The fifth-generation (5G) communication requires a highly accurate estimation of the channel state information (CSI)to take advantage of the massive multiple-input multiple-output(MIMO) system. However, traditional ch...The fifth-generation (5G) communication requires a highly accurate estimation of the channel state information (CSI)to take advantage of the massive multiple-input multiple-output(MIMO) system. However, traditional channel estimation methods do not always yield reliable estimates. The methodology of this paper consists of deep residual shrinkage network (DRSN)neural network-based method that is used to solve this problem.Thus, the channel estimation approach, based on DRSN with its learning ability of noise-containing data, is first introduced. Then,the DRSN is used to train the noise reduction process based on the results of the least square (LS) channel estimation while applying the pilot frequency subcarriers, where the initially estimated subcarrier channel matrix is considered as a three-dimensional tensor of the DRSN input. Afterward, a mixed signal to noise ratio (SNR) training data strategy is proposed based on the learning ability of DRSN under different SNRs. Moreover, a joint mixed scenario training strategy is carried out to test the multi scenarios robustness of DRSN. As for the findings, the numerical results indicate that the DRSN method outperforms the spatial-frequency-temporal convolutional neural networks (SF-CNN)with similar computational complexity and achieves better advantages in the full SNR range than the minimum mean squared error (MMSE) estimator with a limited dataset. Moreover, the DRSN approach shows robustness in different propagation environments.展开更多
Hypersonic Glide Vehicles(HGVs)are advanced aircraft that can achieve extremely high speeds(generally over 5 Mach)and maneuverability within the Earth's atmosphere.HGV trajectory prediction is crucial for effectiv...Hypersonic Glide Vehicles(HGVs)are advanced aircraft that can achieve extremely high speeds(generally over 5 Mach)and maneuverability within the Earth's atmosphere.HGV trajectory prediction is crucial for effective defense planning and interception strategies.In recent years,HGV trajectory prediction methods based on deep learning have the great potential to significantly enhance prediction accuracy and efficiency.However,it's still challenging to strike a balance between improving prediction performance and reducing computation costs of the deep learning trajectory prediction models.To solve this problem,we propose a new deep learning framework(FECA-LSMN)for efficient HGV trajectory prediction.The model first uses a Frequency Enhanced Channel Attention(FECA)module to facilitate the fusion of different HGV trajectory features,and then subsequently employs a Light Sampling-oriented Multi-Layer Perceptron Network(LSMN)based on simple MLP-based structures to extract long/shortterm HGV trajectory features for accurate trajectory prediction.Also,we employ a new data normalization method called reversible instance normalization(RevIN)to enhance the prediction accuracy and training stability of the network.Compared to other popular trajectory prediction models based on LSTM,GRU and Transformer,our FECA-LSMN model achieves leading or comparable performance in terms of RMSE,MAE and MAPE metrics while demonstrating notably faster computation time.The ablation experiments show that the incorporation of the FECA module significantly improves the prediction performance of the network.The RevIN data normalization technique outperforms traditional min-max normalization as well.展开更多
To address the shortcomings of single-step decision making in the existing deep reinforcement learning based unmanned aerial vehicle(UAV)real-time path planning problem,a real-time UAV path planning algorithm based on...To address the shortcomings of single-step decision making in the existing deep reinforcement learning based unmanned aerial vehicle(UAV)real-time path planning problem,a real-time UAV path planning algorithm based on long shortterm memory(RPP-LSTM)network is proposed,which combines the memory characteristics of recurrent neural network(RNN)and the deep reinforcement learning algorithm.LSTM networks are used in this algorithm as Q-value networks for the deep Q network(DQN)algorithm,which makes the decision of the Q-value network has some memory.Thanks to LSTM network,the Q-value network can use the previous environmental information and action information which effectively avoids the problem of single-step decision considering only the current environment.Besides,the algorithm proposes a hierarchical reward and punishment function for the specific problem of UAV real-time path planning,so that the UAV can more reasonably perform path planning.Simulation verification shows that compared with the traditional feed-forward neural network(FNN)based UAV autonomous path planning algorithm,the RPP-LSTM proposed in this paper can adapt to more complex environments and has significantly improved robustness and accuracy when performing UAV real-time path planning.展开更多
It is important to calculate the reachable domain(RD)of the manned lunar mission to evaluate whether a lunar landing site could be reached by the spacecraft. In this paper, the RD of free return orbits is quickly eval...It is important to calculate the reachable domain(RD)of the manned lunar mission to evaluate whether a lunar landing site could be reached by the spacecraft. In this paper, the RD of free return orbits is quickly evaluated and calculated via the classification and regression neural networks. An efficient databasegeneration method is developed for obtaining eight types of free return orbits and then the RD is defined by the orbit’s inclination and right ascension of ascending node(RAAN) at the perilune. A classify neural network and a regression network are trained respectively. The former is built for classifying the type of the RD, and the latter is built for calculating the inclination and RAAN of the RD. The simulation results show that two neural networks are well trained. The classification model has an accuracy of more than 99% and the mean square error of the regression model is less than 0.01°on the test set. Moreover, a serial strategy is proposed to combine the two surrogate models and a recognition tool is built to evaluate whether a lunar site could be reached. The proposed deep learning method shows the superiority in computation efficiency compared with the traditional double two-body model.展开更多
Projective synchronization problems of a drive system and a particular response network were investigated,where the drive system is an arbitrary system with n+1 dimensions;it may be a linear or nonlinear system,and ev...Projective synchronization problems of a drive system and a particular response network were investigated,where the drive system is an arbitrary system with n+1 dimensions;it may be a linear or nonlinear system,and even a chaotic or hyperchaotic system,the response network is complex system coupled by N nodes,and every node is showed by the approximately linear part of the drive system.Only controlling any one node of the response network by designed controller can achieve the projective synchronization.Some numerical examples were employed to verify the effectiveness and correctness of the designed controller.展开更多
The burgeoning development of nanomedicine has provided state-of-the-art technologies and innovative methodologies for contemporary biomedical research,presenting unprecedented opportunities for resolving pivotal biom...The burgeoning development of nanomedicine has provided state-of-the-art technologies and innovative methodologies for contemporary biomedical research,presenting unprecedented opportunities for resolving pivotal biomedical challenges.Nanomaterials possess distinctive structures and properties.Through the exploration of the fabrication of emerging nanomedicines,multiple functions can be integrated to enable more precise diagnosis and treatment,thereby compensating for the limitations of traditional treatment modalities.Among various substances,polyphenols are natural organic compounds classified as plant secondary metabolites and are ubiquitously present in vegetables,teas,and other plants.Polyphenols are rich in active groups,including hydroxyl,carboxyl,amino,and conjugated double bonds.They exhibit robust adhesion,antioxidant,anti-inflammatory,and antibacterial biological activities and are extensively applied in pharmaceutical formulations.Additionally,polyphenols are characterized by their low cost,ready availability,and do not necessitate intricate chemical synthesis processes.Nevertheless,when natural polyphenol-based nanomedicines are utilized in isolation,they encounter several issues.These include poor water solubility,feeble stability,low bioavailability,the requirement for high dosages,and difficulties in precisely reaching the site of action.To address these concerns,researchers have developed nanomedicines by combining metal ions and functional ligands through metal coordination strategies.Nanomaterials,owing to their unique electronic and optical properties,have been successfully introduced into the realm of medical biology.Nano preparations not only enhance the stability of natural products but also endow them with targeting capabilities,thus enabling precise drug delivery.Polyphenols can further synergize with metal ions,anti-cancer drugs,or photosensitizers via supramolecular interactions to achieve multifunctional synergistic therapies,such as targeted drug delivery,efficacy enhancement,and the construction of engineering scaffolds.Metal-Polyphenol Coordination Polymers(MPCPs),composed of metal ions and phenolic ligands,are regarded as ideal nanoplatforms for disease diagnosis and treatment.In recent years,MPCPs have attracted extensive research in the biomedical field on account of their advantages,including facile synthesis,adjustable structure,excellent biocompatibility,and pH responsiveness.In this review,the classification and preparation strategies of MPCPs were systematically presented.Subsequently,their remarkable achievements in biomedical domains,such as bioimaging,biosensing,drug delivery,tumor therapy,and antimicrobial applications were highlighted.Finally,the principal limitations and prospects of MPCPs were comprehensi vely discussed.展开更多
Human disturbance activities is one of the main reasons for inducing geohazards.Ecological impact assessment metrics of roads are inconsistent criteria and multiple.From the perspective of visual observation,the envir...Human disturbance activities is one of the main reasons for inducing geohazards.Ecological impact assessment metrics of roads are inconsistent criteria and multiple.From the perspective of visual observation,the environment damage can be shown through detecting the uncovered area of vegetation in the images along road.To realize this,an end-to-end environment damage detection model based on convolutional neural network is proposed.A 50-layer residual network is used to extract feature map.The initial parameters are optimized by transfer learning.An example is shown by this method.The dataset including cliff and landslide damage are collected by us along road in Shennongjia national forest park.Results show 0.4703 average precision(AP)rating for cliff damage and 0.4809 average precision(AP)rating for landslide damage.Compared with YOLOv3,our model shows a better accuracy in cliff and landslide detection although a certain amount of speed is sacrificed.展开更多
Objective Traditional Chinese medicine(TCM)constitutes a valuable cultural heritage and an important source of antitumor compounds.Poria(Poria cocos(Schw.)Wolf),the dried sclerotium of a polyporaceae fungus,was first ...Objective Traditional Chinese medicine(TCM)constitutes a valuable cultural heritage and an important source of antitumor compounds.Poria(Poria cocos(Schw.)Wolf),the dried sclerotium of a polyporaceae fungus,was first documented in Shennong’s Classic of Materia Medica and has been used therapeutically and dietarily in China for millennia.Traditionally recognized for its diuretic,spleen-tonifying,and sedative properties,modern pharmacological studies confirm that Poria exhibits antioxidant,anti-inflammatory,antibacterial,and antitumor activities.Pachymic acid(PA;a triterpenoid with the chemical structure 3β-acetyloxy-16α-hydroxy-lanosta-8,24(31)-dien-21-oic acid),isolated from Poria,is a principal bioactive constituent.Emerging evidence indicates PA exerts antitumor effects through multiple mechanisms,though these remain incompletely characterized.Neuroblastoma(NB),a highly malignant pediatric extracranial solid tumor accounting for 15%of childhood cancer deaths,urgently requires safer therapeutics due to the limitations of current treatments.Although PA shows multi-mechanistic antitumor potential,its efficacy against NB remains uncharacterized.This study systematically investigated the potential molecular targets and mechanisms underlying the anti-NB effects of PA by integrating network pharmacology-based target prediction with experimental validation of multi-target interactions through molecular docking,dynamic simulations,and in vitro assays,aimed to establish a novel perspective on PA’s antitumor activity and explore its potential clinical implications for NB treatment by integrating computational predictions with biological assays.Methods This study employed network pharmacology to identify potential targets of PA in NB,followed by validation using molecular docking,molecular dynamics(MD)simulations,MM/PBSA free energy analysis,RT-qPCR and Western blot experiments.Network pharmacology analysis included target screening via TCMSP,GeneCards,DisGeNET,SwissTargetPrediction,SuperPred,and PharmMapper.Subsequently,potential targets were predicted by intersecting the results from these databases via Venn analysis.Following target prediction,topological analysis was performed to identify key targets using Cytoscape software.Molecular docking was conducted using AutoDock Vina,with the binding pocket defined based on crystal structures.MD simulations were performed for 100 ns using GROMACS,and RMSD,RMSF,SASA,and hydrogen bonding dynamics were analyzed.MM/PBSA calculations were carried out to estimate the binding free energy of each protein-ligand complex.In vitro validation included RT-qPCR and Western blot,with GAPDH used as an internal control.Results The CCK-8 assay demonstrated a concentration-dependent inhibitory effect of PA on NB cell viability.GO analysis suggested that the anti-NB activity of PA might involve cellular response to chemical stress,vesicle lumen,and protein tyrosine kinase activity.KEGG pathway enrichment analysis suggested that the anti-NB activity of PA might involve the PI3K/AKT,MAPK,and Ras signaling pathways.Molecular docking and MD simulations revealed stable binding interactions between PA and the core target proteins AKT1,EGFR,SRC,and HSP90AA1.RT-qPCR and Western blot analyses further confirmed that PA treatment significantly decreased the mRNA and protein expression of AKT1,EGFR,and SRC while increasing the HSP90AA1 mRNA and protein levels.Conclusion It was suggested that PA may exert its anti-NB effects by inhibiting AKT1,EGFR,and SRC expression,potentially modulating the PI3K/AKT signaling pathway.These findings provide crucial evidence supporting PA’s development as a therapeutic candidate for NB.展开更多
Social interaction with peer pressure is widely studied in social network analysis.Game theory can be utilized to model dynamic social interaction,and one class of game network models assumes that people’s decision p...Social interaction with peer pressure is widely studied in social network analysis.Game theory can be utilized to model dynamic social interaction,and one class of game network models assumes that people’s decision payoff functions hinge on individual covariates and the choices of their friends.However,peer pressure would be misidentified and induce a non-negligible bias when incomplete covariates are involved in the game model.For this reason,we develop a generalized constant peer effects model based on homogeneity structure in dynamic social networks.The new model can effectively avoid bias through homogeneity pursuit and can be applied to a wider range of scenarios.To estimate peer pressure in the model,we first present two algorithms based on the initialize expand merge method and the polynomial-time twostage method to estimate homogeneity parameters.Then we apply the nested pseudo-likelihood method and obtain consistent estimators of peer pressure.Simulation evaluations show that our proposed methodology can achieve desirable and effective results in terms of the community misclassification rate and parameter estimation error.We also illustrate the advantages of our model in the empirical analysis when compared with a benchmark model.展开更多
In this paper,we propose a neural network approach to learn the parameters of a class of stochastic Lotka-Volterra systems.Approximations of the mean and covariance matrix of the observational variables are obtained f...In this paper,we propose a neural network approach to learn the parameters of a class of stochastic Lotka-Volterra systems.Approximations of the mean and covariance matrix of the observational variables are obtained from the Euler-Maruyama discretization of the underlying stochastic differential equations(SDEs),based on which the loss function is built.The stochastic gradient descent method is applied in the neural network training.Numerical experiments demonstrate the effectiveness of our method.展开更多
In the field of image processing,the analysis of Synthetic Aperture Radar(SAR)images is crucial due to its broad range of applications.However,SAR images are often affected by coherent speckle noise,which significantl...In the field of image processing,the analysis of Synthetic Aperture Radar(SAR)images is crucial due to its broad range of applications.However,SAR images are often affected by coherent speckle noise,which significantly degrades image quality.Traditional denoising methods,typically based on filter techniques,often face challenges related to inefficiency and limited adaptability.To address these limitations,this study proposes a novel SAR image denoising algorithm based on an enhanced residual network architecture,with the objective of enhancing the utility of SAR imagery in complex electromagnetic environments.The proposed algorithm integrates residual network modules,which directly process the noisy input images to generate denoised outputs.This approach not only reduces computational complexity but also mitigates the difficulties associated with model training.By combining the Transformer module with the residual block,the algorithm enhances the network's ability to extract global features,offering superior feature extraction capabilities compared to CNN-based residual modules.Additionally,the algorithm employs the adaptive activation function Meta-ACON,which dynamically adjusts the activation patterns of neurons,thereby improving the network's feature extraction efficiency.The effectiveness of the proposed denoising method is empirically validated using real SAR images from the RSOD dataset.The proposed algorithm exhibits remarkable performance in terms of EPI,SSIM,and ENL,while achieving a substantial enhancement in PSNR when compared to traditional and deep learning-based algorithms.The PSNR performance is enhanced by over twofold.Moreover,the evaluation of the MSTAR SAR dataset substantiates the algorithm's robustness and applicability in SAR denoising tasks,with a PSNR of 25.2021 being attained.These findings underscore the efficacy of the proposed algorithm in mitigating speckle noise while preserving critical features in SAR imagery,thereby enhancing its quality and usability in practical scenarios.展开更多
Low Earth orbit(LEO)satellite networks exhibit distinct characteristics,e.g.,limited resources of individual satellite nodes and dynamic network topology,which have brought many challenges for routing algorithms.To sa...Low Earth orbit(LEO)satellite networks exhibit distinct characteristics,e.g.,limited resources of individual satellite nodes and dynamic network topology,which have brought many challenges for routing algorithms.To satisfy quality of service(QoS)requirements of various users,it is critical to research efficient routing strategies to fully utilize satellite resources.This paper proposes a multi-QoS information optimized routing algorithm based on reinforcement learning for LEO satellite networks,which guarantees high level assurance demand services to be prioritized under limited satellite resources while considering the load balancing performance of the satellite networks for low level assurance demand services to ensure the full and effective utilization of satellite resources.An auxiliary path search algorithm is proposed to accelerate the convergence of satellite routing algorithm.Simulation results show that the generated routing strategy can timely process and fully meet the QoS demands of high assurance services while effectively improving the load balancing performance of the link.展开更多
基金supported by the National Key Scientific Instrument and Equipment Development Project(61827801).
文摘The fifth-generation (5G) communication requires a highly accurate estimation of the channel state information (CSI)to take advantage of the massive multiple-input multiple-output(MIMO) system. However, traditional channel estimation methods do not always yield reliable estimates. The methodology of this paper consists of deep residual shrinkage network (DRSN)neural network-based method that is used to solve this problem.Thus, the channel estimation approach, based on DRSN with its learning ability of noise-containing data, is first introduced. Then,the DRSN is used to train the noise reduction process based on the results of the least square (LS) channel estimation while applying the pilot frequency subcarriers, where the initially estimated subcarrier channel matrix is considered as a three-dimensional tensor of the DRSN input. Afterward, a mixed signal to noise ratio (SNR) training data strategy is proposed based on the learning ability of DRSN under different SNRs. Moreover, a joint mixed scenario training strategy is carried out to test the multi scenarios robustness of DRSN. As for the findings, the numerical results indicate that the DRSN method outperforms the spatial-frequency-temporal convolutional neural networks (SF-CNN)with similar computational complexity and achieves better advantages in the full SNR range than the minimum mean squared error (MMSE) estimator with a limited dataset. Moreover, the DRSN approach shows robustness in different propagation environments.
文摘Hypersonic Glide Vehicles(HGVs)are advanced aircraft that can achieve extremely high speeds(generally over 5 Mach)and maneuverability within the Earth's atmosphere.HGV trajectory prediction is crucial for effective defense planning and interception strategies.In recent years,HGV trajectory prediction methods based on deep learning have the great potential to significantly enhance prediction accuracy and efficiency.However,it's still challenging to strike a balance between improving prediction performance and reducing computation costs of the deep learning trajectory prediction models.To solve this problem,we propose a new deep learning framework(FECA-LSMN)for efficient HGV trajectory prediction.The model first uses a Frequency Enhanced Channel Attention(FECA)module to facilitate the fusion of different HGV trajectory features,and then subsequently employs a Light Sampling-oriented Multi-Layer Perceptron Network(LSMN)based on simple MLP-based structures to extract long/shortterm HGV trajectory features for accurate trajectory prediction.Also,we employ a new data normalization method called reversible instance normalization(RevIN)to enhance the prediction accuracy and training stability of the network.Compared to other popular trajectory prediction models based on LSTM,GRU and Transformer,our FECA-LSMN model achieves leading or comparable performance in terms of RMSE,MAE and MAPE metrics while demonstrating notably faster computation time.The ablation experiments show that the incorporation of the FECA module significantly improves the prediction performance of the network.The RevIN data normalization technique outperforms traditional min-max normalization as well.
基金supported by the Natural Science Basic Research Prog ram of Shaanxi(2022JQ-593)。
文摘To address the shortcomings of single-step decision making in the existing deep reinforcement learning based unmanned aerial vehicle(UAV)real-time path planning problem,a real-time UAV path planning algorithm based on long shortterm memory(RPP-LSTM)network is proposed,which combines the memory characteristics of recurrent neural network(RNN)and the deep reinforcement learning algorithm.LSTM networks are used in this algorithm as Q-value networks for the deep Q network(DQN)algorithm,which makes the decision of the Q-value network has some memory.Thanks to LSTM network,the Q-value network can use the previous environmental information and action information which effectively avoids the problem of single-step decision considering only the current environment.Besides,the algorithm proposes a hierarchical reward and punishment function for the specific problem of UAV real-time path planning,so that the UAV can more reasonably perform path planning.Simulation verification shows that compared with the traditional feed-forward neural network(FNN)based UAV autonomous path planning algorithm,the RPP-LSTM proposed in this paper can adapt to more complex environments and has significantly improved robustness and accuracy when performing UAV real-time path planning.
基金supported by the National Natural Science Foundation of China (12072365)the Natural Science Foundation of Hunan Province of China (2020JJ4657)。
文摘It is important to calculate the reachable domain(RD)of the manned lunar mission to evaluate whether a lunar landing site could be reached by the spacecraft. In this paper, the RD of free return orbits is quickly evaluated and calculated via the classification and regression neural networks. An efficient databasegeneration method is developed for obtaining eight types of free return orbits and then the RD is defined by the orbit’s inclination and right ascension of ascending node(RAAN) at the perilune. A classify neural network and a regression network are trained respectively. The former is built for classifying the type of the RD, and the latter is built for calculating the inclination and RAAN of the RD. The simulation results show that two neural networks are well trained. The classification model has an accuracy of more than 99% and the mean square error of the regression model is less than 0.01°on the test set. Moreover, a serial strategy is proposed to combine the two surrogate models and a recognition tool is built to evaluate whether a lunar site could be reached. The proposed deep learning method shows the superiority in computation efficiency compared with the traditional double two-body model.
基金Supported by the National Natural Science Foundation of China (11161027)。
文摘Projective synchronization problems of a drive system and a particular response network were investigated,where the drive system is an arbitrary system with n+1 dimensions;it may be a linear or nonlinear system,and even a chaotic or hyperchaotic system,the response network is complex system coupled by N nodes,and every node is showed by the approximately linear part of the drive system.Only controlling any one node of the response network by designed controller can achieve the projective synchronization.Some numerical examples were employed to verify the effectiveness and correctness of the designed controller.
文摘The burgeoning development of nanomedicine has provided state-of-the-art technologies and innovative methodologies for contemporary biomedical research,presenting unprecedented opportunities for resolving pivotal biomedical challenges.Nanomaterials possess distinctive structures and properties.Through the exploration of the fabrication of emerging nanomedicines,multiple functions can be integrated to enable more precise diagnosis and treatment,thereby compensating for the limitations of traditional treatment modalities.Among various substances,polyphenols are natural organic compounds classified as plant secondary metabolites and are ubiquitously present in vegetables,teas,and other plants.Polyphenols are rich in active groups,including hydroxyl,carboxyl,amino,and conjugated double bonds.They exhibit robust adhesion,antioxidant,anti-inflammatory,and antibacterial biological activities and are extensively applied in pharmaceutical formulations.Additionally,polyphenols are characterized by their low cost,ready availability,and do not necessitate intricate chemical synthesis processes.Nevertheless,when natural polyphenol-based nanomedicines are utilized in isolation,they encounter several issues.These include poor water solubility,feeble stability,low bioavailability,the requirement for high dosages,and difficulties in precisely reaching the site of action.To address these concerns,researchers have developed nanomedicines by combining metal ions and functional ligands through metal coordination strategies.Nanomaterials,owing to their unique electronic and optical properties,have been successfully introduced into the realm of medical biology.Nano preparations not only enhance the stability of natural products but also endow them with targeting capabilities,thus enabling precise drug delivery.Polyphenols can further synergize with metal ions,anti-cancer drugs,or photosensitizers via supramolecular interactions to achieve multifunctional synergistic therapies,such as targeted drug delivery,efficacy enhancement,and the construction of engineering scaffolds.Metal-Polyphenol Coordination Polymers(MPCPs),composed of metal ions and phenolic ligands,are regarded as ideal nanoplatforms for disease diagnosis and treatment.In recent years,MPCPs have attracted extensive research in the biomedical field on account of their advantages,including facile synthesis,adjustable structure,excellent biocompatibility,and pH responsiveness.In this review,the classification and preparation strategies of MPCPs were systematically presented.Subsequently,their remarkable achievements in biomedical domains,such as bioimaging,biosensing,drug delivery,tumor therapy,and antimicrobial applications were highlighted.Finally,the principal limitations and prospects of MPCPs were comprehensi vely discussed.
文摘Human disturbance activities is one of the main reasons for inducing geohazards.Ecological impact assessment metrics of roads are inconsistent criteria and multiple.From the perspective of visual observation,the environment damage can be shown through detecting the uncovered area of vegetation in the images along road.To realize this,an end-to-end environment damage detection model based on convolutional neural network is proposed.A 50-layer residual network is used to extract feature map.The initial parameters are optimized by transfer learning.An example is shown by this method.The dataset including cliff and landslide damage are collected by us along road in Shennongjia national forest park.Results show 0.4703 average precision(AP)rating for cliff damage and 0.4809 average precision(AP)rating for landslide damage.Compared with YOLOv3,our model shows a better accuracy in cliff and landslide detection although a certain amount of speed is sacrificed.
文摘Objective Traditional Chinese medicine(TCM)constitutes a valuable cultural heritage and an important source of antitumor compounds.Poria(Poria cocos(Schw.)Wolf),the dried sclerotium of a polyporaceae fungus,was first documented in Shennong’s Classic of Materia Medica and has been used therapeutically and dietarily in China for millennia.Traditionally recognized for its diuretic,spleen-tonifying,and sedative properties,modern pharmacological studies confirm that Poria exhibits antioxidant,anti-inflammatory,antibacterial,and antitumor activities.Pachymic acid(PA;a triterpenoid with the chemical structure 3β-acetyloxy-16α-hydroxy-lanosta-8,24(31)-dien-21-oic acid),isolated from Poria,is a principal bioactive constituent.Emerging evidence indicates PA exerts antitumor effects through multiple mechanisms,though these remain incompletely characterized.Neuroblastoma(NB),a highly malignant pediatric extracranial solid tumor accounting for 15%of childhood cancer deaths,urgently requires safer therapeutics due to the limitations of current treatments.Although PA shows multi-mechanistic antitumor potential,its efficacy against NB remains uncharacterized.This study systematically investigated the potential molecular targets and mechanisms underlying the anti-NB effects of PA by integrating network pharmacology-based target prediction with experimental validation of multi-target interactions through molecular docking,dynamic simulations,and in vitro assays,aimed to establish a novel perspective on PA’s antitumor activity and explore its potential clinical implications for NB treatment by integrating computational predictions with biological assays.Methods This study employed network pharmacology to identify potential targets of PA in NB,followed by validation using molecular docking,molecular dynamics(MD)simulations,MM/PBSA free energy analysis,RT-qPCR and Western blot experiments.Network pharmacology analysis included target screening via TCMSP,GeneCards,DisGeNET,SwissTargetPrediction,SuperPred,and PharmMapper.Subsequently,potential targets were predicted by intersecting the results from these databases via Venn analysis.Following target prediction,topological analysis was performed to identify key targets using Cytoscape software.Molecular docking was conducted using AutoDock Vina,with the binding pocket defined based on crystal structures.MD simulations were performed for 100 ns using GROMACS,and RMSD,RMSF,SASA,and hydrogen bonding dynamics were analyzed.MM/PBSA calculations were carried out to estimate the binding free energy of each protein-ligand complex.In vitro validation included RT-qPCR and Western blot,with GAPDH used as an internal control.Results The CCK-8 assay demonstrated a concentration-dependent inhibitory effect of PA on NB cell viability.GO analysis suggested that the anti-NB activity of PA might involve cellular response to chemical stress,vesicle lumen,and protein tyrosine kinase activity.KEGG pathway enrichment analysis suggested that the anti-NB activity of PA might involve the PI3K/AKT,MAPK,and Ras signaling pathways.Molecular docking and MD simulations revealed stable binding interactions between PA and the core target proteins AKT1,EGFR,SRC,and HSP90AA1.RT-qPCR and Western blot analyses further confirmed that PA treatment significantly decreased the mRNA and protein expression of AKT1,EGFR,and SRC while increasing the HSP90AA1 mRNA and protein levels.Conclusion It was suggested that PA may exert its anti-NB effects by inhibiting AKT1,EGFR,and SRC expression,potentially modulating the PI3K/AKT signaling pathway.These findings provide crucial evidence supporting PA’s development as a therapeutic candidate for NB.
基金supported by the National Nature Science Foundation of China(71771201,72531009,71973001)the USTC Research Funds of the Double First-Class Initiative(FSSF-A-240202).
文摘Social interaction with peer pressure is widely studied in social network analysis.Game theory can be utilized to model dynamic social interaction,and one class of game network models assumes that people’s decision payoff functions hinge on individual covariates and the choices of their friends.However,peer pressure would be misidentified and induce a non-negligible bias when incomplete covariates are involved in the game model.For this reason,we develop a generalized constant peer effects model based on homogeneity structure in dynamic social networks.The new model can effectively avoid bias through homogeneity pursuit and can be applied to a wider range of scenarios.To estimate peer pressure in the model,we first present two algorithms based on the initialize expand merge method and the polynomial-time twostage method to estimate homogeneity parameters.Then we apply the nested pseudo-likelihood method and obtain consistent estimators of peer pressure.Simulation evaluations show that our proposed methodology can achieve desirable and effective results in terms of the community misclassification rate and parameter estimation error.We also illustrate the advantages of our model in the empirical analysis when compared with a benchmark model.
基金Supported by the National Natural Science Foundation of China(11971458,11471310)。
文摘In this paper,we propose a neural network approach to learn the parameters of a class of stochastic Lotka-Volterra systems.Approximations of the mean and covariance matrix of the observational variables are obtained from the Euler-Maruyama discretization of the underlying stochastic differential equations(SDEs),based on which the loss function is built.The stochastic gradient descent method is applied in the neural network training.Numerical experiments demonstrate the effectiveness of our method.
文摘In the field of image processing,the analysis of Synthetic Aperture Radar(SAR)images is crucial due to its broad range of applications.However,SAR images are often affected by coherent speckle noise,which significantly degrades image quality.Traditional denoising methods,typically based on filter techniques,often face challenges related to inefficiency and limited adaptability.To address these limitations,this study proposes a novel SAR image denoising algorithm based on an enhanced residual network architecture,with the objective of enhancing the utility of SAR imagery in complex electromagnetic environments.The proposed algorithm integrates residual network modules,which directly process the noisy input images to generate denoised outputs.This approach not only reduces computational complexity but also mitigates the difficulties associated with model training.By combining the Transformer module with the residual block,the algorithm enhances the network's ability to extract global features,offering superior feature extraction capabilities compared to CNN-based residual modules.Additionally,the algorithm employs the adaptive activation function Meta-ACON,which dynamically adjusts the activation patterns of neurons,thereby improving the network's feature extraction efficiency.The effectiveness of the proposed denoising method is empirically validated using real SAR images from the RSOD dataset.The proposed algorithm exhibits remarkable performance in terms of EPI,SSIM,and ENL,while achieving a substantial enhancement in PSNR when compared to traditional and deep learning-based algorithms.The PSNR performance is enhanced by over twofold.Moreover,the evaluation of the MSTAR SAR dataset substantiates the algorithm's robustness and applicability in SAR denoising tasks,with a PSNR of 25.2021 being attained.These findings underscore the efficacy of the proposed algorithm in mitigating speckle noise while preserving critical features in SAR imagery,thereby enhancing its quality and usability in practical scenarios.
基金National Key Research and Development Program(2021YFB2900604)。
文摘Low Earth orbit(LEO)satellite networks exhibit distinct characteristics,e.g.,limited resources of individual satellite nodes and dynamic network topology,which have brought many challenges for routing algorithms.To satisfy quality of service(QoS)requirements of various users,it is critical to research efficient routing strategies to fully utilize satellite resources.This paper proposes a multi-QoS information optimized routing algorithm based on reinforcement learning for LEO satellite networks,which guarantees high level assurance demand services to be prioritized under limited satellite resources while considering the load balancing performance of the satellite networks for low level assurance demand services to ensure the full and effective utilization of satellite resources.An auxiliary path search algorithm is proposed to accelerate the convergence of satellite routing algorithm.Simulation results show that the generated routing strategy can timely process and fully meet the QoS demands of high assurance services while effectively improving the load balancing performance of the link.
