Objective:To investigate the effects and potential mechanisms of action of Panax notoginseng(Burk)F.H.Chen(P.notoginseng,San Qi)flowers in type 2 diabetes mellitus(T2DM)using network pharmacology,in vivo experiments,a...Objective:To investigate the effects and potential mechanisms of action of Panax notoginseng(Burk)F.H.Chen(P.notoginseng,San Qi)flowers in type 2 diabetes mellitus(T2DM)using network pharmacology,in vivo experiments,and RNA sequencing(RNA-seq).Methods:Network pharmacology analysis was performed to identify and correlate the drug targets of flower buds of P.notoginseng(PNF)with T2DM disease targets and to predict the key targets and pathways involved in the therapeutic effects of PNF in T2DM.In vivo experiments were conducted to assess the effects of PNF on glucose and lipid metabolism in mice with T2DM.RNA-seq was performed,and the results were integrated with network pharmacology data to assess the therapeutic mechanisms of PNF in T2DM.The results from transcriptomics and network pharmacology were validated using real-time polymerase chain reaction.Results:A total of 27 intersecting targets were identified by overlapping 35 drug targets with T2DM targets.Further topological analysis using the Centiscape 2.2 tool revealed five core targets,including signal transducer and activator of transcription 3(STAT3).Kyoto Encyclopedia of Genes and Genomes(KEGG)pathway analysis indicated that the JAK/STAT signaling pathway is a key mechanism underlying the therapeutic effects of PNF in T2DM.In vivo experiments confirmed that PNF effectively regulates glycolipid metabolism in a mouse model of diabetes.KEGG pathway enrichment analysis of RNA-seq data highlighted the JAK2/STAT3 and PI3K/AKT pathway as a potential mechanism.PNF high-dose(PNFH)increased the gene expression levels of PIK3R1 and AKT2,decreased the expression of PCK1,JAK2,and STAT3,and showed a trend toward increasing INSR expression without reaching statistical significance.Conclusion:PNF improves glycolipid metabolism disorders in T2DM,potentially by modulating the JAK2/STAT3 and PI3K/AKT signaling pathway.展开更多
针对燃煤电厂参与调峰负荷波动较大,出口SO_(2)浓度控制效果不佳的问题,建立了一种基于捕鱼优化算法(catch fish optimization algorithm,CFOA)优化融合神经网络的出口SO_(2)浓度预测模型。首先使用互信息算法筛选由机理分析得到的特征...针对燃煤电厂参与调峰负荷波动较大,出口SO_(2)浓度控制效果不佳的问题,建立了一种基于捕鱼优化算法(catch fish optimization algorithm,CFOA)优化融合神经网络的出口SO_(2)浓度预测模型。首先使用互信息算法筛选由机理分析得到的特征变量,并通过逐次变分模态分解对筛选后的辅助变量进行分解重构,保留相关性较大的重构分量作为输入变量。随后采用双向时间卷积网络、双向门控循环单元与多头自注意力机制构建融合神经网络模型,通过CFOA对模型超参数寻优以进一步提高精度。最后使用某660 MW燃煤电厂历史运行数据进行对比实验,实验结果表明,该模型在出口SO_(2)浓度剧烈波动的工况下仍能实现较好的预测效果。同多种模型对比,该模型具有更小的误差和更高的预测精度,体现出其在复杂变化环境中的鲁棒性和可靠性。展开更多
Severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)mutations are influenced by random and uncontrollable factors,and the risk of the next widespread epidemic remains.Dual-target drugs that synergistically act ...Severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)mutations are influenced by random and uncontrollable factors,and the risk of the next widespread epidemic remains.Dual-target drugs that synergistically act on two targets exhibit strong therapeutic effects and advantages against mutations.In this study,a novel computational workflow was developed to design dual-target SARS-CoV-2 candidate inhibitors with the Envelope protein and Main protease selected as the two target proteins.The drug-like molecules of our self-constructed 3D scaffold database were used as high-throughput molecular docking probes for feature extraction of two target protein pockets.A multi-layer perceptron(MLP)was employed to embed the binding affinities into a latent space as conditional vectors to control conditional distribution.Utilizing a conditional generative neural network,cG-SchNet,with 3D Euclidean group(E3)symmetries,the conditional probability distributions of molecular 3D structures were acquired and a set of novel SARS-CoV-2 dual-target candidate inhibitors were generated.The 1D probability,2D joint probability,and 2D cumulative probability distribution results indicate that the generated sets are significantly enhanced compared to the training set in the high binding affinity area.Among the 201 generated molecules,42 molecules exhibited a sum binding affinity exceeding 17.0 kcal/mol while 9 of them having a sum binding affinity exceeding 19.0 kcal/mol,demonstrating structure diversity along with strong dual-target affinities,good absorption,distribution,metabolism,excretion,and toxicity(ADMET)properties,and ease of synthesis.Dual-target drugs are rare and difficult to find,and our“high-throughput docking-multi-conditional generation”workflow offers a wide range of options for designing or optimizing potent dual-target SARS-CoV-2 inhibitors.展开更多
BACKGROUND Current evidence suggests that commonly used antidiabetic drugs have varying effects on cancer risk.Some antidiabetics offer protective effects against cancer,whereas others may increase risk in specific po...BACKGROUND Current evidence suggests that commonly used antidiabetic drugs have varying effects on cancer risk.Some antidiabetics offer protective effects against cancer,whereas others may increase risk in specific populations.AIM To comprehensively compare the effects of different antidiabetic drugs on the risk of various cancers in patients with type 2 diabetes mellitus(T2DM)through a systematic review and network meta-analysis.METHODS Four databases(PubMed,EMBASE,Cochrane Library,and Web of Science)were searched from their inception until April 11,2025.Published randomized controlled trials that enrolled at least 100 participants and had an intervention duration of at least 1 year were included.The inclusion criteria were studies involving adult patients with T2DM and interventions that compared different classes of antidiabetic drugs with a placebo or another antidiabetic drug.Network meta-analysis was conducted using Stata 17.0 software.Confidence in network meta-analysis was used to assess the quality of evidence regarding the risk of cancer associated with different antidiabetic drugs.RESULTS A total of 13535 articles were identified.After applying the inclusion and exclusion criteria,87 high-quality studies involving 216106 patients and 26 different drugs across seven classes were included in this study.Indirect evidence from network meta-analysis revealed some heterogeneity;however,this did not affect the reliability of the results.The results indicated that antidiabetic drugs did not increase the overall risk of cancer compared with placebo.In contrast,some antidiabetic medications demonstrated a more pronounced advantage in reducing cancer risk,such as dipeptidyl peptidase-4 inhibitors for thyroid and rectal cancers;sodium-glucose co-transporter type 2 inhibitors for lung and bronchial cancers;sulfonylureas for gastric and colon cancers;biguanides for pancreatic cancer;insulin for bladder cancer;glucagon-like peptide-1 receptor agonists for prostate,uterine,hepatocellular,renal,and hematologic cancers;and thiazolidinediones for breast cancer.CONCLUSION Antidiabetic drugs reduce cancer risk in patients with T2DM.However,given the limitations in the number and quality of the included studies,our conclusions should be interpreted with caution.More large-scale,high-quality clinical trials are required to validate our findings towards the optimization of comprehensive cancer management strategies for patients with T2DM.展开更多
Objective Epidemiological studies have shown that vitamin D status affects glycemic control in individuals with type 2 diabetes mellitus(T2DM).However,findings from intervention studies remain inconsistent.Therefore,a...Objective Epidemiological studies have shown that vitamin D status affects glycemic control in individuals with type 2 diabetes mellitus(T2DM).However,findings from intervention studies remain inconsistent.Therefore,a network meta-analysis was conducted to evaluate the comparative efficacy of various vitamin D supplementation strategies on glucose indicators in adults with T2DM.Methods Eligible studies published before September 12,2024,were retrieved from PubMed,EMBASE,Cochrane Library,and Web of Science.A network meta-analysis of multiple dosage strategies—low(<1,000 IU/day,LDS),medium(1,000–2,000 IU/day,MDS),high(2,000–4,000 IU/day,HDS),and extremely high(≥4,000 IU/day,EHDS)—was performed.Results The network meta-analysis of 40 RCTs indicated that,compared with placebo,vitamin D_(3)supplementation increased 25-hydroxyvitamin D[25-(OH)-D]levels,with pooled mean difference(MD)showing a stepwise increase from LDS to EHDS.Ranking probabilities showed a corresponding rise in 25-(OH)-D levels from LDS(46.7%)to EHDS(91.2%).EHDS reduced fasting blood glucose(FBG)relative to no treatment.LDS significantly decreased hemoglobin A1c(HbA1c),and vitamin D_(2) significantly affected FBG levels.MDS led to a significant change in fasting insulin(FIN)compared to both placebo(MD:-4.76;95%CI-8.91 to-0.61)and no treatment(MD:-7.30;95%CI-14.44 to-0.17).Conclusion The findings suggest that vitamin D supplementation may be a viable approach for improving glycemic control in adults with T2DM,with lower doses potentially offering benefit.The analysis also showed a dose-dependent increase in 25-(OH)-D levels.展开更多
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
Speech Emotion Recognition(SER)has received widespread attention as a crucial way for understanding human emotional states.However,the impact of irrelevant information on speech signals and data sparsity limit the dev...Speech Emotion Recognition(SER)has received widespread attention as a crucial way for understanding human emotional states.However,the impact of irrelevant information on speech signals and data sparsity limit the development of SER system.To address these issues,this paper proposes a framework that incorporates the Attentive Mask Residual Network(AM-ResNet)and the self-supervised learning model Wav2vec 2.0 to obtain AM-ResNet features and Wav2vec 2.0 features respectively,together with a cross-attention module to interact and fuse these two features.The AM-ResNet branch mainly consists of maximum amplitude difference detection,mask residual block,and an attention mechanism.Among them,the maximum amplitude difference detection and the mask residual block act on the pre-processing and the network,respectively,to reduce the impact of silent frames,and the attention mechanism assigns different weights to unvoiced and voiced speech to reduce redundant emotional information caused by unvoiced speech.In the Wav2vec 2.0 branch,this model is introduced as a feature extractor to obtain general speech features(Wav2vec 2.0 features)through pre-training with a large amount of unlabeled speech data,which can assist the SER task and cope with data sparsity problems.In the cross-attention module,AM-ResNet features and Wav2vec 2.0 features are interacted with and fused to obtain the cross-fused features,which are used to predict the final emotion.Furthermore,multi-label learning is also used to add ambiguous emotion utterances to deal with data limitations.Finally,experimental results illustrate the usefulness and superiority of our proposed framework over existing state-of-the-art approaches.展开更多
The increasing demand for radioauthorized applications in the 6G era necessitates enhanced monitoring and management of radio resources,particularly for precise control over the electromagnetic environment.The radio m...The increasing demand for radioauthorized applications in the 6G era necessitates enhanced monitoring and management of radio resources,particularly for precise control over the electromagnetic environment.The radio map serves as a crucial tool for describing signal strength distribution within the current electromagnetic environment.However,most existing algorithms rely on sparse measurements of radio strength,disregarding the impact of building information.In this paper,we propose a spectrum cartography(SC)algorithm that eliminates the need for relying on sparse ground-based radio strength measurements by utilizing a satellite network to collect data on buildings and transmitters.Our algorithm leverages Pix2Pix Generative Adversarial Network(GAN)to construct accurate radio maps using transmitter information within real geographical environments.Finally,simulation results demonstrate that our algorithm exhibits superior accuracy compared to previously proposed methods.展开更多
OBJECTIVE:To explore the mechanism of Tangfukang formula(糖复康方,TFK)in treating type 2 diabetes mellitus(T2DM).METHODS:We employed network pharmacology combined with experimental validation to explore the potential ...OBJECTIVE:To explore the mechanism of Tangfukang formula(糖复康方,TFK)in treating type 2 diabetes mellitus(T2DM).METHODS:We employed network pharmacology combined with experimental validation to explore the potential mechanism of TFK against T2DM.Initially,we filtered bioactive compounds with the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform(TCMSP)and Symptom Mapping(Sym Map),and gathered targets of TFK and T2DM.Subsequently,we constructed a protein-protein interaction(PPI)network,enriched core targets through Gene Ontology(GO)and Kyoto Encyclopedia of Genes and Genomes(KEGG),and adopted molecular docking to study the binding mode of compounds and the signaling pathway.Finally,we employed a KKAy mice model to investigate the effect and mechanism of TFK against T2DM.Biochemical assay,histology assay,and Western blot(WB)were used to assess the mechanism.RESULTS:There were 492 bioactive compounds of TFK screened,and 1226 overlapping targets of TFK against T2DM identified.A compound-T2DM-related target network with 997 nodes and 4439 edges was constructed.KEGG enrichment analysis identified some core pathways related to T2DM,including adenosine 5-monophosphate-activated protein kinase(AMPK)signaling pathway.Molecular docking study revealed that compounds of TFK,including citric acid,could bind to the active pocket of AMPK crystal structure with free binding energy of-4.8,-8 and-7.9,respectively.Animal experiments indicated that TFK decreased body weight,fasting blood glucose,fasting serum insulin,homeostasis model of insulin resistance,glycosylated serum protein,total cholesterol,triglyceride,and low-density lipoprotein cholesterol,and improve oral glucose tolerance test results.TFK reduced steatosis in liver tissue,and infiltration of inflammatory cells,and protected liver cells to a certain extent.WB analysis revealed that,TFK upregulated the phosphorylation of AMPK and branchedchainα-ketoacid dehydrogenase proteins.CONCLUSION:TFK has the potential to effectively manage T2DM,possibly by regulating the AMPK signaling pathway.The present study lays a new foundation for the therapeutic application of TFK in the treatment of T2DM.展开更多
基金supported by the Creation and Talent Introduction Base of Prevention and Treatment of Diabetes and Its Complications withTraditional Chinese Medicine(B20055).
文摘Objective:To investigate the effects and potential mechanisms of action of Panax notoginseng(Burk)F.H.Chen(P.notoginseng,San Qi)flowers in type 2 diabetes mellitus(T2DM)using network pharmacology,in vivo experiments,and RNA sequencing(RNA-seq).Methods:Network pharmacology analysis was performed to identify and correlate the drug targets of flower buds of P.notoginseng(PNF)with T2DM disease targets and to predict the key targets and pathways involved in the therapeutic effects of PNF in T2DM.In vivo experiments were conducted to assess the effects of PNF on glucose and lipid metabolism in mice with T2DM.RNA-seq was performed,and the results were integrated with network pharmacology data to assess the therapeutic mechanisms of PNF in T2DM.The results from transcriptomics and network pharmacology were validated using real-time polymerase chain reaction.Results:A total of 27 intersecting targets were identified by overlapping 35 drug targets with T2DM targets.Further topological analysis using the Centiscape 2.2 tool revealed five core targets,including signal transducer and activator of transcription 3(STAT3).Kyoto Encyclopedia of Genes and Genomes(KEGG)pathway analysis indicated that the JAK/STAT signaling pathway is a key mechanism underlying the therapeutic effects of PNF in T2DM.In vivo experiments confirmed that PNF effectively regulates glycolipid metabolism in a mouse model of diabetes.KEGG pathway enrichment analysis of RNA-seq data highlighted the JAK2/STAT3 and PI3K/AKT pathway as a potential mechanism.PNF high-dose(PNFH)increased the gene expression levels of PIK3R1 and AKT2,decreased the expression of PCK1,JAK2,and STAT3,and showed a trend toward increasing INSR expression without reaching statistical significance.Conclusion:PNF improves glycolipid metabolism disorders in T2DM,potentially by modulating the JAK2/STAT3 and PI3K/AKT signaling pathway.
文摘针对燃煤电厂参与调峰负荷波动较大,出口SO_(2)浓度控制效果不佳的问题,建立了一种基于捕鱼优化算法(catch fish optimization algorithm,CFOA)优化融合神经网络的出口SO_(2)浓度预测模型。首先使用互信息算法筛选由机理分析得到的特征变量,并通过逐次变分模态分解对筛选后的辅助变量进行分解重构,保留相关性较大的重构分量作为输入变量。随后采用双向时间卷积网络、双向门控循环单元与多头自注意力机制构建融合神经网络模型,通过CFOA对模型超参数寻优以进一步提高精度。最后使用某660 MW燃煤电厂历史运行数据进行对比实验,实验结果表明,该模型在出口SO_(2)浓度剧烈波动的工况下仍能实现较好的预测效果。同多种模型对比,该模型具有更小的误差和更高的预测精度,体现出其在复杂变化环境中的鲁棒性和可靠性。
基金supported by Interdisciplinary Innova-tion Project of“Bioarchaeology Laboratory”of Jilin University,China,and“MedicineþX”Interdisciplinary Innovation Team of Norman Bethune Health Science Center of Jilin University,China(Grant No.:2022JBGS05).
文摘Severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)mutations are influenced by random and uncontrollable factors,and the risk of the next widespread epidemic remains.Dual-target drugs that synergistically act on two targets exhibit strong therapeutic effects and advantages against mutations.In this study,a novel computational workflow was developed to design dual-target SARS-CoV-2 candidate inhibitors with the Envelope protein and Main protease selected as the two target proteins.The drug-like molecules of our self-constructed 3D scaffold database were used as high-throughput molecular docking probes for feature extraction of two target protein pockets.A multi-layer perceptron(MLP)was employed to embed the binding affinities into a latent space as conditional vectors to control conditional distribution.Utilizing a conditional generative neural network,cG-SchNet,with 3D Euclidean group(E3)symmetries,the conditional probability distributions of molecular 3D structures were acquired and a set of novel SARS-CoV-2 dual-target candidate inhibitors were generated.The 1D probability,2D joint probability,and 2D cumulative probability distribution results indicate that the generated sets are significantly enhanced compared to the training set in the high binding affinity area.Among the 201 generated molecules,42 molecules exhibited a sum binding affinity exceeding 17.0 kcal/mol while 9 of them having a sum binding affinity exceeding 19.0 kcal/mol,demonstrating structure diversity along with strong dual-target affinities,good absorption,distribution,metabolism,excretion,and toxicity(ADMET)properties,and ease of synthesis.Dual-target drugs are rare and difficult to find,and our“high-throughput docking-multi-conditional generation”workflow offers a wide range of options for designing or optimizing potent dual-target SARS-CoV-2 inhibitors.
基金Supported by National Natural Science Foundation of China,No.82305205Young Elite Scientists Sponsorship Program by China Association of Chinese Medicine,No.2023-QNRC2-A05+1 种基金Safeguard Project of Guang’anmen Hospital,China Academy of Chinese Medical Sciences,No.GAMHH9324001Special Program for the Training of Outstanding Young Scientific and Technological Talents Under the Basic Scientific Research Operating Expenses of the China Academy of Chinese Medical Sciences,No.ZZ18-YQ-011.
文摘BACKGROUND Current evidence suggests that commonly used antidiabetic drugs have varying effects on cancer risk.Some antidiabetics offer protective effects against cancer,whereas others may increase risk in specific populations.AIM To comprehensively compare the effects of different antidiabetic drugs on the risk of various cancers in patients with type 2 diabetes mellitus(T2DM)through a systematic review and network meta-analysis.METHODS Four databases(PubMed,EMBASE,Cochrane Library,and Web of Science)were searched from their inception until April 11,2025.Published randomized controlled trials that enrolled at least 100 participants and had an intervention duration of at least 1 year were included.The inclusion criteria were studies involving adult patients with T2DM and interventions that compared different classes of antidiabetic drugs with a placebo or another antidiabetic drug.Network meta-analysis was conducted using Stata 17.0 software.Confidence in network meta-analysis was used to assess the quality of evidence regarding the risk of cancer associated with different antidiabetic drugs.RESULTS A total of 13535 articles were identified.After applying the inclusion and exclusion criteria,87 high-quality studies involving 216106 patients and 26 different drugs across seven classes were included in this study.Indirect evidence from network meta-analysis revealed some heterogeneity;however,this did not affect the reliability of the results.The results indicated that antidiabetic drugs did not increase the overall risk of cancer compared with placebo.In contrast,some antidiabetic medications demonstrated a more pronounced advantage in reducing cancer risk,such as dipeptidyl peptidase-4 inhibitors for thyroid and rectal cancers;sodium-glucose co-transporter type 2 inhibitors for lung and bronchial cancers;sulfonylureas for gastric and colon cancers;biguanides for pancreatic cancer;insulin for bladder cancer;glucagon-like peptide-1 receptor agonists for prostate,uterine,hepatocellular,renal,and hematologic cancers;and thiazolidinediones for breast cancer.CONCLUSION Antidiabetic drugs reduce cancer risk in patients with T2DM.However,given the limitations in the number and quality of the included studies,our conclusions should be interpreted with caution.More large-scale,high-quality clinical trials are required to validate our findings towards the optimization of comprehensive cancer management strategies for patients with T2DM.
文摘Objective Epidemiological studies have shown that vitamin D status affects glycemic control in individuals with type 2 diabetes mellitus(T2DM).However,findings from intervention studies remain inconsistent.Therefore,a network meta-analysis was conducted to evaluate the comparative efficacy of various vitamin D supplementation strategies on glucose indicators in adults with T2DM.Methods Eligible studies published before September 12,2024,were retrieved from PubMed,EMBASE,Cochrane Library,and Web of Science.A network meta-analysis of multiple dosage strategies—low(<1,000 IU/day,LDS),medium(1,000–2,000 IU/day,MDS),high(2,000–4,000 IU/day,HDS),and extremely high(≥4,000 IU/day,EHDS)—was performed.Results The network meta-analysis of 40 RCTs indicated that,compared with placebo,vitamin D_(3)supplementation increased 25-hydroxyvitamin D[25-(OH)-D]levels,with pooled mean difference(MD)showing a stepwise increase from LDS to EHDS.Ranking probabilities showed a corresponding rise in 25-(OH)-D levels from LDS(46.7%)to EHDS(91.2%).EHDS reduced fasting blood glucose(FBG)relative to no treatment.LDS significantly decreased hemoglobin A1c(HbA1c),and vitamin D_(2) significantly affected FBG levels.MDS led to a significant change in fasting insulin(FIN)compared to both placebo(MD:-4.76;95%CI-8.91 to-0.61)and no treatment(MD:-7.30;95%CI-14.44 to-0.17).Conclusion The findings suggest that vitamin D supplementation may be a viable approach for improving glycemic control in adults with T2DM,with lower doses potentially offering benefit.The analysis also showed a dose-dependent increase in 25-(OH)-D levels.
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 Chongqing University of Posts and Telecommunications Ph.D.Innovative Talents Project(Grant No.BYJS202106)Chongqing Postgraduate Research Innovation Project(Grant No.CYB21203).
文摘Speech Emotion Recognition(SER)has received widespread attention as a crucial way for understanding human emotional states.However,the impact of irrelevant information on speech signals and data sparsity limit the development of SER system.To address these issues,this paper proposes a framework that incorporates the Attentive Mask Residual Network(AM-ResNet)and the self-supervised learning model Wav2vec 2.0 to obtain AM-ResNet features and Wav2vec 2.0 features respectively,together with a cross-attention module to interact and fuse these two features.The AM-ResNet branch mainly consists of maximum amplitude difference detection,mask residual block,and an attention mechanism.Among them,the maximum amplitude difference detection and the mask residual block act on the pre-processing and the network,respectively,to reduce the impact of silent frames,and the attention mechanism assigns different weights to unvoiced and voiced speech to reduce redundant emotional information caused by unvoiced speech.In the Wav2vec 2.0 branch,this model is introduced as a feature extractor to obtain general speech features(Wav2vec 2.0 features)through pre-training with a large amount of unlabeled speech data,which can assist the SER task and cope with data sparsity problems.In the cross-attention module,AM-ResNet features and Wav2vec 2.0 features are interacted with and fused to obtain the cross-fused features,which are used to predict the final emotion.Furthermore,multi-label learning is also used to add ambiguous emotion utterances to deal with data limitations.Finally,experimental results illustrate the usefulness and superiority of our proposed framework over existing state-of-the-art approaches.
文摘The increasing demand for radioauthorized applications in the 6G era necessitates enhanced monitoring and management of radio resources,particularly for precise control over the electromagnetic environment.The radio map serves as a crucial tool for describing signal strength distribution within the current electromagnetic environment.However,most existing algorithms rely on sparse measurements of radio strength,disregarding the impact of building information.In this paper,we propose a spectrum cartography(SC)algorithm that eliminates the need for relying on sparse ground-based radio strength measurements by utilizing a satellite network to collect data on buildings and transmitters.Our algorithm leverages Pix2Pix Generative Adversarial Network(GAN)to construct accurate radio maps using transmitter information within real geographical environments.Finally,simulation results demonstrate that our algorithm exhibits superior accuracy compared to previously proposed methods.
基金Tsinghua Precision Medicine Foundation:Tangfukang Plays the Therapeutic Role in Type 2 Diabetes Patients with Qi and Yin Deficiency Syndrome by Regulating the Intestinal Flora Mediated Branched-chain Amino Acids-Phosphatidylinositide 3-Kinases-Protein Kinase B Signaling Pathway(grant number 10001020105)National Natural Science Foundation of China:Tangfukang Plays the Therapeutic Role in Type 2 Diabetes Mellitus by Regulating the Intestinal Flora Mediated Adiponectin-adenosine 5-Monophosphate-activated Protein Kinase-branched-chain Amino Acids Signaling Pathway(grant number 82104812)。
文摘OBJECTIVE:To explore the mechanism of Tangfukang formula(糖复康方,TFK)in treating type 2 diabetes mellitus(T2DM).METHODS:We employed network pharmacology combined with experimental validation to explore the potential mechanism of TFK against T2DM.Initially,we filtered bioactive compounds with the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform(TCMSP)and Symptom Mapping(Sym Map),and gathered targets of TFK and T2DM.Subsequently,we constructed a protein-protein interaction(PPI)network,enriched core targets through Gene Ontology(GO)and Kyoto Encyclopedia of Genes and Genomes(KEGG),and adopted molecular docking to study the binding mode of compounds and the signaling pathway.Finally,we employed a KKAy mice model to investigate the effect and mechanism of TFK against T2DM.Biochemical assay,histology assay,and Western blot(WB)were used to assess the mechanism.RESULTS:There were 492 bioactive compounds of TFK screened,and 1226 overlapping targets of TFK against T2DM identified.A compound-T2DM-related target network with 997 nodes and 4439 edges was constructed.KEGG enrichment analysis identified some core pathways related to T2DM,including adenosine 5-monophosphate-activated protein kinase(AMPK)signaling pathway.Molecular docking study revealed that compounds of TFK,including citric acid,could bind to the active pocket of AMPK crystal structure with free binding energy of-4.8,-8 and-7.9,respectively.Animal experiments indicated that TFK decreased body weight,fasting blood glucose,fasting serum insulin,homeostasis model of insulin resistance,glycosylated serum protein,total cholesterol,triglyceride,and low-density lipoprotein cholesterol,and improve oral glucose tolerance test results.TFK reduced steatosis in liver tissue,and infiltration of inflammatory cells,and protected liver cells to a certain extent.WB analysis revealed that,TFK upregulated the phosphorylation of AMPK and branchedchainα-ketoacid dehydrogenase proteins.CONCLUSION:TFK has the potential to effectively manage T2DM,possibly by regulating the AMPK signaling pathway.The present study lays a new foundation for the therapeutic application of TFK in the treatment of T2DM.
