With the advancement of Vehicle-to-Everything(V2X)technology,efficient resource allocation in dynamic vehicular networks has become a critical challenge for achieving optimal performance.Existing methods suffer from h...With the advancement of Vehicle-to-Everything(V2X)technology,efficient resource allocation in dynamic vehicular networks has become a critical challenge for achieving optimal performance.Existing methods suffer from high computational complexity and decision latency under high-density traffic and heterogeneous network conditions.To address these challenges,this study presents an innovative framework that combines Graph Neural Networks(GNNs)with a Double Deep Q-Network(DDQN),utilizing dynamic graph structures and reinforcement learning.An adaptive neighbor sampling mechanism is introduced to dynamically select the most relevant neighbors based on interference levels and network topology,thereby improving decision accuracy and efficiency.Meanwhile,the framework models communication links as nodes and interference relationships as edges,effectively capturing the direct impact of interference on resource allocation while reducing computational complexity and preserving critical interaction information.Employing an aggregation mechanism based on the Graph Attention Network(GAT),it dynamically adjusts the neighbor sampling scope and performs attention-weighted aggregation based on node importance,ensuring more efficient and adaptive resource management.This design ensures reliable Vehicle-to-Vehicle(V2V)communication while maintaining high Vehicle-to-Infrastructure(V2I)throughput.The framework retains the global feature learning capabilities of GNNs and supports distributed network deployment,allowing vehicles to extract low-dimensional graph embeddings from local observations for real-time resource decisions.Experimental results demonstrate that the proposed method significantly reduces computational overhead,mitigates latency,and improves resource utilization efficiency in vehicular networks under complex traffic scenarios.This research not only provides a novel solution to resource allocation challenges in V2X networks but also advances the application of DDQN in intelligent transportation systems,offering substantial theoretical significance and practical value.展开更多
With the development of the Semantic Web,the number of ontologies grows exponentially and the semantic relationships between ontologies become more and more complex,understanding the true semantics of specific terms o...With the development of the Semantic Web,the number of ontologies grows exponentially and the semantic relationships between ontologies become more and more complex,understanding the true semantics of specific terms or concepts in an ontology is crucial for the matching task.At present,the main challenges facing ontology matching tasks based on representation learning methods are how to improve the embedding quality of ontology knowledge and how to integrate multiple features of ontology efficiently.Therefore,we propose an Ontology Matching Method Based on the Gated Graph Attention Model(OM-GGAT).Firstly,the semantic knowledge related to concepts in the ontology is encoded into vectors using the OWL2Vec^(*)method,and the relevant path information from the root node to the concept is embedded to understand better the true meaning of the concept itself and the relationship between concepts.Secondly,the ontology is transformed into the corresponding graph structure according to the semantic relation.Then,when extracting the features of the ontology graph nodes,different attention weights are assigned to each adjacent node of the central concept with the help of the attention mechanism idea.Finally,gated networks are designed to further fuse semantic and structural embedding representations efficiently.To verify the effectiveness of the proposed method,comparative experiments on matching tasks were carried out on public datasets.The results show that the OM-GGAT model can effectively improve the efficiency of ontology matching.展开更多
High-entropy alloy(HEA)offer tunable composition and surface structures,enabling the creation of novel active sites that enhance catalytic performance in renewable energy application.However,the inherent surface compl...High-entropy alloy(HEA)offer tunable composition and surface structures,enabling the creation of novel active sites that enhance catalytic performance in renewable energy application.However,the inherent surface complexity and tendency for elemental segregation,which results in discrepancies between bulk and surface compositions,pose challenges for direct investigation via density functional theory.To address this,Monte Carlo simulations combined with molecular dynamics were employed to model surface segregation across a broad range of elements,including Cu,Ag,Au,Pt,Pd,and Al.The analysis revealed a trend in surface segregation propensity following the order Ag>Au>Al>Cu>Pd>Pt.To capture the correlation between surface site characteristics and the free energy of multi-dentate CO_(2)reduction intermediates,a graph neural network was designed,where adsorbates were transformed into pseudo-atoms at their centers of mass.This model achieved mean absolute errors of 0.08–0.15 eV for the free energies of C_(2)intermediates,enabling precise site activity quantification.Results indicated that increasing the concentration of Cu,Ag,and Al significantly boosts activity for CO and C_(2)formation,whereas Au,Pd,and Pt exhibit negative effects.By screening stable composition space,promising HEA bulk compositions for CO,HCOOH,and C_(2)products were predicted,offering superior catalytic activity compared to pure Cu catalysts.展开更多
In this paper,we jointly design the power control and position dispatch for Multi-Unmanned Aerial Vehicle(UAV)-enabled communication in Device-to-Device(D2D)networks.Our objective is to maximize the total transmission...In this paper,we jointly design the power control and position dispatch for Multi-Unmanned Aerial Vehicle(UAV)-enabled communication in Device-to-Device(D2D)networks.Our objective is to maximize the total transmission rate of Downlink Users(DUs).Meanwhile,the Quality of Service(QoS)of all D2D users must be satisfied.We comprehensively considered the interference among D2D communications and downlink transmissions.The original problem is strongly non-convex,which requires high computational complexity for traditional optimization methods.And to make matters worse,the results are not necessarily globally optimal.In this paper,we propose a novel Graph Neural Networks(GNN)based approach that can map the considered system into a specific graph structure and achieve the optimal solution in a low complexity manner.Particularly,we first construct a GNN-based model for the proposed network,in which the transmission links and interference links are formulated as vertexes and edges,respectively.Then,by taking the channel state information and the coordinates of ground users as the inputs,as well as the location of UAVs and the transmission power of all transmitters as outputs,we obtain the mapping from inputs to outputs through training the parameters of GNN.Simulation results verified that the way to maximize the total transmission rate of DUs can be extracted effectively via the training on samples.Moreover,it also shows that the performance of proposed GNN-based method is better than that of traditional means.展开更多
In this paper, a sufficient condition for a balanced bipartite graph to contain a 2-factor F is given. We show that every balanced bipartite graph of order 2n (n≥6)and e(G)>n2−2n+4contains a 2-factor with k compon...In this paper, a sufficient condition for a balanced bipartite graph to contain a 2-factor F is given. We show that every balanced bipartite graph of order 2n (n≥6)and e(G)>n2−2n+4contains a 2-factor with k components, 2d1-cycle, ⋯, 2dk-cycle, if one of the following is satisfied: (1) k=2, δ(G)≥2and d1−2≥d2≥2;(2) k=3, δ(G)≥d3+2and d1−2≥d2≥d3≥4. In particular, this extends one result of Moon and Moser in 1963 under condition (1).展开更多
In this paper,we prove that there does not exist an r-UPC[2]-graph for each r≥5 and there does not exist an r-UPC[C_t^2]-graph for each r≥3,where t is the number of bridges in a graph and C_t^2 is the number of comb...In this paper,we prove that there does not exist an r-UPC[2]-graph for each r≥5 and there does not exist an r-UPC[C_t^2]-graph for each r≥3,where t is the number of bridges in a graph and C_t^2 is the number of combinations of t bridges taken 2 at a time.展开更多
The performance of the graph-based scheduling for device-to-device communications overlaying cellular networks is studied. The graph-based scheduling consists of two stages, the frequency assignment stage and the time...The performance of the graph-based scheduling for device-to-device communications overlaying cellular networks is studied. The graph-based scheduling consists of two stages, the frequency assignment stage and the time slot scheduling stage. For such scheduling, a theoretical method to analyze the average spectrum efficiency of the D2D subsystem is proposed. The method consists of three steps. First, the frequency assignment stage is analyzed and the approximate formula of the average number of the D2D links which are assigned the same frequency is derived. Secondly, the time slot scheduling stage is analyzed and the approximate formula of the average probability of a D2D link being scheduled in a time slot is derived. Thirdly, the average spectrum efficiency of the D2D subsystem is analyzed and the corresponding approximate formula is derived. Analysis results show that the average spectrum efficiency of the D2D subsystem is approximately inversely linearly proportional to the second- order origin moment of the normalized broadcast radius of D2D links. Simulation results show that the proposed method can correctly predict the average spectrum efficiency of the D2D subsystem.展开更多
BACKGROUND Cognitive decline in type 2 diabetes mellitus(T2DM)occurs years before the onset of clinical symptoms.Early detection of this incipient cognitive decline stage,which is T2DM without mild cognitive impairmen...BACKGROUND Cognitive decline in type 2 diabetes mellitus(T2DM)occurs years before the onset of clinical symptoms.Early detection of this incipient cognitive decline stage,which is T2DM without mild cognitive impairment,is critical for clinical intervention,yet it remains elusive and challenging to identify.AIM To identify structural changes in the brains of T2DM patients without cognitive impairment to gain insights into the early-stage cognitive decline.METHODS Using diffusion tensor imaging(DTI),we constructed structural brain networks in 47 T2DM patients and 47 age-/sex-matched healthy controls.Machine learning models incorporating connectivity features were developed to classify T2DM brains and predict disease duration.RESULTS T2DM patients exhibited reduced global/local efficiency and small-worldness,alongside weakened connectivity in cortical regions but enhanced subcortical-frontal connections,suggesting compensatory mechanisms.A classification model leveraging 18 connectivity features achieved 92.5%accuracy in distinguishing T2DM brains.Structural connectivity patterns further predicted disease onset with an error of±1.9 years.CONCLUSION Our findings reveal early-stage brain network reorganization in T2DM,highlighting subcortical-frontal connectivity as a compensatory biomarker.The high-accuracy models demonstrate the potential of DTI-based biomarkers for preclinical cognitive decline detection.展开更多
Objective To improve the accuracy and professionalism of question-answering(QA)model in traditional Chinese medicine(TCM)lung cancer by integrating large language models with structured knowledge graphs using the know...Objective To improve the accuracy and professionalism of question-answering(QA)model in traditional Chinese medicine(TCM)lung cancer by integrating large language models with structured knowledge graphs using the knowledge graph(KG)to text-enhanced retrievalaugmented generation(KG2TRAG)method.Methods The TCM lung cancer model(TCMLCM)was constructed by fine-tuning Chat-GLM2-6B on the specialized datasets Tianchi TCM,HuangDi,and ShenNong-TCM-Dataset,as well as a TCM lung cancer KG.The KG2TRAG method was applied to enhance the knowledge retrieval,which can convert KG triples into natural language text via ChatGPT-aided linearization,leveraging large language models(LLMs)for context-aware reasoning.For a comprehensive comparison,MedicalGPT,HuatuoGPT,and BenTsao were selected as the baseline models.Performance was evaluated using bilingual evaluation understudy(BLEU),recall-oriented understudy for gisting evaluation(ROUGE),accuracy,and the domain-specific TCM-LCEval metrics,with validation from TCM oncology experts assessing answer accuracy,professionalism,and usability.Results The TCMLCM model achieved the optimal performance across all metrics,including a BLEU score of 32.15%,ROUGE-L of 59.08%,and an accuracy rate of 79.68%.Notably,in the TCM-LCEval assessment specific to the field of TCM,its performance was 3%−12%higher than that of the baseline model.Expert evaluations highlighted superior performance in accuracy and professionalism.Conclusion TCMLCM can provide an innovative solution for TCM lung cancer QA,demonstrating the feasibility of integrating structured KGs with LLMs.This work advances intelligent TCM healthcare tools and lays a foundation for future AI-driven applications in traditional medicine.展开更多
A graph has exactly two main eigenvalues if and only if it is a 2-walk linear graph.In this paper,we show some necessary conditions that a 2-walk（a,b）-linear graph must obey.Using these conditions and some basic the...A graph has exactly two main eigenvalues if and only if it is a 2-walk linear graph.In this paper,we show some necessary conditions that a 2-walk（a,b）-linear graph must obey.Using these conditions and some basic theorems in graph theory,we characterize all 2-walk linear graphs with small cyclic graphs without pendants.The results are given in sort on unicyclic,bicyclic,tricyclic graphs.展开更多
基金Project ZR2023MF111 supported by Shandong Provincial Natural Science Foundation。
文摘With the advancement of Vehicle-to-Everything(V2X)technology,efficient resource allocation in dynamic vehicular networks has become a critical challenge for achieving optimal performance.Existing methods suffer from high computational complexity and decision latency under high-density traffic and heterogeneous network conditions.To address these challenges,this study presents an innovative framework that combines Graph Neural Networks(GNNs)with a Double Deep Q-Network(DDQN),utilizing dynamic graph structures and reinforcement learning.An adaptive neighbor sampling mechanism is introduced to dynamically select the most relevant neighbors based on interference levels and network topology,thereby improving decision accuracy and efficiency.Meanwhile,the framework models communication links as nodes and interference relationships as edges,effectively capturing the direct impact of interference on resource allocation while reducing computational complexity and preserving critical interaction information.Employing an aggregation mechanism based on the Graph Attention Network(GAT),it dynamically adjusts the neighbor sampling scope and performs attention-weighted aggregation based on node importance,ensuring more efficient and adaptive resource management.This design ensures reliable Vehicle-to-Vehicle(V2V)communication while maintaining high Vehicle-to-Infrastructure(V2I)throughput.The framework retains the global feature learning capabilities of GNNs and supports distributed network deployment,allowing vehicles to extract low-dimensional graph embeddings from local observations for real-time resource decisions.Experimental results demonstrate that the proposed method significantly reduces computational overhead,mitigates latency,and improves resource utilization efficiency in vehicular networks under complex traffic scenarios.This research not only provides a novel solution to resource allocation challenges in V2X networks but also advances the application of DDQN in intelligent transportation systems,offering substantial theoretical significance and practical value.
基金supported by the National Natural Science Foundation of China(grant numbers 62267005 and 42365008)the Guangxi Collaborative Innovation Center of Multi-Source Information Integration and Intelligent Processing.
文摘With the development of the Semantic Web,the number of ontologies grows exponentially and the semantic relationships between ontologies become more and more complex,understanding the true semantics of specific terms or concepts in an ontology is crucial for the matching task.At present,the main challenges facing ontology matching tasks based on representation learning methods are how to improve the embedding quality of ontology knowledge and how to integrate multiple features of ontology efficiently.Therefore,we propose an Ontology Matching Method Based on the Gated Graph Attention Model(OM-GGAT).Firstly,the semantic knowledge related to concepts in the ontology is encoded into vectors using the OWL2Vec^(*)method,and the relevant path information from the root node to the concept is embedded to understand better the true meaning of the concept itself and the relationship between concepts.Secondly,the ontology is transformed into the corresponding graph structure according to the semantic relation.Then,when extracting the features of the ontology graph nodes,different attention weights are assigned to each adjacent node of the central concept with the help of the attention mechanism idea.Finally,gated networks are designed to further fuse semantic and structural embedding representations efficiently.To verify the effectiveness of the proposed method,comparative experiments on matching tasks were carried out on public datasets.The results show that the OM-GGAT model can effectively improve the efficiency of ontology matching.
文摘High-entropy alloy(HEA)offer tunable composition and surface structures,enabling the creation of novel active sites that enhance catalytic performance in renewable energy application.However,the inherent surface complexity and tendency for elemental segregation,which results in discrepancies between bulk and surface compositions,pose challenges for direct investigation via density functional theory.To address this,Monte Carlo simulations combined with molecular dynamics were employed to model surface segregation across a broad range of elements,including Cu,Ag,Au,Pt,Pd,and Al.The analysis revealed a trend in surface segregation propensity following the order Ag>Au>Al>Cu>Pd>Pt.To capture the correlation between surface site characteristics and the free energy of multi-dentate CO_(2)reduction intermediates,a graph neural network was designed,where adsorbates were transformed into pseudo-atoms at their centers of mass.This model achieved mean absolute errors of 0.08–0.15 eV for the free energies of C_(2)intermediates,enabling precise site activity quantification.Results indicated that increasing the concentration of Cu,Ag,and Al significantly boosts activity for CO and C_(2)formation,whereas Au,Pd,and Pt exhibit negative effects.By screening stable composition space,promising HEA bulk compositions for CO,HCOOH,and C_(2)products were predicted,offering superior catalytic activity compared to pure Cu catalysts.
基金supported in part by the National Natural Science Foundation of China(61901231)in part by the National Natural Science Foundation of China(61971238)+3 种基金in part by the Natural Science Foundation of Jiangsu Province of China(BK20180757)in part by the open project of the Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space,Ministry of Industry and Information Technology(KF20202102)in part by the China Postdoctoral Science Foundation under Grant(2020M671480)in part by the Jiangsu Planned Projects for Postdoctoral Research Funds(2020z295).
文摘In this paper,we jointly design the power control and position dispatch for Multi-Unmanned Aerial Vehicle(UAV)-enabled communication in Device-to-Device(D2D)networks.Our objective is to maximize the total transmission rate of Downlink Users(DUs).Meanwhile,the Quality of Service(QoS)of all D2D users must be satisfied.We comprehensively considered the interference among D2D communications and downlink transmissions.The original problem is strongly non-convex,which requires high computational complexity for traditional optimization methods.And to make matters worse,the results are not necessarily globally optimal.In this paper,we propose a novel Graph Neural Networks(GNN)based approach that can map the considered system into a specific graph structure and achieve the optimal solution in a low complexity manner.Particularly,we first construct a GNN-based model for the proposed network,in which the transmission links and interference links are formulated as vertexes and edges,respectively.Then,by taking the channel state information and the coordinates of ground users as the inputs,as well as the location of UAVs and the transmission power of all transmitters as outputs,we obtain the mapping from inputs to outputs through training the parameters of GNN.Simulation results verified that the way to maximize the total transmission rate of DUs can be extracted effectively via the training on samples.Moreover,it also shows that the performance of proposed GNN-based method is better than that of traditional means.
文摘In this paper, a sufficient condition for a balanced bipartite graph to contain a 2-factor F is given. We show that every balanced bipartite graph of order 2n (n≥6)and e(G)>n2−2n+4contains a 2-factor with k components, 2d1-cycle, ⋯, 2dk-cycle, if one of the following is satisfied: (1) k=2, δ(G)≥2and d1−2≥d2≥2;(2) k=3, δ(G)≥d3+2and d1−2≥d2≥d3≥4. In particular, this extends one result of Moon and Moser in 1963 under condition (1).
文摘In this paper,we prove that there does not exist an r-UPC[2]-graph for each r≥5 and there does not exist an r-UPC[C_t^2]-graph for each r≥3,where t is the number of bridges in a graph and C_t^2 is the number of combinations of t bridges taken 2 at a time.
基金The National Natural Science Foundation of China(No.61571111)the National High Technology Research and Development Program of China(863 Program)(No.2014AA01A703,2015AA01A706)the Fundamental Research Funds for the Central Universities of China(No.2242016K40098)
文摘The performance of the graph-based scheduling for device-to-device communications overlaying cellular networks is studied. The graph-based scheduling consists of two stages, the frequency assignment stage and the time slot scheduling stage. For such scheduling, a theoretical method to analyze the average spectrum efficiency of the D2D subsystem is proposed. The method consists of three steps. First, the frequency assignment stage is analyzed and the approximate formula of the average number of the D2D links which are assigned the same frequency is derived. Secondly, the time slot scheduling stage is analyzed and the approximate formula of the average probability of a D2D link being scheduled in a time slot is derived. Thirdly, the average spectrum efficiency of the D2D subsystem is analyzed and the corresponding approximate formula is derived. Analysis results show that the average spectrum efficiency of the D2D subsystem is approximately inversely linearly proportional to the second- order origin moment of the normalized broadcast radius of D2D links. Simulation results show that the proposed method can correctly predict the average spectrum efficiency of the D2D subsystem.
基金Supported by National Natural Science Foundation of China,No.82104698,No.82330058,No.T2341014,and No.32200923.
文摘BACKGROUND Cognitive decline in type 2 diabetes mellitus(T2DM)occurs years before the onset of clinical symptoms.Early detection of this incipient cognitive decline stage,which is T2DM without mild cognitive impairment,is critical for clinical intervention,yet it remains elusive and challenging to identify.AIM To identify structural changes in the brains of T2DM patients without cognitive impairment to gain insights into the early-stage cognitive decline.METHODS Using diffusion tensor imaging(DTI),we constructed structural brain networks in 47 T2DM patients and 47 age-/sex-matched healthy controls.Machine learning models incorporating connectivity features were developed to classify T2DM brains and predict disease duration.RESULTS T2DM patients exhibited reduced global/local efficiency and small-worldness,alongside weakened connectivity in cortical regions but enhanced subcortical-frontal connections,suggesting compensatory mechanisms.A classification model leveraging 18 connectivity features achieved 92.5%accuracy in distinguishing T2DM brains.Structural connectivity patterns further predicted disease onset with an error of±1.9 years.CONCLUSION Our findings reveal early-stage brain network reorganization in T2DM,highlighting subcortical-frontal connectivity as a compensatory biomarker.The high-accuracy models demonstrate the potential of DTI-based biomarkers for preclinical cognitive decline detection.
基金Postgraduate Research&Practice Innovation Program of Jiangsu Province(KYCX24_2145).
文摘Objective To improve the accuracy and professionalism of question-answering(QA)model in traditional Chinese medicine(TCM)lung cancer by integrating large language models with structured knowledge graphs using the knowledge graph(KG)to text-enhanced retrievalaugmented generation(KG2TRAG)method.Methods The TCM lung cancer model(TCMLCM)was constructed by fine-tuning Chat-GLM2-6B on the specialized datasets Tianchi TCM,HuangDi,and ShenNong-TCM-Dataset,as well as a TCM lung cancer KG.The KG2TRAG method was applied to enhance the knowledge retrieval,which can convert KG triples into natural language text via ChatGPT-aided linearization,leveraging large language models(LLMs)for context-aware reasoning.For a comprehensive comparison,MedicalGPT,HuatuoGPT,and BenTsao were selected as the baseline models.Performance was evaluated using bilingual evaluation understudy(BLEU),recall-oriented understudy for gisting evaluation(ROUGE),accuracy,and the domain-specific TCM-LCEval metrics,with validation from TCM oncology experts assessing answer accuracy,professionalism,and usability.Results The TCMLCM model achieved the optimal performance across all metrics,including a BLEU score of 32.15%,ROUGE-L of 59.08%,and an accuracy rate of 79.68%.Notably,in the TCM-LCEval assessment specific to the field of TCM,its performance was 3%−12%higher than that of the baseline model.Expert evaluations highlighted superior performance in accuracy and professionalism.Conclusion TCMLCM can provide an innovative solution for TCM lung cancer QA,demonstrating the feasibility of integrating structured KGs with LLMs.This work advances intelligent TCM healthcare tools and lays a foundation for future AI-driven applications in traditional medicine.
基金Supported by the National Natural Science Foundation of China (10671081)
文摘A graph has exactly two main eigenvalues if and only if it is a 2-walk linear graph.In this paper,we show some necessary conditions that a 2-walk（a,b）-linear graph must obey.Using these conditions and some basic theorems in graph theory,we characterize all 2-walk linear graphs with small cyclic graphs without pendants.The results are given in sort on unicyclic,bicyclic,tricyclic graphs.
