHODS This study employed two datasets for automated bleeding detection:One from Cheng Kung University,consisting of white light imaging images from 100 patients obtained via PillCamTMSB 3 CE,and the Kvasir-Capsule Image dataset,which includes 47238 labeled images across 14 pathological categories.Nineteen continuous picture sequences were recovered,comprising 3806 bleeding photos and 3275 non-bleeding images.RESULTS Data augmentation was implemented,utilizing CNNs for feature extraction,succeeded by long short-term memory networks for prediction.The CNN model attained an accuracy of 98.6%for 10 categories and 96.7%for 2 categories.Findings demonstrate that CNN-LSTM models exhibit superior performance with expanded category sets.CONCLUSION These findings underscore the capability of deep learning models to enhance the accuracy and efficiency of CEbased gastrointestinal bleeding diagnosis,hence facilitating improved clinical decision-making. 展开更多
关键词 Capsule endoscopy Small intestinal bleeding Convolutional neural networks Long short-term memory networks Temporal modeling
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 250 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈